Computer Science

Cooperation and Confrontation in Crowd Intelligence

ZHU Di-di, WU Chao

Computer Science. 2022, 49 (11A): 210900249-7. doi:10.11896/jsjkx.210900249

Abstract

PDF(2277KB) ( 496 )

References | Related Articles | Metrics

Crowd intelligence has rich connotations and denotations.Its algorithms include both the early algorithms based on the characteristics of biological groups(particle swarm optimization,ant colony algorithm,etc.) and the later large-scale crowd algorithms based on network interconnection(multi-agent system,crowd intelligence perception,federated learning,etc.).The core idea of these crowd intelligence algorithms is cooperation or confrontation.Collaboration can combine the limited intelligence of individuals into the powerful intelligence of the group.However,collaboration itself has certain limitations,which may lead to the over-dependence between individuals and the unfairness of the system.Confrontation can overcome this limitation,and its basic idea is that individuals seek their maximum interests through the game.Therefore,cooperation and confrontation are indispensable.It is the inevitable development trend of a crowd intelligence to promote cooperation with confrontation,and to build a crowd intelligence ecology in which cooperation and confrontation coexist.This paper mainly focuses on the cooperation and confrontation methods of crowd intelligence algorithms,expounds on the classical crowd intelligence algorithms,and prospects the next development direction of emerging crowd intelligence algorithms.

Survey of Deep Learning Technologies for Financial Technology

ZHOU Fan, CHEN Xiao-die, ZHONG Ting, WU Jin

Computer Science. 2022, 49 (11A): 210900016-17. doi:10.11896/jsjkx.210900016

Abstract

PDF(2406KB) ( 528 )

References | Related Articles | Metrics

In recent years,deep learning techniques have been widely applied in addressing various problems in financial technology(Fintech) and have attracted increasing attention from both academia and business.Researchers utilize deep learning techniques for mining and analyzing financial data while finding the economic patterns behind tremendous data.Deep learning outperforms traditional statistical machine learning models in a range of crucial financial applications,including market movement prediction,trading strategy improvement,financial text processing,etc.To facilitate the development of Fintech and the deployment of new deep learning techniques,this paper provides a comprehensive survey of the deep learning-based Fintech studies published in recent years.Our survey focuses on the most recent advances in Fintech and provides a roadmap of financial problems as well as corresponding solutions.To this end,we investigate the widely used methodologies in finance data mining and summarize the popular deep models in Fintech data learning.Besides,we propose a taxonomy that categorizes existing Fintech research into ten well-studied applications in the literature.Subsequently,we systematically review the state-of-the-art deep learning methods and provide insights on the improvement for future endeavors.Finally,the pros and cons of existing research are summarized,followed by outlining the trend,open challenges,and opportunities in the Fintech research community.

Analysis of Technology Trends Based on Deep Learning and Text Measurement

WEI Ru-ming, CHEN Ruo-yu, LI Han, LIU Xu-hong

Computer Science. 2022, 49 (11A): 211100119-6. doi:10.11896/jsjkx.211100119

Abstract

PDF(3429KB) ( 403 )

References | Related Articles | Metrics

Traditionally,technical trend analysis tasks need to be done by experienced analysts,involving a lot of literature review and data analysis work,which is time-consuming and labor-intensive.Facing the above problems,this paper proposes a technology trend analysis model based on deep learning and text measurement,and a domain specific named entity recognition(NER) algorithm based on the BERT_BiLSTM_CRF model is designed with optimized masking mechanism.Taking news and literatures texts in the field of integrated circuit as data set,a comparative study between BiLSTM_CRF,BERT_BiGRU_CRF and the optimized BERT_BiLSTM_CRF^* model proposed in this paper is carried out.The performance of NER is compared and analyzed.Compared with other algorithms,the proposed algorithm reaches 88.6%(measured by F1 value),laying the foundation for technical trend analysis.Based on the characteristics of knowledge graphs that relationships can be naturally expressed,an innovative method that combines knowledge graphs with text measurement technology is proposed,and the results of technical trend analysis are visualized from various perspectives,and ultimately assist analysts to carry out intelligent analysis of technical trends.

Survey of Research on Extended Models of Pre-trained Language Models

Abudukelimu ABULIZI, ZHANG Yu-ning, Alimujiang YASEN, GUO Wen-qiang, Abudukelimu HALIDANMU

Computer Science. 2022, 49 (11A): 210800125-12. doi:10.11896/jsjkx.210800125

Abstract

PDF(2450KB) ( 459 )

References | Related Articles | Metrics

In recent years,the proposal of Transformer neural network has greatly promoted the development of pre-training technology.At present,pre-training models based on deep learning have become a research hotspot in the field of natural language processing.Since the end of 2018,BERT has achieved optimal results in multiple natural language processing tasks.A series of improved pre-training models based on BERT have been proposed one after another,and pre-training model extension models designed for various scenarios have also appeared.The expansion of pre-training models from single-language to tasks such as cross-language,multi-modality,and light-weighting has enabled natural language processing to enter a new era of pre-training.This paper mainly summarizes the research methods and research conclusions of lightweight pre-training models,knowledge-incorporated pre-training models,cross-modal pre-training language models and cross-language pre-training language models,as well as the main challenges faced by the pre-training model expansion model.In summary,four research trends for the possible development of extended models are proposed to provide theoretical support for beginners who learn and understand pre-training models.

Optimal Order Acceptance Decision Based on After-state Reinforcement Learning

QIAN Jing, WU Ke-yu, CHEN Chao, HU Xing-chen

Computer Science. 2022, 49 (11A): 210800261-9. doi:10.11896/jsjkx.210800261

Abstract

PDF(3720KB) ( 384 )

References | Related Articles | Metrics

As the diversification of customer demand increases,the make-to-order(MTO) model,i.e.,adapting production scheme according to customers’ orders,has attracted increasingly more attention from industry.How to determine whether to accept incoming orders according to the limited production capacity and order status of the enterprise,which is crucial for the enterprise to improve profits.On the basis of the traditional order acceptance problems,this paper proposes a more complete model.Besides the traditional model elements(including delayed delivery cost,rejection cost,and production cost),we further consider the order inventory cost,customer priority and others.Moreover,we model the optimal order acceptance problem as a Markov decision process(MDP).In addition,because the classic MDP method relies on solving and estimating high-dimensional state value function,its computation complexity is high.Therefore,in order to reduce the complexity,this paper proves that the optimal strategy based on the state value function in the classical MDP problem can be defined and constructed by the value function based on the after-state equivalent,thus transforming the multi-dimensional control problem into a one-dimensional control problem.At the same time,in order to solve the continuous state space,this paper combines neural network to parameterize the after-state value function,and solves the problem of large state space.Finally,simulation experiments verify the applicability and superiority of the proposed order acceptance strategy model and algorithm.

Sub-BN-Merge Based Bayesian Network Structure Learning Algorithm

ZHONG Kun-hua, CHEN Yu-wen, QIN Xiao-lin

Computer Science. 2022, 49 (11A): 210800172-7. doi:10.11896/jsjkx.210800172

Abstract

PDF(2221KB) ( 451 )

References | Related Articles | Metrics

Aiming at the problem that Bayesian network structure learning method K2 requires to provide accurate prior node order information which is difficult to obtain in practice,and hill-climb algorithm is highly dependent on initial network structure and easy to fall into local optimal,.a sub-BN merge based Bayesian network structure learning algorithm,(Sub-BN-Merge) is proposed in this paper.Firstly,for each node,the Sub-BN-Merge algorithm constructs a sub-net and merges them via voting to get a candidate parent set.Next,based on a scoring criterion,the algorithm searches the temporary optimal parent set of every nodes.Then,we breaks the cycle in the directed graph of the search result to get an directed acyclic graph.At last,further optimization is executed via a heuristic search method with directed acyclic graph as the initial value to get the final Bayesian network structure.Experiment is carried out on small network Asia,medium network Alarm and large network Win95pts.we also analyze the algorithm performance for the missing value situation.Experimental results show the effectiveness of the proposed algorithm.Our Sub-BN-Merge algorithm outperforms the comparison algorithms in term of structural Hamming distance and algorithm correct rate.

Gated Two-tower Transformer-based Model for Predicting Antigenicity of Influenza H1N1

LI Chuan, LI Wei-hua, WANG Ying-hui, CHEN Wei, WEN Jun-ying

Computer Science. 2022, 49 (11A): 211000209-6. doi:10.11896/jsjkx.211000209

Abstract

PDF(2629KB) ( 312 )

References | Related Articles | Metrics

The rapid evolution of influenza virus hemagglutinin protein has led to the continuous production of new virus strains,which may cause seasonal influenza and even global influenza outbreaks.Timely detection of antigen variants is essential for vaccine screening and design.Therefore,a robust predictive model of antigenicity is an effective method to deal with the challenge of vaccines.Various end-to-end feature learning tools provide good feature representation methods for proteomics,but the existing influenza A prediction models cannot effectively extract and utilize features in amino acid sequences.In this paper,a gated two-tower model is designed based on the transformer.By inputting the amino acid sequence of the influenza A virus hemagglutinin protein,two parallel encoders are used to capture the antigenic characteristics from the time and space dimensions of the hemagglutinin protein amino acid sequence,and learn the nonlinear relationship between features and prediction results.In order to reduce the noise in the data,when fusing the features in the time dimension and the space dimension,the weights that measure their relative importance are adaptively obtained through the gate mechanism for selective fusion,and finally the fusion features are used to predict the H1N1 influenza antigen variants.Experimental results on the H1N1 data set show that the use of the model’sexcellent non-linear feature learning ability improves the predictive performance of antigenic variation,and at the same time has good robustness.

Multi-view Distance Metric Learning with Inter-class and Intra-class Density

REN Shuang-yan, GUO Wei, FAN Chang-qi, WANG Zhe, WU Song-yang

Computer Science. 2022, 49 (11A): 211000131-6. doi:10.11896/jsjkx.211000131

Abstract

PDF(2148KB) ( 426 )

References | Related Articles | Metrics

Geometric information can provide prior knowledge and intuitive explanation for classification methods.Observing samples from geometric perspective is a novel method of sample learning,and density is a very intuitive form of geometric information.This paper proposes a multi-view distance metric learning method with inter-class and intra-class density to learn a metric space.In this space,the heterogeneous samples are more scattered,and the homogeneous samples are closer.First,the inter-class density is introduced under the large margin framework,and the samples in the metric space are constrained by minimizing the inter-class density,so as to realize the inter-class dispersion and improve the classification performance.Second,maximize the intra-class density to achieve the effect of similar samples close to each other,so as to achieve intra-class compactness.Finally,to better mine the complementary information of the multi-view samples,the correlation between the views in the metric space is maximized,so that the views can learn from each other adaptively and explore the complementary information among the views.A large number of experimental results on real-world datasets demonstrate the superiority of the proposed method.

Multi-UAV Cooperative Exploring for Large Unknown Indoor Environment Based on Behavior Tree

SHI Dian-xi, SU Ya-qian-wen, LI Ning, SUN Yi-xuan, ZHANG Yong-jun

Computer Science. 2022, 49 (11A): 210900083-11. doi:10.11896/jsjkx.210900083

Abstract

PDF(4482KB) ( 369 )

References | Related Articles | Metrics

This paper proposes a method of using behavior tree framework to schedule multiple UAVs and path planning algorithms for collaborative exploration in a large unknown indoor space without GPS signals.The core of this method is to use the Tracking-D*Lite algorithm to track moving targets in unknown terrain,combined with the Wall-Around algorithm based on the Bug algorithm to navigate the UAV in the unknown indoor environment.Finally,the behavior tree is used to schedule and switch multiple UAVs and these two algorithms.This method is based on ROS and uses Gazebo for simulation and visualization.It designs and implements comparative experiments with other unknown indoor environment exploration methods.Experimental results show that it can effectively complete the exploration task and finally draw the boundary contour map of the entire unknown indoor environment.Once extended to the real world,this method can be applied to dangerous buildings after earthquakes,hazar-dous gas factories,underground mines,or other search and rescue scenarios.

Improved Algorithm for Tabu Search of Graph Coloring Problems

WANG Jian-chang, WANG Shuo, LI Zhuang, JIANG Hua

Computer Science. 2022, 49 (11A): 211000128-5. doi:10.11896/jsjkx.211000128

Abstract

PDF(1983KB) ( 522 )

References | Related Articles | Metrics

The graph coloring problem is an NP-hard problem,which has a wide range of applications in reality,such as register allocation,airport scheduling and so on.Tabu search algorithm is a classic heuristic search algorithm,which is widely used in the algorithm design of graph coloring problems.As a low-level operator,the tabu search algorithm is also commonly used in the design of graph coloring algorithms such as hybrid evolutionary algorithm(HEA),which plays a key role in the performance of the algorithm.Therefore,the improvement of the tabu search algorithm has practical significance for promoting the research of graph coloring algorithm.Aiming at the problem of graph coloring,this paper proposes an improved version of Tabucol+ to enhance the concentration of search.Based on the traditional tabu search strategy,the proposed algorithm introduces a new scoring strategy.Experimental results show that the new algorithm can significantly reduce the number of iterations andsearch time.In some cases,even the improvement of the number of colors has been achieved.

Personalized Dialogue Generation Integrating Sentimental Information

XU Hui, WANG Zhong-qing, LI Shou-shan, ZHANG Min

Computer Science. 2022, 49 (11A): 211100019-6. doi:10.11896/jsjkx.211100019

Abstract

PDF(2473KB) ( 366 )

References | Related Articles | Metrics

Nowadays,more and more attention has been paid to the man-machine dialogue system.However,the current mainstream man-machine dialogue system rarely considers the personalized characteristics of the speaker.An important aspect of the dialogue system is to improve the response quality of dialogue according to the personality of interactive personnel.Personalization is the key to create intelligent dialogue system,which can be well adapted to human life.Emotion is a very important factor in the generation of personalized dialogue.Therefore,a personalized dialogue generation model integrating attribute level emotion is proposed in this paper.The BERT-MRC model is used to extract the emotional and attribute information of character personality and historical dialogue.The improved UNILM neural network model is used to encode character personality and historical dialogue.At the same time,the emotional word information and attribute word information are combined in the coding representation to finally generate a dialogue in line with character personality.Experiments show that the proposed method can effectively improve the quality of personalized dialogue generation and increase the diversity of generated responses.

Online Learning Emotion Recognition Based on Videos

WEI Yan-tao, LUO Jie-lin, HU Mei-jia, LI Wen-hao, YAO Huang

Computer Science. 2022, 49 (11A): 211000049-6. doi:10.11896/jsjkx.211000049

Abstract

PDF(3178KB) ( 413 )

References | Related Articles | Metrics

With the normalization of epidemic prevention and control,online learning has become one of the main forms of daily teaching activities.However,with the large-scale development of online learning activities,the problem of “emotional loss” is increasingly prominent,which has become the main reason for the low completion rate of online learning.Aiming to deal with the above problems,the non-invasive online learning emotion state recognition method using video data is discussed.Firstly,the facial videos and heart rate data of 22 students learning online are collected to construct a bimodal online learning emotion database.Secondly,the frame attention network is used to extract facial expression features from the learning video and recognize the emotional state of online learning,and its recognition accuracy reaches 87.8%.Finally,the application of the video heart rate recognition method in online learning emotion analysis is discussed.Research results show that the heart rate level in the confused state is significant.Starting from learning video data mining,focusing on learning emotion recognition based on facial expressions and video heart rate,which provides a new idea for improving the perception of emotional state in online learning.

Study on Dual Sequence Decision-making for Trucks and Cargo Matching Based on Dual Pointer Network

CAI Yue, WANG En-liang, SUN Zhe, SUN Zhi-xin

Computer Science. 2022, 49 (11A): 210800257-9. doi:10.11896/jsjkx.210800257

Abstract

PDF(2931KB) ( 338 )

References | Related Articles | Metrics

Due to the uneven utilization of road transportation resources in my country,the supply and demand of trucks and cargo become a hot issue today.In order to maximize the utilization of overall transportation resources,the truck and cargo supply-demand matching platform needs to integrate transportation demand and capacity,reduce costs and improve efficiency.The algorithms used by most platforms are usually heuristic algorithms to solve the problem of trucks-cargo matching.Such algorithms have a bottleneck in optimizing when faced with large-scale problems.In response to the above-mentioned problems,this paper transforms the supply-demand matching problem of vehicles and goods into a double sequence decision-making problem for the first time.Based on this,we study an efficient algorithm that is suitable for today’s vehicle and goods supply-demand matching links.First,a mathematical model of trucks-cargo matching is proposed and the model is abstracted as a double sequence decision problem,and then a dual-pointer-network algorithm is innovatively proposed to solve this problem.The experiment uses the Actor-Critic algorithm as the model training framework to train the dual-pointer-network and evaluates the model.Experiments show that the dual-pointer-network’s vehicle-to-cargo matching solution method is equivalent to traditional heuristic algorithms in small problem scales,and surpasses heuristic algorithms in large problem scales.At the same time,the time consumption is greatlyreduced.

Prediction of Antigenic Similarity of Influenza A/H5N1 Virus Based on Attention Mechanism and Ensemble Learning

WANG Ying-hui, LI Wei-hua, LI Chuan, CHEN Wei, WEN Jun-ying

Computer Science. 2022, 49 (11A): 210900032-6. doi:10.11896/jsjkx.210900032

Abstract

PDF(2012KB) ( 324 )

References | Related Articles | Metrics

Influenza A virus can lead to seasonal influenza virus outbreaks or even global outbreaks.Continued and cumulative changes in the hemagglutinin protein of influenza viruses can lead to the antigenic variants that reduce vaccine effectiveness or even cause vaccine failure.Therefore,antigenic similarity prediction is critical for influenza outbreak surveillance and vaccine selection.Although A/H5N1 virus originates in poultry,they can cause pneumonia and multiple organ failure in humans.In view of influenza virus and the antigenic characteristics,this paper designs a neural network model to predict the antigenic similarity between viruses.Specifically,the model represents amino acid sequences based on the K-mer embedding and position specific scoring matrices(PSSM),then integrates the features.Furthermore,integrated deep learning model fused with attention mechanism for antigen similarity prediction.Experimental results show that the model significantly improves the accuracy,precision,F1 and MCC compares with the baseline models.Experimental results show that the model has good robustness and extensibility,and has good application potential in the field of antigenic similarity prediction.

Cross-lingual Term Alignment with Kernel-XGBoost

YU Juan, ZHANG Chen

Computer Science. 2022, 49 (11A): 211000111-6. doi:10.11896/jsjkx.211000111

Abstract

PDF(2599KB) ( 314 )

References | Related Articles | Metrics

Cross-lingual term alignment is a crucial step for cross-lingual text data analysis and knowledge discovery.Current research usually focuses on single-word term alignment and relies heavily on vector space alignment.Therefore,a new Kernel-XGBoost method is proposed for the one-to-many alignment of cross-lingual terms including multi-word terms.Given a cross-lingual parallel corpus,the proposed method obtains synonymous cross-lingual terms in two steps:1) extracting cross-lingual terms and generating candidate term pairs;2) aligning cross-lingual terms based on word embedding.Experiments on Chinese-Spanish and Chinese-French term alignments demonstrate that the proposed method can achieve an accuracy of 80% at Top-5.It can effectively support cross-lingual text mining tasks such as information retrieval,ontology building.

Stance Detection Based on Argument Boundary Recognition

CHEN Zi-zhuo, LIN Xi, WANG Zhong-qing

Computer Science. 2022, 49 (11A): 210800180-5. doi:10.11896/jsjkx.210800180

Abstract

PDF(3282KB) ( 314 )

References | Related Articles | Metrics

In online debates,people often use emotional language to make their points with casual expressions.As a supporting evidence of these points,argument contains more of the author’s stance polarity,so the argument information is of great help to the stance detection.In this paper,we propose a stance detection model of BERT via argument boundary recognition to improve the effect of classification on texts in online debates.We use bidirectional encoder representations from transformers(BERT) to screen the arguments related to the topics from the debate posts.Then we combine the argument information and the text information to predict the stance polarity via BERT.Experiments are carried out on the English online debate dataset,compared with the stance analysis model of BERT using only text information and other machine learning models,the model based on argument boundary recognition has better performance in stance detection.

Empirical Study on the Forecast of Large Stock Dividends of Listed Companies Based on DE-lightGBM

CEN Jian-ming, FENG Quan-xi, ZHANG Li-li, TONG Rui-chao

Computer Science. 2022, 49 (11A): 211000017-7. doi:10.11896/jsjkx.211000017

Abstract

PDF(2816KB) ( 294 )

References | Related Articles | Metrics

Large stock dividends refers to the transfer of a large proportion of shares by listed companies.Aiming at the prediction problem of large stock dividends phenomenon implemented by listed companies,this paper proposes alightGBM based on Differential Evolution algorithm hyperparametric optimization(Named as DE-lightGBM).The model mainly includes two aspects:Firstly,Differential Evolution algorithm is used to adjust the weight of a few categories and the coefficient of regular term in the loss function of lightGBM to deal with the problem of data category imbalance.Secondly,taking F1 and AUC as evaluation indexes,Differential Evolution algorithm is used to optimize the important hyperparametric variables of lightGBM model again to find a group of parameter combinations with the best prediction effect.The numerical results show that the DE-lightGBM has achieved good results,and the F1 and AUC are 0.536 8 and 0.873 4 respectively.DE-lightGBM proposed in this paper can effectively identify the listed companies that will implement stock dividends next year.

Text Classification Based on Knowledge Distillation Model ELECTRA-base-BiLSTM

HUANG Yu-jiao, ZHAN Li-chao, FAN Xing-gang, XIAO Jie, LONG Hai-xia

Computer Science. 2022, 49 (11A): 211200181-6. doi:10.11896/jsjkx.211200181

Abstract

PDF(2970KB) ( 397 )

References | Related Articles | Metrics

Text emotion analysis is often used in word-of-mouth analysis,topic monitoring and public opinion analysis.It is one of the most active research fields of natural language processing.The pre-training language model in deep learning can solve the problems of polysemy,part of speech and its position in text emotion classification task.However,its model is complex and has many parameters,which leads to huge consumption of resources and difficult deployment of the model.To solve the above problems,using the idea of knowledge distillation,using ELECTRA pre-training model as teacher model and BiLSTM as student model,a distillation model based on ELECTRA-base-BiLSTM is proposed.The word vector representation encoded by text “one-hot” is used as the input of distillation model to classify Chinese text emotion.Through experimental verification,the distillation results of seven teacher models including ALBERT-tiny,ALBERT-base,BERT-base,BERT-wwm-ext,ERNIE-1.0,ERNIE-GRAM and ELECTRA-base are compared respectively.It is found that ELECTRA-base-BiLSTM distillation model has the highest accuracy,precision and comprehensive evaluation indicators,and the best emotion classification effect,which can obtain text emotion classification results close to ELECTRA language model.Its classification accuracy is 5.58% higher than that of lightweight shallow network BiLSTM model.This model not only reduces the complexity of ELECTRA model and reduces resource consumption,but also improves the effect of Chinese text emotion classification of lightweight BiLSTM model,which has a certain reference value for the subsequent research of text emotion classification.

Multi-target Regression Method Based on Hypernetwork

SUN Kai-wei, GUO Hao, ZENG Ya-yuan, FANG Yang, LIU Qi-lie

Computer Science. 2022, 49 (11A): 211000205-9. doi:10.11896/jsjkx.211000205

Abstract

PDF(3924KB) ( 357 )

References | Related Articles | Metrics

Multi-target regression(MTR) is a kind of machine learning problem which predicts multiple relevant continuous output targets simultaneously.In MTR,multiple output targets share the same input feature representation,the main challenge of MTR lies in how to effectively explore and utilize the correlations among multiple output targets to improve the prediction accuracy of all output targets.In this paper,a multi-target regression method based on hypernetwork(MTR-HN) is proposed.First,the k-means method is applied to each output target to divide it into multiple clusters.Then,according to the clustering results,MTR problem is transformed into a multi-class multi-label classification problem.Finally,hypernetwork model is utilized to model the multi-class multi-label classification problem,and the final prediction model for MTR is built based on hypernetwork.The main merits of MTR-HN lie in:1)discretizing the output space,can reduce the risk of overfitting;2)hypernetwork can model the inter-target correlations more effectively.Comparative experiments on 18 multi-target regression datasets show that the proposed MTR-HN achieves better prediction performance than existing state-of-the-art multi-target regression methods.

Customs Synonym Recognition Fusing Multi-level Information

LIU Da-wei, CHE Chao, WEI Xiao-peng

Computer Science. 2022, 49 (11A): 210800197-5. doi:10.11896/jsjkx.210800197

Abstract

PDF(2756KB) ( 384 )

References | Related Articles | Metrics

In the text information of customs import and export commodities,different words are often used to describe the chara-cteristics of the same commodity.Recognizing the characteristic synonyms of these commodities can better summarize opinions,and then prevent and control the tax-related risks for commodities with the same characteristics.According to the characteristics of phrases of customs declaration elements,a convolution neural network model fusing multi-level information is proposed,and a Sentence-BERT based on twin and three-level network structure is constructed and trained,which has a better semantic representation of similar element phrases,and makes up for the shortage of discrete and sparse embedded features of short text words in Word2Vec.Multi-size convolution kernel is used to extract different features of keywords.The BiLSTM neural network is used to learn the word order information of element phrases,and the attention mechanism is used to assign the weight of keywords.The full connection layer integrates semantic features of synonyms and keyword features,and is predicted by SoftMax layer.Experiments show that the convolution model fusing multi-level information has better performance than other models.

Improved Ant Colony Algorithm for Solving Multi-objective Unilateral Assembly Line Balancing Problem

WU Xiao-wen, ZHENG Qiao-xian, XU Xin-qiang

Computer Science. 2022, 49 (11A): 210900165-5. doi:10.11896/jsjkx.210900165

Abstract

PDF(2069KB) ( 307 )

References | Related Articles | Metrics

In response to the second type of unilateral assembly line balance in industrial production,it is established with minimal chemical sections under two constraints.In these two constraints,Mathematical model for optimizing the balance loss rate.A feasible solution to the unilateral assembly line balance problem using an improved ant colony algorithm combining ant colony algorithm and simulated annealing algorithm.The algorithm uses the operation selection mechanism and the operation allocation mechanism to select and assign it to a station.In the experiment,simulation examples are used to verify the feasibility of the algorithm,and 8 examples are used to verify the effectiveness of the proposed algorithm for solving the problem,and to produce certain technical method support for actual industrial production.

Rescheduling of Production System Under Interference of Emergency Order

HUANG Peng-peng, ZHAO Chun, GUO Yu

Computer Science. 2022, 49 (11A): 211100193-6. doi:10.11896/jsjkx.211100193

Abstract

PDF(2770KB) ( 405 )

References | Related Articles | Metrics

The rescheduling of all orders is investigated after the insertion of emergency order into the mixed-flow production system.First,according to the product’s technology and equipments used,the similarity between the emergency order and the original virtual cells is calculated.Similar rush orders are then inserted into existing cells and the production resource scheduling scheme is adjusted to prioritise the production of rush orders.In order to reduce the impact of rescheduling on the production system and take into account the efficiency and stability of production,a mathematical model is constructed with the goal of minimizing the total process time and product sequence disturbance for all task orders,and a genetic-ant colony algorithm is designed to solve the problem with the positive feedback of the ant colony algorithm after finding a better solution by the genetic algorithm.Finally,an example is substituted into the constructed model and solved with the help of MATLAB programming.The results show that the method could optimize the allocation of production resources for rescheduling and ensure the efficiency and stability of enterprise production.

Multi-armed Bandit Model Based on Time-variant Budgets

LIN Bao-ling, JIA Ri-heng, LIN Fei-long, ZHENG Zhong-long, LI Ming-lu

Computer Science. 2022, 49 (11A): 210800212-6. doi:10.11896/jsjkx.210800212

Abstract

PDF(2161KB) ( 277 )

References | Related Articles | Metrics

Many budget-related multi-armed bandit models have been proposed,but the practical problems they can solve are limi-ted,that is,they must all be subject to a total budget limit.Therefore,this paper proposes a multi-armed bandit model based on time-variant budgets,which can break this limitation and be used to solve other practical problems.The model captures the situation where the learner’s actions for each round are limited by the corresponding round budget.More specifically,at each round,the player is required to choose to pull L(L≥1) arms(L is not a fixed value) within the budget limits of that round.The player’sgoal is to maximize the total average reward within the budget limits of each round.According to this model,a dynamic programming algorithm based on confidence bound is proposed.The algorithm takes advantage of the characteristics of the model,takes the confidence upper bound of the empirical average reward of the arm as the basis for each round,and then uses the dynamic programming algorithm to perform the arm pull operation.In this paper,the concept of regret is introduced,and it is deduced theoretically that there is a relationship between the upper bound of regret and the sum of budget.Finally,the feasibility of the proposed algorithm is verified by comparing the proposed algorithm with other traditional budget-limited multi-armed bandit algorithms(ε-first,KUBE,BTS) under different scenarios.

EGOS-DST:Efficient Schema-guided Approach to One-step Dialogue State Tracking for Diverse Expressions

ZHU Ruo-chen, YANG Chang-chun, ZHANG Deng-hui

Computer Science. 2022, 49 (11A): 210900246-7. doi:10.11896/jsjkx.210900246

Abstract

PDF(2506KB) ( 296 )

References | Related Articles | Metrics

Recent dialogue state tracking works have focused on the hybrid approach to balance the two extreme methods(i.e.,over-reliance on ontology and complete abandoning ontology).However,some special phenomena are ignored in these works.For instant,value sharing and recommendation acceptance.In addition,the widely used slot gate mechanism makes it difficult for the model to process slots in parallel and the mechanism also propagates errors to the slot value generation steps.This paper proposes a new hybrid approach that deals with four different phenomena,namely diverse value,unseen value,value sharing and recommendation acceptance.By modifying the candidate value set and the model input,our model can parallelly process slots in one step and no longer depend on the slot gate.Experimental results indicate that the model achieves 57.7% and 59.5% joint goal accuracy on the English dataset MultiWOZ 2.2 and 2.3,respectively,and reaches 68.1% on the Chinese dataset RiSAWOZ,with only 10ms infer time.Finally,the robustness of the model is analyzed.The results on MultiWOZ 2.2 show that the joint target accuracy rate is 55.4% when the recommendation error rate reaches 15%.

Hybrid Particle Swarm Optimization Algorithm Based on Hierarchical Learning and Different Evolution for Solving Capacitated Vehicle Routing Problem

CHEN Ying, HUANG Pei-xuan, CHEN Jin-ping, WANG Zu-yi, SHEN Ying-shan, FAN Xiao-mao

Computer Science. 2022, 49 (11A): 210800271-7. doi:10.11896/jsjkx.210800271

Abstract

PDF(2519KB) ( 328 )

References | Related Articles | Metrics

The purpose of the vehicle routing problem(VRP) is to search the service route of each vehicle,so as to minimize the sum of driving distances in the case of completing all of the distribution tasks.CVRP,a classical combinatorial optimization problem in operations research,belongs to NP-hard problem and has high theoretical significance and practical value.In order to solve this problem,a hybrid particle swarm optimization algorithm based on hierarchical learning and different evolution(DE-HSLPSO) is proposed.First,the hierarchical learning strategy is introduced and the population particles are divided into three layers according to their fitness values and number of iterations.Secondly,the social learning mechanism is introduced in the evolution of the first two layers of particles,while particles in the third layer carry out differential evolution which effectively increases the diversity of particles,thus expanding the space and jumping out of local optimal.Simulation experiment whose examples are taken from the classical CVRP data sets explores the impact of each part of DE-HSLPSO on the overall performance.It is found that both hierarchical strategy and differential evolution can improve the overall performance of the algorithm.In addition,DE-HSLPSO and other algorithms are tested on seven benchmark examples.With comprehensive comparison of time and optimal solution,the result shows that the solution performance of DE-HSLPSO is better than that of other algorithms.

Study on Evolution of Sentiment-Topic of Internet Reviews with Time in Emergencies

SHI Wei, FU Yue

Computer Science. 2022, 49 (11A): 211000193-6. doi:10.11896/jsjkx.211000193

Abstract

PDF(2557KB) ( 290 )

References | Related Articles | Metrics

The analysis of sentiment topic evolution is of great value to the control of network public opinion in emergencies.According to the dynamic characteristics of sentiment topics,this paper constructs a sentiment topic model based on LDA,analyzes the evolution of sentiment topics with time through the joint modeling of time,topic and sentiment,deduces the reasoning algorithm based on Gibbs sampling process,and finally puts forward the analysis results of product reviews and microblog emergency data sets,which shows that the joint model has good accuracy and good applicability in the process of time evolution.

Study on Risk Control Model of Selective Ensemble Algorithm Based on Hierarchical Clustering and Simulated Annealing

WANG Mao-guang, JI Hao-yue, WANG Tian-ming

Computer Science. 2022, 49 (11A): 210800105-7. doi:10.11896/jsjkx.210800105

Abstract

PDF(2253KB) ( 380 )

References | Related Articles | Metrics

Eensemble learning model can effectively solve the problems of single model structure,stability and weak predictive ability.However,due to the complexity of its structure,problems such as low operating efficiency and excessive storage cost often occur.Selective ensemble algorithms are often used to optimize ensemble learning models to solve these problems.The currently proposed selective ensemble algorithm still has the phenomenon of insufficient operating effect and efficiency improvement.In order to make up for these shortcomings,a selective ensemble algorithm based on the stacking ensemble framework is proposed.It mainly uses the agglomerated hierarchical clustering(AHC) algorithm and the metropolis criterion of simulated annealing to select the type and number of base learners.In terms of empirical analysis,domestic and foreign online loan data are used separately to build the model.Experimental results prove that the selective ensemble model of AHC-Metropolis can effectively improve the computational efficiency,predictive ability,stability and generalization ability.It is helpful for regulating the order of the Internet financial industry,assist in financial supervision tasks,and provide an effective basis for establishing our country’s financial risk control management system and guaranteeing national financial security.

Survey of Community Detection in Complex Network

PAN Yu, WANG Shuai-hui, ZHANG Lei, HU Gu-yu, ZOU Jun-hua, WANG Tian-feng, PAN Zhi-song

Computer Science. 2022, 49 (11A): 210800144-11. doi:10.11896/jsjkx.210800144

Abstract

PDF(3022KB) ( 434 )

References | Related Articles | Metrics

Community structure is an important potential feature that exists widely in complex networks.As a key task of network analysis,mining the community structure has important theoretical and practical significance for exploring the potential characteristics,understanding the network organization structure,and discovering the hidden rules and interaction pattern.This paper introduces the background and significance of community detection,and summarizes and combs the methods of community detection from two aspects:static network community detection and dynamic network community detection.Among them,the community detection methods of static network include community detection based on division,community detection based on hierarchical clustering,community detection based on modularity,community detection based on non-negative matrix factorization and community detection based on deep learning.Dynamic network community detection methods include incremental clustering community detection and evolutionary clustering community detection.This paper also introduces the commonly used evaluation metrics of community detection.Finally,some challenges faced by community detection and the future development direction are discussed.

Data Fusion Method of Network Collaborative Manufacturing Based on Rule Chain

HU Chu-yang, LIU Xian-hui, ZHAO Wei-dong

Computer Science. 2022, 49 (11A): 220300175-7. doi:10.11896/jsjkx.220300175

Abstract

PDF(5118KB) ( 318 )

References | Related Articles | Metrics

The efficient organization and utilization of manufacturing resource data with effective data fusion to extract more beneficial information is a hot research topic in the field of intelligent manufacturing today.Moreover,the rule chain technology based on event flow is emerging,and its high degree of freedom provides the possibility of combining with data fusion.In view of the problems that there are few manufacturing resource organization models,the application scope of data fusion models is governed within the same architecture system,and the combination with rule chains is less studied,we model the organization method of complex manufacturing resources,improve the scheduling process based on MROM-VMC,summarize the manufacturing resource data storage chain structure,and propose a rule chain-based data fusion for the data processing link in the data chain.A rule-based data fusion method is proposed for the data processing link in the data chain to handle a large amount of homogeneous and heterogeneous sensor data,which is finally validated in the data processing link in the network collaborative manufacturing resource platform.It improves the efficiency of manufacturing resource data utilization and the operability of the data fusion method,and provides users with auxiliary decision support.

Ranking and Recognition of Influential Nodes Based on k-shell Entropy

YUAN Hui-lin, FENG Chong

Computer Science. 2022, 49 (11A): 210800177-5. doi:10.11896/jsjkx.210800177

Abstract

PDF(3741KB) ( 338 )

References | Related Articles | Metrics

The spreading capacity of nodes has been one of the most attractive problems in the field of complex networks.Due to the large size of nodes in network,researchers want to find accurate measures to estimate the spreading capacity of nodes.In this paper,a new method is proposed based on the basic concepts of information theory and k-shell,which measures the spreading capacity of nodes according to the topological information of their locations in the network.Experimental results show that the proposed method is more effective than other similar methods,and can effectively avoid the “rich club phenomenon” of k-shell method.

Dynamic and Static Relationship Fusion of Multi-source Health Perception Data for Disease Diagnosis

HUO Tian-yuan, GU Jing-jing

Computer Science. 2022, 49 (11A): 211100241-9. doi:10.11896/jsjkx.211100241

Abstract

PDF(3300KB) ( 304 )

References | Related Articles | Metrics

Disease diagnosis is a field of electronic health record data mining where lots of researchers are interested in,and it is also an important link to realize the intellectualization of medical diagnosis.However,due to the diversity of data sources,complex data structure and potential correlation among different types of health sensing data,there is a problem of how to fuse heterogeneous data in the process of feature extraction and data mining.Therefore,comprehensively considering clinical sensing data,personal physical record data and relationship data between diseases,and mining the latent relevant features can make the diagnosis of multi-category diseases more accurate.Dynamic and static relationship fusion of multi-source health perception data for disease diagnosis(DSRF) is proposed.Firstly,the dynamic and static relationship fusion algorithm is used to extract data correlation features and solve the heterogeneity of dynamic clinical sensing time series data and static personal physical condition data.Then the dependency matrix of multi-category diseases is calculated to extract the correlations among diseases.Finally,various health sen-sing data is fused based on the gated recurrent unit network.The comprehensive analysis of multi-source heterogeneous data is completed after the above three steps.Experimental results on the real-world American MIMIC-III clinical dataset show that the proposed model outperforms state-of-the-art models and is able to diagnose multiple categories of diseases accurately.

Community Discovery Method Based on Influence of Core Nodes

YUAN Hui-lin, HAN Zhen, FENG Chong, HUANG Bi, LIU Jun-tao

Computer Science. 2022, 49 (11A): 211100002-7. doi:10.11896/jsjkx.211100002

Abstract

PDF(3274KB) ( 332 )

References | Related Articles | Metrics

Community discovery is a hot topic in the field of complex networks.Many local community detection algorithms have been proposed to quickly discover high-quality communities,but most of them have seed-dependent or stability problems.Some algorithms try to accurately find the seed nodes according to the topology characteristics of the core nodes that they are highly surrounded by neighbors and far away from each other to avoid the above problems.But the calculation of distance makes its time complexity is high.In this paper,a community detection method based on influence of core nodes(CDIC) is proposed.This me-thod first searches for all possible core nodes according to the topological characteristics of core nodes and network adjacency information.Then it uses the higher influential of true core nodes and the idea of label propagation to expand the communities and eliminate nodes wrongly selected as the core to avoid the seed-dependent problems.Besides,the calculation without distance also ensures low time complexity.Finally,a community attraction to nodes based on the similarity theory is proposed to merge specific nodes to ensure the stability of the results.The normalized mutual information and purity of the proposed method,6 classic algorithms and 2 algorithms proposed in recent years are compared on 64 artificial networks and 4 real networks.The results show the effectiveness of CDIC.

Mining Spatial co-location Pattern with Dominant Feature

XIONG Kai-fang, CHEN Hong-mei, WANG Li-zhen, XIAO Qing

Computer Science. 2022, 49 (11A): 211000126-7. doi:10.11896/jsjkx.211000126

Abstract

PDF(3167KB) ( 327 )

References | Related Articles | Metrics

A spatial co-location pattern is a subset of spatial features whose instances frequently locate together in the neighborhood.Traditional co-location pattern does not distinguish the importance of features in the pattern,and ignores the dominant relationship among features.The co-location pattern with dominant feature considers the inequality of features in the pattern,and analyzes the dominant relationship among features,which can be used in many applications.However,the existing methods for mining co-location pattern with dominant feature do not comprehensively consider the possible tendency and influence intensity of one feature dominating other features from the perspective of features’ instances distribution,so that the dominant relationship among features is not properly revealed.This paper first analyzes the spatial distribution of features’ instances in a co-location pattern,proposes the pattern dominance index to measure the possible tendency of a feature dominating other features in a pattern,and proposes the dominant influence index to measure the influence intensity of the dominance tendency.Based on the two new measures,the dominant feature mining of co-location pattern is proposed.Then an efficient algorithm for mining co-location pattern with dominant feature is proposed by optimizing the calculation of new measures.A large number of experiments on real data sets and synthetic data sets verify that the proposed method can effectively identify the dominant feature in a co-location pattern,and it can efficiently mine co-location patterns with dominant feature.

Novel College Entrance Filling Recommendation Algorithm Based on Score Line Prediction andMulti-feature Fusion

WANG Ze-qing, JI Sheng-peng, LI Xin, ZHAO Zi-xuan, WANG Peng-xu, HAN Xiao-song

Computer Science. 2022, 49 (11A): 211100266-7. doi:10.11896/jsjkx.211100266

Abstract

PDF(2646KB) ( 727 )

References | Related Articles | Metrics

In recent years,as the number of high school graduates growing,the demand of college entrance filling is increasing.But faced with massive amounts of college entrance data,students always cannot make reasonable decisions conform to their own will in a short time,resulting in filling accident.To address this issue,on the basis of crawling college entrance history data by web spider,a novel college entrance filling recommendation algorithm based on score line prediction and multi-feature fusion(Reco-PMF) is proposed.Firstly,BP neural network is applied to predict all the colleges admission lines of current year.Then,combining with colleges’ rankings,an admission probability algorithm is constructed on the basis of three score related features.Genetic algorithm is employed to optimize the weights of above features.On this basis,recommendation-score is defined to measure admission risk.Finally,a college filling list with multi-admission risk is generated.Experiment results show that,the college admission line prediction algorithm based on BP neural network performs better than other algorithms under all error bounds.Compared with existing on-line services of Baidu and Kuake,Reco-PMF increases the acceptance rates by 14.8% and 24.1%,and improves the average ranking of recommended colleges by 99 and 87 in accepted colleges.

Memory-augmented GAN-based Anomaly Detection

ZHOU Shi-jin, XING Hong-jieHebei

Computer Science. 2022, 49 (11A): 211000202-9. doi:10.11896/jsjkx.211000202

Abstract

PDF(3189KB) ( 450 )

References | Related Articles | Metrics

In the training stage of the generative adversarial networks(GAN) based anomaly detection method,its training set consists of only normal data.When training data are sufficient,the GAN based anomaly detection method may obtain smaller reconstruction error.However,in the testing stage,the difference between the reconstruction errors of normal data and those of part novel data is too small,which makes the discriminant performance of the GAN based anomaly detection method become poor.To solve this problem,a memory-augmented GAN based anomaly detection method is proposed.A memory-augmented mo-dule is introduced into the proposed method to make it remember the characteristic of normal data.Hence,the reconstruction error of novel data becomes larger and thus the discriminant ability of the proposed method is enhanced.In comparison with the related approaches,experimental results on MNIST,Fashion-MNIST and CIFAR-10 verify that the proposed method has better detection performance.

DCPFS:Distributed Companion Patterns Mining Framework for Streaming Trajectories

ZHANG Kang-wei, ZHANG Jing-wei, YANG Qing, HU Xiao-li, SHAN Mei-jing

Computer Science. 2022, 49 (11A): 211100268-10. doi:10.11896/jsjkx.211100268

Abstract

PDF(3802KB) ( 364 )

References | Related Articles | Metrics

The widespread use of location technology leads to huge volumes of spatio-temporal data collected in the form of tra-jectory data streams.How to discover useful information from it has attracted more and more scholars’ attention.Mining companion pattern from trajectory stream refers to discovering groups with highly similar behaviors at the same time,which is essential for real-time applications of traffic management and recommendation systems.However,the existing research only achieves a second-level response,and it is difficult to respond quickly in milliseconds to large-scale trajectory data.Therefore,this paper proposes a distributed companion patterns mining framework DCPFS.The main contents of our work include:1) In order to reduce the time consumption of the density-based clustering algorithm DBSCAN for large-scale data,this paper proposes a data partition strategy and clustering merging algorithm based on a distributed deployment plan to ensure clustering parallelism and accuracy.2) Because the trajectory movement is directional in reality,we increase the direction dimension to reduce the redundancy in the clustering.3) We designed a parallel intersection algorithm to improve the efficiency of the intersection of clustering results in the pattern mining stage.4) We implement DCPFS on the Flink distributed big data processing platform and use Chengdu taxi GPS dataset and Google life dataset for experiments.Comprehensive empirical study demonstrates that the proposed framework has faster response speed than the baseline method.

Intelligent Operation Framework for Relational Database Application

JIANG Zong-lin, LI Zhi-jun, GU Hai-jun

Computer Science. 2022, 49 (11A): 211200030-9. doi:10.11896/jsjkx.211200030

Abstract

PDF(4556KB) ( 381 )

References | Related Articles | Metrics

Relational database refers to the database that uses relational model to organize data.It needs to use structured query language(SQL) to operate the data.When facing the application,it can only operate the database according to the program rules set by the developer.The process of modifying and adding program rules is cumbersome and requires a certain degree of professionalism,which is not friendly to ordinary users.In order to improve the expansion and universality of the application of rela-tional database,this paper uses the knowledge representation theory to model the knowledge related to database operation,uses the knowledge representation method of framework combined with rules to establish the general paradigm of database operation,and studies and designs the reasoning algorithm based on the operation characteristics of relational database and the syntax and semantics of relational model and structured query sentences.The user oriented database operation related things are abstracted into logical symbols,and the internal relationship between them is abstracted into the rule constraints between logical symbols.The problem is solved according to the rule constraints represented by logical symbols using the solving system.Based on the above theories and algorithms,a relational database operation framework integrating knowledge representation is designed and implemented,user input is converted into database operation statements to realize database system operation.It can be seen from the application example that the proposed operation framework can be embedded into the application system on the basis of friendly compatibility with relational database.The program rules are easy to expand,the application system has low difficulty in use,update and maintenance,and has strong self adaptability.It can provide users with more flexible and intelligent database ope-ration management and control services.

Novel Method Based on Graph Attentive Aggregation for POI Recommendations

CAI Guo-yong, CHEN Xin-yi, WANG Shun-jie

Computer Science. 2022, 49 (11A): 210800149-5. doi:10.11896/jsjkx.210800149

Abstract

PDF(2162KB) ( 350 )

References | Related Articles | Metrics

For services on location-based social network(LBSNs),effective point of interest(POI) recommendation has great economic and social utility.However,how to comprehend the position,structure and behavior related information of LBSNs and proceed reasoning for POI recommendation is still a challenge task.To exploit the heterogeneous information on LBSN,a novel graph attentive aggregation model for POI recommendation(POIR-GAT) is proposed,which exploits both users’ social information and POIs’ attributed information.Firstly,POIR-GAT uses social relationship to construct user-user graph,and extracts user feature vector together with user-POI interaction graph.Secondly,it constructs feature matrix based on different attributes of POIs,obtains hidden factors through matrix decomposition,integrates multiple features into POI feature vector,and learns their common influence on user behavior.Finally,it realizes the integration of social factors and POI features recommended model.Extensive experiments on two public datasets show that the proposed POIR-GAT model can effectively integrate users’ social information and POI feature information,and improve the quality of POI recommendation.

Movie Recommendation Model Based on Attribute Graph Attention Network

SUN Kai-wei, LIU Song, DU Yu-lu

Computer Science. 2022, 49 (11A): 211100106-8. doi:10.11896/jsjkx.211100106

Abstract

PDF(3128KB) ( 323 )

References | Related Articles | Metrics

In recent years,graph network has been widely used in the field of recommendation and made a great progress.How-ever,the existing methods tend to focus on the interaction modeling of user projects,so the performance is limited by the problem of data sparsity.Therefore,this paper proposes a movie recommendation model based on graph attention network of attribute graph by using additional attribute information.Firstly,an attention-based GNN is proposed,which uses explicit feed-back to calculate the attention score between entities and attributes.Compared with the aggregation method using Laplace matrix,it can distinguish the influence of different attributes on entities more effectively,and the information aggregation between attributes and entities can be more effective.In addition,different entities are affected differently by attributes and behaviors,a fine-grained pre-ference fusion strategy is designed in this paper to calculate a set of preference fusion weights for each entity to make the embedding representation of entities more accurate and personalized.Experimental results on real data set show that the recommendation method that makes full use of attribute information contained in attribute graph can effectively alleviate the problem of data sparsity and is significantly better than other basic algorithm in terms of recall rate and nDCG,two evaluation indexes of movie recommendation.

Fuzzy Multiple Kernel Support Vector Machine Based on Weighted Mahalanobis Distance

DAI Xiao-lu, WANG Ting-hua, ZHOU Hui-ying

Computer Science. 2022, 49 (11A): 210800216-5. doi:10.11896/jsjkx.210800216

Abstract

PDF(1789KB) ( 303 )

References | Related Articles | Metrics

Fuzzy support vector machine(FSVM) effectively distinguishes the importance of different samples by introducing fuzzy memberships,which reduces the sensitivity of traditional support vector machines to noise data.The membership function designed based on Euclidean distance ignores the overall distribution of samples and does not consider the different importance of sample features.A fuzzy support vector machine method based on weighted Mahalanobis distance is proposed.This method first applies the Relief-F algorithm to estimate the weight of each feature.Then it utilizes the weight for calculating the weighted Mahalanobis distance between the sample and the center of its class.Finally,the fuzzy membership of the sample is calculated based on weighted Mahalanobis distance.Furthermore,considering the difficulty of determining the kernel function and its parameters,a fuzzy multi-kernel support vector machine(FMKSVM) based on weighted Mahalanobis distance is put forward,which combines FSVM with multiple kernel learning methods.The multi-kernel is constructed in the form of weighted sum,and the weight of each kernel is calculated according to the central kernel alignment method(CKA).The proposed method not only reduces the influence of weakly relevant features on classification results,but also enables a more adequate and accurate representation of the data.Experimental results show that,FSVM based on weighted Mahalanobis distance has higher classification accuracy than FSVM based on Euclidean distance and Mahalanobis distance,and the classification performance of FMKSVM based on weighted Mahalanobis distance is superior to that of the single-kernel model.

Recommendation Algorithm Based on Apriori Algorithm and Improved Similarity

DONG Yun-xin, LIN Geng, ZHANG Qing-wei, CHEN Ying-ting

Computer Science. 2022, 49 (11A): 211000005-5. doi:10.11896/jsjkx.211000005

Abstract

PDF(2228KB) ( 337 )

References | Related Articles | Metrics

In order to alleviate the data sparse problem and improve the accuracy of collaborative filtering algorithm,a recommendation algorithm based on Apriori algorithm and improved similarity is presented.Firstly,it uses Apriori algorithm to mine the potential connections between users,and uses the confidence of the association rules between users to represent the potential connections between users,then constructs a user confidence matrix to fill the user rating matrix.Secondly,the algorithm uses the confidence matrix to improve the traditional similarity calculation formula and build a comprehensive similarity calculation formula between users.Finally,the algorithm uses the filled user rating matrix and the comprehensive similarity between users to make recommendations for users.The proposed algorithm has higher algorithm accuracy than traditional algorithms.Compared with other algorithms,the proposed algorithm can effectively alleviate the long tail problem of the recommendation system,so as to further improve the recommendation quality of the recommendation system.

Distribution Reduction in Fuzzy Order Decision Data Sets with Attention Degree

XU Wei-hua, ZHANG Jun-jie, CHEN Xiu-wei

Computer Science. 2022, 49 (11A): 210700191-5. doi:10.11896/jsjkx.210700191

Abstract

PDF(1759KB) ( 275 )

References | Related Articles | Metrics

With the advent of the era of big data,the structure of data becomes more and more complex,and the dimensions of data set become higher and higher,which will affect the efficiency of data mining greatly.Therefore,it is necessary to perform data compression or attribute reduction to information systems,that is,to remove unnecessary redundant attributes,reduce data dimensions,and improve the efficiency of data mining.The reduction methods proposed by many scholars in the past regard each attribute as equally important.But in real life,people’s attention to each conditional attribute in the data set is often different.Aiming at this phenomenon,based on the classical fuzzy decision data set,this paper weights different conditional attributes,defines the weighted score function,and further establishes the fuzzy order decision information system with attention degree.Then the distribution function is introduced into the system and the distribution reduction method is established by the distribution discer-nible matrix.Finally,the feasibility of the method is verified by a case study.

Fuzzy Random Events and Its Probabilities Based on Axiomatic Fuzzy Sets

XIE Jian-xiang, PAN Xiao-dong, ZHANG Bo

Computer Science. 2022, 49 (11A): 211100242-7. doi:10.11896/jsjkx.211100242

Abstract

PDF(1828KB) ( 340 )

References | Related Articles | Metrics

This paper studies the probability of fuzzy random events based on axiomatic fuzzy set,defines fuzzy random events and their corresponding probabilities,discusses some basic properties of probabilities of fuzzy random events,gives the product rule of fuzzy random events probability,and proves the law of total probability of fuzzy random events and Bayes’rule.

Attribute Reduction Algorithm Based on a New q-rung orthopair Fuzzy Cross Entropy

WANG Zhi-qiang, ZHENG Ting-ting, SUN Xin, LI Qing

Computer Science. 2022, 49 (11A): 211200142-6. doi:10.11896/jsjkx.211200142

Abstract

PDF(2078KB) ( 297 )

References | Related Articles | Metrics

Entropy is an important means to describe the degree of uncertainty of fuzzy sets.In order to reflect the ambiguity produced by the comparison between the membership degree and the non-membership degree in the q-rung orthopair fuzzy set,a related score function is first proposed.Taking into account the shortcomings of the similarity measures of most of the current q-rung orthopair fuzzy sets,a q-rung orthopair fuzzy set cross entropy is proposed,which is more in line with people’s intuition.As there is relatively little research on attribute reduction of q-rung orthopair fuzzy information system at present,through property discussion and theoretical proof,it is found that this kind of cross entropy can be better applied to attribute reduction of q-rung orthopair fuzzy information system.The related attribute reduction algorithm is presented,and an example is given to illustrate the rationality of this algorithm.Secondly,a method to convert ordinary information system into q-rung orthopair fuzzy information system is given.Finally,the rationality and effectiveness of this method are verified by calculating multiple databases in UCI,which provides new ideas for q-rung orthopair fuzzy information system data preprocessing.

Fuzzy Rough Sets Model Based on Fuzzy Neighborhood Systems

RAN Hong, HOU Ting, HE Long-yu, QIN Ke-yun

Computer Science. 2022, 49 (11A): 211100224-5. doi:10.11896/jsjkx.211100224

Abstract

PDF(1773KB) ( 317 )

References | Related Articles | Metrics

For fuzzy neighborhood systems,upper and lower fuzzy rough approximation operators based on general fuzzy logic operators are proposed,and the basic properties of the operators are investigated.Then,the concepts of neighborhood system of serial,reflexive,symmetric,unary and Euclidean are extended to fuzzy neighborhood systems.Finally,the related algebraic structures of fuzzy rough approximation operators are discussed when the fuzzy neighborhood system is serial,reflexive,symmetric,unary and Euclidean.

Effective Low-frequency Path Mining Method for Information Flow of Networking Information-centric System of Systems

LIN Wen-xiang, LIU De-sheng

Computer Science. 2022, 49 (11A): 211000001-6. doi:10.11896/jsjkx.211000001

Abstract

PDF(3411KB) ( 277 )

References | Related Articles | Metrics

With the rapid development of information technology and network technology and their widespread use in military field,networking information-centric system of systems comes into being.The networking information-centric system of systems is dominated by information,its main manifestation is the information activity process.The rationality and efficiency of the information activity process directly affect the operational effectiveness of information in the combat system.The use of process mi-ning technology to discover information activity process models from information activity event logs can provide effective support for modelling,testing and enhancement of information activity processes.Simply filtering noise in logs through event frequency analysis can easily lead to the loss of valid low-frequency paths and reduce the accuracy of the mined information activity processes.Combining the special characteristics of military information activities and the effectiveness characteristics of information transfer,a structure aggregation degree based effective low frequency path mining algorithm is proposed.Simulation analysis shows that the method can successfully separate log noise and effective low frequency paths,which is important for mining real and effective information processes.

Survey of Deep Learning Networks for Video Recognition

QIAN Wen-xiang, YI Yang

Computer Science. 2022, 49 (11A): 211200025-10. doi:10.11896/jsjkx.211200025

Abstract

PDF(2351KB) ( 550 )

References | Related Articles | Metrics

Video recognition is one of the most important tasks in computer vision research,which is concerned by many resear-chers.Video recognition refers to extracting the key features from different video clips,analyzing these features,and classification of the video.Compared to a single,static picture,there are many significant differences between frames of a video clip.How to tell the differences through the dimension of spatial-temporal information from video clips are well concerned by researchers.Taking video recognition technology as the target of the research,first,this paper introduces the basic concepts of video recognition and challenges in this area,together with some of the most frequently used datasets in video recognition tasks.Then,the classic video recognition methods based on spatio-temporal interest points,dense trajectories,and improved dense trajectories are reviewed.Also,the deep learning network frameworks for video recognition proposed in recent years are then summarized.They are summarized according to the time order of their proposal and grouped by the different architecture of their network.Among them,the video recognition framework based on 2D convolution neural network is introduced,including two-stream convolutional network architecture,long short-term memory network,and long-term recurrent convolutional network.Then,a framework based on a 3D convolutional neural network is introduced,including Slowfast Network,X3D(eXpand 3D) Network.Following that,the pseudo-3D convolutional neural network is introduced,including R(2+1)d network,Pseudo-3D residual network,and a set of light-weight networks based on building models on temporal information.At last,a Transformer-based network is introduced,including Timesformer,video vision Transformer,shifted window Transformer(Swin Transformer).The evolution of these deep learning frameworks,their implementation details and characteristics are analyzed.The performance of each network on different datasets is evaluated,and the applicable scenarios of each network are analyzed.In the end,the future research trend of video recognition network framework is prospected.Video recognition task can automatically and efficiently recognize the category to which the video belongs,and video recognition based on deep learning has a wide range of practical value.

Overview of 3D Reconstruction of Indoor Structures Based on Point Clouds

REN Fei, CHANG Qing-ling, LIU Xing-lin, YANG Xin, LI Ming-hua, CUI Yan

Computer Science. 2022, 49 (11A): 211000176-11. doi:10.11896/jsjkx.211000176

Abstract

PDF(3577KB) ( 456 )

References | Related Articles | Metrics

The 3D reconstruction of indoor structure is essentially a multi-task problem of restoring the indoor layout,which can further reconstruct and semantically segment wall details and furniture.This paper mainly introduces the 3D reconstruction of indoor structure based on point cloud data.Firstly,the data set commonly used for 3D reconstruction of indoor structure is summarized,and then the main methods of 3D reconstruction of indoor structure based on point cloud are described and discussed,and the advantages and disadvantages of the three types of reconstruction methods are analyzed and summarized.Finally,the difficulties and challenges faced by the current 3D reconstruction research of indoor structures are explained,and the future research trends are prospected.It can be concluded that the diversity of scenes and tasks completed by most reconstruction models at pre-sent is relatively poor,and the multi-task coordination scheme that uses redundant information from different angles to jointly optimize has great potential in the reconstruction of indoor structures.In addition,the model still needs to be improved for the seamless integration of the indoor and outdoor environments and the full performance of the interior and exterior buildings.

Review on Classification of Breast Cancer Histopathological Images Based on Convolutional Neural Network

ZHANG Xi-ke, MA Zhi-qing, ZHAO Wen-hua, CUI Dong-mei

Computer Science. 2022, 49 (11A): 210800232-9. doi:10.11896/jsjkx.210800232

Abstract

PDF(2708KB) ( 475 )

References | Related Articles | Metrics

Histopathological examination of breast cancer is the “gold standard” for the diagnosis of breast cancer.The classification of breast cancer histopathological images based on convolutional neural network has become one of the research hotspots in the field of medical image processing and analysis.Automatic and accurate classification of breast cancer histopathological images has important clinical application value.Firstly,two public datasets widely used in the classification of breast cancer histopathological images and their evaluation criteria are introduced.Then,the research progress of convolutional neural network on two datasets is mainly elaborated.In the process of describing the research progress,the reasons for the low accuracy of some models are analyzed,and some suggestions are given to improve the performance of the models.Finally,existing problems and future prospects of breast cancer histopathological image classification are discussed.

Pedestrian Detection Optimization Method Based on Data Enhancement and SupervisedEqualization in Fisheye Image

SI Shao-feng, ZHANG Sai-qiang, LI Qing, CHEN Ben-yao

Computer Science. 2022, 49 (11A): 210900070-6. doi:10.11896/jsjkx.210900070

Abstract

PDF(3277KB) ( 317 )

References | Related Articles | Metrics

In recent years,due to the fisheye camera is widely used in the field of intelligent monitoring,many scholars propose pedestrian detection algorithm for fisheye image.However,the fisheye scene is complex and distorted,which leads to the imba-lance of data set sample distribution and algorithm supervision allocation,which will reduce the performance of the detector.To solve these problems,a data enhancement method for pedestrian detection in fisheye image is proposed,which consists of pattern sampling enhancement and angle histogram enhancement.The pattern sampling enhancement focuses on the mining of difficult samples in fisheye image,and the generated new samples enrich the pedestrian patterns near the center of fisheye image.Angle histogram enhancement is based on the idea of histogram equalization,which smooths the angle distribution of fisheye image samples to alleviate the over fitting problem of single scene.In addition,based on Anchor-free fisheye image pedestrian detector,the fusion of location quality prediction and supervision information is proposed to extend Focal Loss to continuous domain to optimize the supervision allocation of detector location branches.Experimental results show that the proposed data enhancement algorithm can effectively alleviate the uneven distribution of fisheye image data set,and show good results in both Anchor-Based and Anchor-Free detectors.The continuous Focal Loss optimization localization supervision method improves the overall performance by 3.8% without increasing the reasoning complexity of the Anchor-Free detector.

Classification Algorithm of Diabetic Retinopathy Based on Attention Mechanism

SUN Fu-quan, ZOU Peng, CUI Zhi-qing, ZHANG Kun

Computer Science. 2022, 49 (11A): 211000213-5. doi:10.11896/jsjkx.211000213

Abstract

PDF(2986KB) ( 353 )

References | Related Articles | Metrics

Diabetic retinopathy is one of the important complications of diabetes and the main cause of blindness in the working population.The gap between retinal images is small and easy to be confused.Due to insufficient medical resources and lack of experienced ophthalmologists,it is difficult to carry out large-scale retinal image screening.Therefore,a classification algorithm for diabetic retinopathy based on attention mechanism is proposed to achieve accurate classification of the degree of retinal image lesions.The preprocessing operations such as data enhancement and image enhancement are carried out on data set.Using EfficientNetV2 as the backbone classification network,the attention mechanism is added to the network for fine-grained classification of retinal images,and the transfer learning strategy is used to train the network.The classification accuracy and the second weighted Kappa value of the proposed model are 97.8% and 0.843 respectively,which can effectively classify the disease degree of retinal images.Compared with other models,it has advantages and is of great significance for the diagnosis and treatment of diabetic retinopathy.

MRI and PET/SPECT Image Fusion Based on Subspace Feature Mutual Learning

ZHANG Ying, NIE Ren-can, MA Chao-zhen, YU Shi-shuang

Computer Science. 2022, 49 (11A): 211000171-6. doi:10.11896/jsjkx.211000171

Abstract

PDF(3470KB) ( 379 )

References | Related Articles | Metrics

In medical imaging,MRI images provide detailed texture information and better resolution,while PET/SPECT images retain molecular activity information and color function information,so fusing them is an important task.Most of the existing methods have some problems in the fusion process,such as color distortion,blur and noise.Therefore,a new subspace attention-siamese auto-encoding network(SSA-SAEN) is proposed to fully fuse meaningful information from MRI and PET/SPECT images.SSA-SAEN is proposed in image fusion network,and the subspace feature mutual learning concept is introduced.By using subspace attention module,MRI and PET/SPECT images can learn each other’s features,while reducing information redundancy and ensuring efficient and complete feature extraction.In addition,the conditional probability model is used to complement and fuse the extracted features,and the weighted fidelity gradient loss term is added into the training network to achieve the goal of network optimization.A large number of qualitative and quantitative experiments on public datasets show that the proposed me-thod can obtain a clear fused image,which demonstrates the superiority and effectiveness of the proposed method compared with other advanced methods.

Improved Water Quality Remote Sensing Monitoring Algorithms Based on Multilayer Convolutional Neural Network

FENG Lei, FENG Li, FANG Fang, GUO Jin-song, PAN Jiang, YU You, CHEN Yu

Computer Science. 2022, 49 (11A): 210200160-5. doi:10.11896/jsjkx.210200160

Abstract

PDF(2979KB) ( 416 )

References | Related Articles | Metrics

With the rapid development of water environment online monitoring technology in recent years,the categories and quantities of monitoring data have been greatly improved.Online monitoring and remote sensing monitoring are important data sources for water environment monitoring.How to quickly and efficiently understand massive monitoring data is a research hot-spot of artificial intelligence technology in the field of ecological environment data research.Changshou lake is a national good water body in the Three Gorges reservoir area.This paper aims at proposing an improved CNN convolution neural network algorithm WRCNN model,and this model is studied to extract features directly from water environment data in remote sensing images and increasing data dimension of water monitoring data.The ability of extraction can eliminate the uncertainty of function selection,reduce the calculation steps,suppress the influence of over-fitting and realize the application of remote sensing technology of large-scale monitoring in water environment.The results show that the improved WRCNN convolution neural network algorithm model can effectively identify the concentration of chlorophyll,the indicator of eutrophication in Changshou lake,and provide an efficient measures for monitoring eutrophication in reservoir area.

Study on Human Pose Estimation Based on Multiscale Dual Attention

MA Wan-yi, ZHANG De-ping

Computer Science. 2022, 49 (11A): 220100057-5. doi:10.11896/jsjkx.220100057

Abstract

PDF(2817KB) ( 323 )

References | Related Articles | Metrics

In view of the problem of low discrimination between human body and background in human posture estimation,and incomplete utilization of important feature information in human posture estimation based on HRNet,a human posture estimation method MDA-HRNet based on multiscale dual attention is proposed by using channel and spatial attention mechanism.Conside-ring both of the channel domain and spatial domain,the Ca-Neck and Ca-Block modules combined with channel attention and Sa-Block module combined with spatial attention are designed respectively.Then integrating these modules into the high-resolution network structure,so that the network can pay more attention to the human body area in the image.Moreover,in the Sa-Block module,3×3 and 7×7 convolution kernels are adopted to derive two spatial attention maps of different scales,which makes the ability of the network to comprehensively distinguish human features and background features more remarkable,so as to accurately locate the human body and its key points.The proposed method is tested and verified on MPII data set,and the results show that MDA-HRNet can improve the accuracy of joint point location of human posture estimation effectively.

Static Gesture Recognition Based on OpenCV in Simple Background

XU Yue, ZHOU Hui1 School of Computer Science, Technology, Xi’an Jiaotong University, Xi’an 710049, China

Computer Science. 2022, 49 (11A): 210800185-6. doi:10.11896/jsjkx.210800185

Abstract

PDF(3000KB) ( 420 )

References | Related Articles | Metrics

Gesture recognition is a very important technology in human-computer interaction,which has high theoretical and practical value.However,due to the complexity of the background and individual differences,gesture recognition has become a challenging topic.Therefore,it is necessary to design an efficient and accurate gesture recognition algorithm to effectively recognize the detected target gesture.An improved method of gesture segmentation and gesture feature extraction is proposed.SVM classifier is used to construct gesture model and recognize gesture.On the basis of YCrCb color space,OTSU threshold processing method is combined to select threshold segmentation gesture to improve the accuracy of segmentation.On the basis of edge detection,the ellipse Fourier descriptor is used to fit the edge and extract gesture features.Experimental results show that the system based on the above algorithm can extract gesture feature information efficiently,and the average recognition accuracy of 13 common gestures in a simple background is 89.96%,which can basically meet the requirements of recognition accuracy and stability.

Using Image Stabilization and VIBE Algorithm to Extract Foreground Target from Jitter Video

LIU Xin-fu, JIANG Mu-rong, HUANG Ya-qun, ZHANG Zhan-wei, ZHOU Ying-ying

Computer Science. 2022, 49 (11A): 210800195-8. doi:10.11896/jsjkx.210800195

Abstract

PDF(6642KB) ( 356 )

References | Related Articles | Metrics

In target detection and tracking processing area,the extracted foreground target is often disturbed by background jittering,resulting the problems of target misjudgment,incomplete contour and so on.In this paper,we present a method to improve the integrity of foreground target extraction by combining image stabilization and frame supplement,and then using VIBE algorithm and connected domain correction.Firstly,the image of two adjacent frames is matched by ORB feature,and the wrong ma-tching points are eliminated by RANSAC method.Then,the image margin is adjusted with the moving target as the center,and the non-coincident parts are cropped and repaired.The offset mean value of two adjacent frames is calculated by statistical method to achieve the purpose of video image stabilization.Secondly,the dense optical flow method is used to calculate the displacement of two adjacent frames,and then the intermediate frame is generated by position remapping and supplemented to make the video sequence more smooth and stable.Thirdly,based on VIBE algorithm,morphological processing and connected domain correction are added,and Canny operator is combined for edge detection to increase the integrity of target contour.Finally,a video example is used to test and compare with the commonly used video target extraction algorithms.The precision and recall rates increase by at least 10%.The rates of FNR and PWC reduce by at least 15%.Experimental results show that the proposed method can effectively remove the influence of jitter in most dynamic backgrounds,and the integrity of the extracted target is high.

Classification Method of Harmful Garbage Images Based on Improved EfficientNetV2

YUAN Hui-lin, LIU Jun-tao, HUANG Bi, HAN Zhen, FENG Chong

Computer Science. 2022, 49 (11A): 211100100-5. doi:10.11896/jsjkx.211100100

Abstract

PDF(2894KB) ( 362 )

References | Related Articles | Metrics

With the rapid development of industry,the amount of waste generated has also exploded,making waste disposal a worldwide problem.The Chinese government’s concern for the environment has gradually deepened,and various garbage classification policies and laws and regulations have been continuously introduced to supervise citizens’ garbage classification.Garbage disposal,especially hazardous garbage such as electronic waste,if it is improperly handled,will result in bad influence.Hazardous garbage image data has the characteristics of low data quality and unclear images.The image samples collected from different devices have obvious differences.Therefore,the image processing of hazardous garbage faces huge challenges.At the same time,the classification results of hazardous waste are related to environmental pollution issues.The amount of waste produced is huge,requiring high processing speed and accuracy.This paper proposes a garbage image classification method based on convolutional neural network and hybrid attention mechanism.This method does not need to manually extract features from the input image.Through the deep learning model framework,it overcomes the shortcomings of traditional image processing algorithms,achieves accurate and efficient classification of hazardous waste,and can better identify multiple types of hazardous waste.Experiment shows that the proposed method has an accuracy rate of 97.47% on the harmful-waste data set,the model training time is shorter,and its performance is better than other algorithm models.Using deep learning methods to deploy automated garbage classification models is of great significance to environmental protection.

Point Cloud Feature Line Extraction Algorithm Based on PCPNET

YU Meng-juan, NIE Jian-hui

Computer Science. 2022, 49 (11A): 210800017-6. doi:10.11896/jsjkx.210800017

Abstract

PDF(4104KB) ( 385 )

References | Related Articles | Metrics

Feature line extraction is the basic operation of geometric model processing,which is of great significance to the expression of 3D model.Based on PCPNET,a calculation method of curvature value and principal curvature direction which is robust to noise and non-uniform sampling is proposed,and a feature line extraction algorithm is proposed.The proposed algorithm uses the weighted quadratic curve to fit the local curvature distribution,and realizes the recognition of ridge and valley feature points by determining the distance from the extreme point of the quadratic curve in the direction of maximum principal curvature.Finally,the minimum spanning tree(MST) of the refined potential feature points is established to connect the feature points and complete the feature line extraction.Experimental results show that the proposed algorithm can use PCPNET to accurately estimate the curvature and principal curvature direction information of point cloud,and according to the proposed feature point recognition method,it can overcome the defect that the traditional simple threshold truncation can not extract the feature lines of flat area normally,and finally extract the feature lines from clean point cloud and noise point cloud accurately and completely.

Image Super-resolution Reconstruction Network Based on Dynamic Pyramid and Subspace Attention

HE Peng-hao, YU Ying, XU Chao-yue

Computer Science. 2022, 49 (11A): 210900202-8. doi:10.11896/jsjkx.210900202

Abstract

PDF(4660KB) ( 402 )

References | Related Articles | Metrics

Aiming at the problems of excessive model parameters and reconstruction distortion in existing single-image super-reso-lution convolutional neural networks,a lightweight single-image super-resolution network model based on dynamic pyramid structure and subspace attention module is proposed.First,the network body with dynamic multi-scale pyramid feature combination module consists of dynamic convolution and pyramid grouping convolution.Dynamic convolution can adaptively perform different convolution operations for different images,so as to extract different features for different images.Pyramid grouping convolution not only can better extract multi-scale features,but also can effectively reduce the number of parameters of the network model.Finally,a subspace attention module is used at the end of the network model to divide the channel space of images into multiple subspaces and learn different attention maps for each subspace,which not only can better capture the cross-channel rela-ted information of images,but also allows for effective fusion of image feature information of each subspace.Compared with the existing mainstream algorithms,the proposed method not only has a smaller number of model parameters,but also the reconstructed super-resolution images can achieve better performance in terms of visual effects and quantitative analysis.

Lycium Barbarum Pest Retrieval Based on Attention and Visual Semantic Reasoning

HAN Hui-zhen, LIU Li-bo

Computer Science. 2022, 49 (11A): 211200087-6. doi:10.11896/jsjkx.211200087

Abstract

PDF(3119KB) ( 307 )

References | Related Articles | Metrics

Aiming at the problem that traditional retrieval model on pest has a single mode,this paper uses a cross-modal retrieval method for 17 kinds of common lycium pests in image and text modal,which integrates attention mechanism and visual semantic reasoning.First,use Faster R-CNN+ResNet101 to realize the attention mechanism to extract local fine-grained information of wolfberry pest images.Then further introduce vision semantic reasoning to build the image region connections and use convolutional network GCN for region relation reasoning to enhance area representation.In addition,global semantic reasoning is performed by enhancing semantic correlation between regions,selecting discriminant features and filtering out unimportant information to capture more key semantic information.Finally,the semantic association between different modalities of lycium barbarum pest image and text is deeply explored through modal interaction.On the self-built lycium barbarum pest dataset,the average accuracy(MAP) is used as the evaluation index to carry out comparative experiment and ablation experiment.Experimental results demonstrate that the averaged MAP of the proposed method in the self-built lycium pest dataset achieves 0.522,compared with the eight mainstream methods,the average MAP of the method improves by 0.048 to 0.244,and it has better retrieval effect.

Noise Event Classification Model Based on Multimodal Attention

WU He-xiang, WANG Zhong-qing, LI Pei-feng

Computer Science. 2022, 49 (11A): 211000161-7. doi:10.11896/jsjkx.211000161

Abstract

PDF(2588KB) ( 396 )

References | Related Articles | Metrics

Social media is nowadays one of the main channels for people to obtain news and learn about real-time events due to its low cost,easy access and rapid dissemination.Social media provides a variety of modal information including text and images for analyzing specific events,which contains abundant irrelevant events and false information.To this end,this paper combines the text-image pairs to determine whether the text and image provide information related to specific events,so as to find out irrelevant noise events from the sentence-level of the text.Motivated by the observation that the description in the text is often associated with the scene in the corresponding image,this paper proposes a method of combining text and image information to classify events based on attention mechanism,which can effectively attend to the important information in text and image and promote information interaction in different modalities.Experimental results on CrisisMMD show that our model outperforms six strong baselines,and it can effectively fuse features of different modality to obtain a superior joint representation.

Identification Method of Maize Disease Based on Transfer Learning and Model Compression

DENG Peng-fei, GUAN Zheng, WANG Yu-yang, WANG Xue

Computer Science. 2022, 49 (11A): 211200009-6. doi:10.11896/jsjkx.211200009

Abstract

PDF(3510KB) ( 284 )

References | Related Articles | Metrics

Traditional image recognition methods have low accuracy in recognizing maize disease images,and convolutional neural networks have a good effect on image recognition.However,the network model has a large amount of calculation and a large amount of parameters,making it difficult to rely on mobile devices with limited computing power to popularize and use in small sample applications.Therefore,this paper aims to improve the accuracy of maize disease images,reduce network parameters and model size,and proposes a convolutional neural network model that combines migration learning and model compression for maize disease recognition.In order to improve the generalization of the model,the data set is enhanced and the structure of convolutional neural network based on transfer learning is constructed.In this paper,the migration recognition of common maize disease images is carried out by using the improved VGG16-Inception network model pre-trained on ImageNet through transfer learning.Experimental results show that the average recognition accuracy of maize disease images using transfer learning is 93.38% on ImageNet data set.After the migration,the model is compressed by channel pruning and knowledge distillation,and the compressed model is used to recognize the maize disease image by transfer learning.Experimental results show that the average recognition accuracy of corn disease image after compression reaches 92.40%,the accuracy is reduced by 0.98%,the model size is compressed from 73.90 MB to 9.45 MB,and the number of parameters is reduced by 87.80%.The proposed method can ensure the recognition accuracy in small sample scenarios and further realize the model lightweight.

Facial Landmark Fast Detection Based on Improved YOLOv4-tiny

FU Bo-wen, LI Chuang-chuang, LIANG Ai-hua

Computer Science. 2022, 49 (11A): 211100290-5. doi:10.11896/jsjkx.211100290

Abstract

PDF(2666KB) ( 348 )

References | Related Articles | Metrics

Facial landmark detection is an important part of face recognition,which has been a hot issue in the field of computer vision.In order to meet the needs of efficient and lightweight face recognition,this paper proposes a facial landmark detection algorithm based on improved YOLOv4-tiny.608*608*3 color image is used for model input.The CSPDarknet53-tiny network is adopted to extract the main features of the input image.Then the extracted features are up-sampled and fused.Attention mechanism is added before feature fusion to improve the detection accuracy.The loss function of YOLOv4-tiny target detection is reconstructed,and the loss function of facial landmark is added to realize the location of facial landmark while detecting.The model output includes face marker frame and five key points.Compared with other facial landmark detection algorithms,the proposed algorithm has higher recognition efficiency and lower configuration requirements while ensuring recognition accuracy.Therefore,it can be better deployed on edge devices or mobile devices.

Thymoma CT Image Prediction Method Based on Deep Learning and Improved Extreme Learning Machine Ensemble Learning

XU Kun-cai, FENG Bao, CHEN Ye-hang, LIU Yu, ZHOU Hao-yang, CHEN Xiang-meng

Computer Science. 2022, 49 (11A): 211200097-6. doi:10.11896/jsjkx.211200097

Abstract

PDF(3580KB) ( 333 )

References | Related Articles | Metrics

To predict the risk of thymoma patients before operation,a computer-aided analysis method combining deep learning and extreme learning machine ensemble learning is proposed.Firstly,the CT image of thymoma is transformed to different scales by wavelet multi-scale transform,and the wavelet energy map is calculated to improve the richness and diversity of image information.Secondly,the convolution neural network model is trained by wavelet energy map,and the specific depth features related to tasks in wavelet energy map are extracted by convolution kernel.Finally,the differentiated training subsets are trained based on the improved limit learning machine,and ensemble learning is constructed to improve the stability and prediction accuracy of the model.Based on multicenter experiments,the results show that the proposed method has good generalization performance and stability.The AUCs of the three verification sets are 0.833,0.771 and 0.784 respectively.

Heart Sound Segmentation Algorithm Based on TK Energy Operator and Envelope Fusion

ZHANG Xin, SUN Jing, YANG Hong-bo, PAN Jia-hua, GUO Tao, WANG Wei-lian

Computer Science. 2022, 49 (11A): 210900135-6. doi:10.11896/jsjkx.210900135

Abstract

PDF(2964KB) ( 293 )

References | Related Articles | Metrics

In order to segment heart sounds by component more effectively,a kind of heart sound segmentation algorithm based on Teager-Kaise energy operator(TKEO) and multi-envelope feature fusion is proposed in experiment.Firstly,the PCG signal is denoised by using the multi-scale wavelet soft threshold.Then TKEO operation is carried out.Since TKEO is extremely sensitive to the instantaneous energy change,the envelope peak can be extracted effectively and the TKEO signal can be obtained.Secondly,the normalized Shannon energy envelope and Viola integral envelope are extracted from the TKEO signal.The Pearson correlation coefficient between each envelope and TKEO signal is calculated.And then the fusion envelope is carried out according to the correlation.Next,the interval search method is used to search the peak envelopes.The variance of the search results is compared.Finally,false peaks are eliminated according to the maximum duration of S1 and S2.The proposed algorithm is tested using PhysioNet2016 data set.Experimental results show that an average accuracy of 0.922 is achieved by using this method.It is proved that this algorithm can be used to segment the heart sound signals effectively.It provides a new method for feature extraction and analysis of heart sound signals collected in clinical environment.

Improved FCOS Target Detection Algorithm

CHEN Jin-ling, CHENG Mao-kai, XU Zi-han

Computer Science. 2022, 49 (11A): 210900220-6. doi:10.11896/jsjkx.210900220

Abstract

PDF(3434KB) ( 354 )

References | Related Articles | Metrics

An enhanced FCOS object detection algorithm is proposed to address the problems that the classical anchorless frame object detection algorithm FCOS(fully constitutional one-stage object detection) has difficulty in extracting target information,insufficient ability to combine location and content information,and weak performance due to insufficient differentiation between positive and negative sample.The method first adds a deformable convolution module and a global attention module to the ResNet50 feature extraction network to improve the feature information capture capability.Then,the FPN feature pyramid is combined with the deep link layer to form a multi-scale feature fusion module to improve the feature extraction effect.Finally,the adaptive division of positive and negative samples module is added to enhance the accuracy of the test frame to achieve the effect of improving the regression accuracy.In order to test the detection effect of the algorithm,the COCO dataset and VOC dataset are used for experiments.Compared with the original FCOS algorithm,the average accuracy of the proposed algorithm on the two datasets improves by 2.3% and 1.8%,respectively.Among them,there is a significant improvement for the detection of small targets in the COCO dataset.

Dual Template and Asynchronous Update Tracking Method Based on SiameseFC

MA Han-da, YIN Da

Computer Science. 2022, 49 (11A): 211200133-7. doi:10.11896/jsjkx.211200133

Abstract

PDF(3024KB) ( 266 )

References | Related Articles | Metrics

SiameseFC has the advantages of fast tracking speed and high accuracy,but it still has some defects in complex scenes,and the tracking mode without updating the template will also cause large errors in the scene that changes rapidly.Therefore,this paper proposes a new tracking method,the dual-template asynchronous update based on SiameseFC.Firstly,both the deep and shallow features are extracted from the VGG-16 network,and two sets of corresponding templates are used respectively,the two sets of templates are updated independently and asynchronously to save computing resources.Then,for the update of the template,the initial template,the template used in the previous tracking,and the template extracted from the tracking result of the previous frame are considered at the same time.And it uses an APCE-based judgment mechanism to dynamically allocate the proportions of the three templatets when updating.This algorithm is superior to mainstream algorithms such as SiamRPN in the benchmark results of OTB100,the success rate and accuracy improve by about 4%～5%,and reaches about 44 fps,which is sufficient to meet real-time tracking requirements.

Study on Recognition and Classification of Congenital Heart Disease and Pulmonary Hypertension Based on ECG Signal

HAN Yu-sen, YANG Hong-bo, SUN Jing, PAN Jia-hua, WANG Wei-lian

Computer Science. 2022, 49 (11A): 210900144-8. doi:10.11896/jsjkx.210900144

Abstract

PDF(5169KB) ( 343 )

References | Related Articles | Metrics

Pulmonary arterial hypertension(PAH) associated with congenital heart disease has a high clinical morbidity,disability and mortality.Its diagnosis is mainly made by measuring the mean pulmonary arterial pressure by right heart catheterization.This method is invasive and has high operational requirements,and it is inconvenient to be used in screening,so it is of great significance to explore a non-invasive CHD-PAH intelligent auxiliary diagnosis scheme.This paper studies CHD-PAH on the basis of congenital heart disease,starting from the analysis of ECG signal,and modeling and predicting CHD-PAH by means of preprocessing,heart beat segmentation,waveform detection,feature extraction,data expansion,classification and identification.Based on the Christov_segmenter algorithm,the differential threshold and local peak improvement are used to detect QRS waves,P waves and T waves,and finally extract bimodal features based on time and amplitude.In order to fit the best classification model,the support vector machine,random forest and K-neighbor classifiers are used in experiments,and a sparrow search algorithm based on T distribution is designed to improve the support vector machine.A total of 460 1-lead ECG signals with a duration of 20 s are used for training and testing.Experimental results show that the prediction accuracy,specificity and sensitivity of the SVM model optimized by the proposed algorithm can reach 99.76%,99.80% and 99.73%,respectively.

Rail Surface Defect Detection Model Based on Attention Module and Hybrid-supervised Learning

ZHAO Chen-yang, ZHANG Hui, LIAO De, LI Chen

Computer Science. 2022, 49 (11A): 210800241-6. doi:10.11896/jsjkx.210800241

Abstract

PDF(4781KB) ( 343 )

References | Related Articles | Metrics

Rail surface defect detection is an important part of ensuring railway safety.By analyzing the necessity of rail surface defect detection and the shortcomings of existing detection methods,a rail surface defect detection model based on attention mo-dule and hybrid-supervised learning is proposed.Aiming at the problem of a large number of parameters and high deployment cost of existing model,an end-to-end rail defect detection model is proposed.The attention module is used to guide the generation of feature clusters,which improves the speed of defect detection and reduces the cost of model deployment.In view of the problems of few abnormal samples and the high cost of labeling in practical applications,the influence of rough labeling and hybrid supervision is studied,and the pixel-level label data is processed to make different areas of the label get different attention and reduce the dependence of model on label.Finally,experiments are carried out on the actual rail datasets.and the results show that the performance of hybrid-supervised learning is equivalent to that of full supervised learning by adding a small amount of pixel-level label samples to image-level label samples,and the classification accuracy of the model reaches 99.7%.

Supervised Similarity Preserving Deep Second-order Hashing

ZHANG Jian-xin, WU Yue, ZHANG Qiang, WEI Xiao-peng

Computer Science. 2022, 49 (11A): 210900021-8. doi:10.11896/jsjkx.210900021

Abstract

PDF(4705KB) ( 318 )

References | Related Articles | Metrics

Recently,deep hashing technology,with its advantages of high storage efficiency and quick query speed,has been widely investigated in the field of large-scale visual image retrieval.However,the fundamental image features obtained by current deep hashing methods mainly depend on the first-order statistics of deep convolutional features,and they seldom take the global structure into consideration,leading to the limitation of retrieval accuracy to a certain degree.Focusing on the global representation capability and the similarity of intra-class samples,this paper proposes a novel supervised similarity preserving deep second-order hashing (S2PDSoH) based on deep pairwise supervised hashing,gaining effective performance improvement in the image retrieval task.Based on the pair-wise deep hashing model,S2PDSoH first employs covariance estimation based on matrix power normalization method to capture the deep second-order information of sample images,so that hash codes can possess good global presentation ability.Then,to gain more robust hash codes,it further constructs a joint constraint of category supervision and similarity preservation motivated by the idea of multi-loss integration,followed by an alternate iteration optimization algorithm to realize the end-to-end training.Therefore,with the semantic information added to the dual channel deep second-order hashing framework,S2PDSoH establishes a mechanism for common constraints on category supervision and similarity maintenance.In addition,it also introduces a hash-like function to achieve the approximate binarization result of hash codes,which solves the problem of non-convexity and avoids the quantization error in the hash mapping process.Extensive experimental results on three commonly used data sets show the effectiveness of the proposed deep-order hashing method with supervised similarity preservation.

MIF-CNNIF:A Multi-classification Image Data Framework Based on CNN with Intersect Features

WANG Pan-hong, ZHU Chang-ming

Computer Science. 2022, 49 (11A): 210800267-8. doi:10.11896/jsjkx.210800267

Abstract

PDF(3241KB) ( 260 )

References | Related Articles | Metrics

In recent years,image multi-classification task and deep learning have received increasingly attentions,and multi-classification image data framework based on convolutional neural network(MIF-CNN) has also been widely used.Traditional CNN-based multi-class image data learning generally has a problem that the image processing is complicated,the feature dimensions are large,and the time complexity is high.To solve this problem,this paper proposes a multi-classification image data framework based on CNN with intersect features(MIF-CNNIF).MIF-CNNIF is a framework for performing multi-classification tasks based on intersect features obtained by multiple feature selection algorithms.Through extensive comparative experiments on 10 multi-class image data sets,the results validate the effectiveness of MIF-CNNIF.The contributions of MIF-CNNIF are that,1)it avoids the problem of setting too many parameters with the usage of pre-trained CNN models;2)it keeps features dimension and time cost after comparing with MIF-CNN;3)it has a better average recognition accuracy than MIF-CNN;4)the effectiveness of combined feature algorithms is verified on multi-class image data sets.

Block-based Compressed Sensing of Image Reconstruction Based on Deep Neural Network

PAN Ze-min, QIN Ya-li, ZHENG Huan, WANG Rong-fang, REN Hong-liang

Computer Science. 2022, 49 (11A): 210900118-9. doi:10.11896/jsjkx.210900118

Abstract

PDF(6444KB) ( 330 )

References | Related Articles | Metrics

Compressed sensing(CS) is a signal processing framework for effectively reconstructing signal from a small number of measurements obtained by linear projections of the signal.It’s an ongoing challenge for the practicality of computational imaging based on CS.The improvement of image reconstruction model is to incorporate more prior constraints under the signal sparse constraint,and the iterative optimization process is complex and time-consuming.Neural networks,as the application models of deep learning,can realize the approximation of any complex function,which provides a new technical route for high-quality and real-time image reconstruction.In this paper,deep neural network(DNN) is used for reconstruction and the block processing is used to reduce the reconstruction time and the number of network nodes,which avoids the complicated algorithm solving process of CS.The DNN model is obtained by training a large number of different types of images,and then the block CS measurement and DNN nonlinear solution are combined jointly to achieve efficient reconstruction.Experimental results show that,compared with six different reconstruction algorithms,the peak signal-to-noise ratio(PSNR) and structure similarity(SSIM) of images are improved in different degrees.Compared with the advanced CS algorithm,not only the reconstruction quality is comparable,but also the time complexity of DNN is greatly reduced and the reconstruction time is less than 3s.When sampling rate is as low as 0.01,the proposed approach can still reconstruct the image clearly while other algorithms fail.When sampling rate is 0.1,compared with the recent residual network method,the maximum(minimum) gain of PSNR is 6.7(1.97) dB,and the maximum(minimum) gain of SSIM is 0.354(0.122).

Study on Quality Evaluation Method of Speech Datasets for Algorithm Model

LI Sun, CAO Feng, LIU Zi-shan

Computer Science. 2022, 49 (11A): 210800246-6. doi:10.11896/jsjkx.210800246

Abstract

PDF(4253KB) ( 345 )

References | Related Articles | Metrics

With the maturity of intelligent voice technology and product application,the demand for high-quality voice datasets is increasing.There have been some researchers put effort on the quality evaluation of the structured data,but there are few stan-dards appeared for the unstructured voice dataset.By analyzing the construction principle of speech algorithm model and analyzing the construction demand of voice dataset,a unified quality assessment framework for the voice dataset is presented.The framework proposes to evaluate the dataset in terms of four dimensions,each of which subsumes a set of criteria:breadth coverage,anthology distinction,field depth and accuracy completeness.The criteria that are suitable to evaluate the quality dimensions are presented,each with the definition,measurement method,and the evaluation process for the voice dataset quality measurement.Experimental assessment and analysis results of the voice datasets in the vehicular application field are presented as the reference for evaluating the voice dataset quality,and promoting the construction of the voice dataset.Considering the diversified applicabi-lity,privacy issues,efficiency requirements,automation requirements and other aspects of the construction of voice data sets,the development suggestions for building high-quality voice datasets are proposed.

Structure Preserved Multi-view Subspace Clustering Based on t-SVD

ZHANG Hua-wei, LU Xin-dong, ZHU Xiao-ming, SUN Jun-tao

Computer Science. 2022, 49 (11A): 210800215-6. doi:10.11896/jsjkx.210800215

Abstract

PDF(2521KB) ( 327 )

References | Related Articles | Metrics

To peruse the manifold structure and correlation among multi-view data for the tensor based subspace clustering algorithms,this paper proposes a novel algorithm named structure preserved multi-view subspace clustering based on t-SVD(t-SVD-SpMSC).For both structures in multi-view data,we employ the graph regularization in which the graph is got adaptively by iteration.To optimize the objective function,we develop an alternative optimization algorithm to solve the final objective function.The accuracy of clustering using t-SVD-SpMSC on three datasets is 100%,91.51%,99.81% respectively,which shows the priority of the proposed method.

Multi-camera Calibration Method Based on Large-scale Scene

LIAO De, ZHANG Hui, ZHAO Chen-yang

Computer Science. 2022, 49 (11A): 211200054-6. doi:10.11896/jsjkx.211200054

Abstract

PDF(3932KB) ( 402 )

References | Related Articles | Metrics

In the field of computer vision,multiple camera sensors need to be used to obtain three-dimensional information of the object so as to achieve a series of measurements such as detection,positioning and size estimation of large target objects.In actual applications,in complex environments,there will be a problem of non-overlapping field of view between the cameras,which prevents effective visual measurement.Therefore,in order to solve the calibration problem of multiple cameras,a multi-camera calibration method with constraints is proposed,without changing the mechanical structure.First,install the cameras in a fixed position,and ensure that there is no vibration between the cameras,by establishing a multi-camera optimization mathematical model and the cameras simultaneously collecting the pose parameter relationships of multiple sets of cameras corresponding to the calibration board,and using the SVRG optimization algorithm to achieve Optimize the pose parameters between the camera coordinate systems,and then obtain the pose matrix between multiple cameras.Finally,the coordinate system transformation matrix between the cameras is used to obtain the relative pose parameters between the corresponding targets as the evaluation accuracy index.And combined with the actual large-scale shield machine to carry out simulation experiment and actual test.The results show that this method has strong anti-interference,stable optimization effect,and can achieve millimeter-level accuracy in practical applications.

Improved Triangular Algorithm for Small Field of View Star Sensor

LU Han, LIN Bao-jun, ZHANG Yong-he, DING Guo-peng, WANG Xin-yu

Computer Science. 2022, 49 (11A): 211000223-5. doi:10.11896/jsjkx.211000223

Abstract

PDF(2321KB) ( 348 )

References | Related Articles | Metrics

In the fields of scientific exploration and satellite high-precision positioning,star sensors need to obtain attitude information in a short time.In order to improve accuracy,it is necessary to increase the angular resolution,reduce the field of view and use a higher magnitude as a reference.The star pattern recognition algorithm is the key to quickly obtain the attitude information for star sensors.When the traditional triangle algorithm faces a situation where the number of stars is small and the proportion of dark stars is larger,the recognition accuracy will quickly drop to 70%~80%,which needs to be improved.Motivated by this,an efficient star pattern recognition algorithm based on triangle angular distance matching is proposed.The proposed method combines the feature of magnitude interval difference and introduces the fourth star verification,so as to reduce redundant matching.Simulation results show that the proposed method improves the recognition rate to 98.4% while the recognition speed is not lower than that of the classical improved triangle algorithm.In the case of introducing position noise and magnitude noise,it still maintains a recognition rate of more than 93%,which has strong robustness.

Multi-label Vehicle Real-time Recognition Algorithm Based on YOLOv3 and Improved VGGNet

GU Xi-long, GONG Ning-sheng, HU Qian-sheng

Computer Science. 2022, 49 (11A): 210600142-7. doi:10.11896/jsjkx.210600142

Abstract

PDF(2663KB) ( 329 )

References | Related Articles | Metrics

In order to quickly and effectively identify vehicle information in video,this paper combines the advantages of YOLOv3 algorithm and CNN algorithm to design an algorithm that can identify vehicle multi-label information in real time.Firstly,the high recognition speed and accuracy of YOLOv3 are used to realize real-time monitoring and positioning of vehicles in video stream.After obtaining the vehicle location information,the vehicle information is passed into the improved simplified and optimized VGGNet multi-label classification network to identify the vehicle with multiple tags.Finally,the label information is output to the video stream to obtain real-time multi-label recognition of vehicles in video.The training and test data sets in this paper are derived from KITTI data sets and multi-label data sets obtained through Bing Image Search API.Experimental results show that the mAP of the proposed method on KITTI data set reaches 91.27,the average accuracy of multi-label is more than 80%,and the frame rate of video reaches 35fps.It achieves good results in vehicle identification and multi-label classification on the basis of ensuring real-time performance.

Liver CT Images Segmentation Based on Multi-scale Feature Fusion and Dual AttentionMechanism

HUANG Yang-lin, HU Kai, GUO Jian-qiang, Peng ChengKey Laboratory of Intelligent Computing & Information Processing of Ministry of Education, Xiangtan University, Xiangtan, Hunan 411105,China

Computer Science. 2022, 49 (11A): 210800162-9. doi:10.11896/jsjkx.210800162

Abstract

PDF(3598KB) ( 361 )

References | Related Articles | Metrics

Liver disease is one of the most common diseases in medicine,and accurate segmentation of liver disease is a necessary step to assist liver disease diagnosis and surgical planning.However,liver segmentation is still a challenging task due to the complexity of liver CT images.With the deepening of research,people begin to consider combining high-level semantics with low-level semantics to further enhance the segmentation effect.However,most of previous studies simply use splicing or summation operation to fuse different semantics,resulting in failure to make full use of its complementarity.To solve the above problems,a network(MD-AUNet) based on multi-scale feature fusion and dual attention mechanism is proposed in this paper.Firstly,the hierarchical dual attention mechanism in the hierarchical multi-scale attention down-sampling module(HAM) is used to effectively fuse feature information of different scales and extract feature representations rich in spatial information.Then,the global context of high-level features is obtained through the global attention up-sampling module(GAM) for weighting the low-level feature information,so as to select more accurate spatial information.At the same time,deep supervision strategy is used in network training to learn the hierarchical representation of different decoding layers.Moreover,a concise and effective post-processing method is proposed to refine the coarse segmentation result of MD-AUNet.Experimental results on the liver datasets collected by the hospital(manually annotated by experts) demonstrate that the proposed algorithm is superior to other existing liver segmentation algorithms in subjective visual perception and objective evaluation indicators,and its mean pixel accuracy,mean IoU and Dice are 97.6%,95.4%,and 95.5% respectively.

Detection of Deepfakes Based on Dual-stream Network

LI Ying, BIAN Shan, WANG Chun-tao, HUANG Qiong

Computer Science. 2022, 49 (11A): 220100106-9. doi:10.11896/jsjkx.220100106

Abstract

PDF(3463KB) ( 421 )

References | Related Articles | Metrics

Deepfake is a kind of deep network model based on generative adversarial networks(GAN).It uses the source and target faces to generate highly realistic face videos that are difficult to identify.If some malicious person uses this technology to make fake videos and spread rumors on the Internet,it will infringe personal portrait right,cause adverse social impact,or even cause serious judicial disputes.In view of the serious threat brought by deepfake technology,many researchers at home and abroad pay close attention to the study of the deepfake detection technology,and have put forward some effective detection me-thods.The existing detection methods achieve good detection results in high-quality videos,but most videos in daily applications are usually compressed into low-quality versions through social software.However,most of the existing deepfake detection methods have a significant decline in detecting this kind of low-quality videos.Besides,the detection performances of existing methods are still unsatisfying in the case of cross datasets,limiting their real applications.To address this issue,this paper proposes a dual-flow network structure based on Xception model under multiple attention mechanism.The network structure includes an RGB branch using multiple attention mechanism and a frequency-domain branch for capturing low quality video artifacts.Based on our research,it is found that the tiny difference between real images and fake images tends to concentrates in some local area.The RGB branch under the multiple attention mechanism makes the model focus on different regions of the face,so it can get the glo-bal features aggregated by the low-level texture and high-level semantic features under the guidance of the attention map.Combined with the RGB branch,the discrete cosine transform(DCT) is introduced in the frequency domain branch to provide complementary feature representation,which can reflect subtle forgery traces or compression errors.Specifically,the proposed algorithm firstly extracts a large number of face frames from videos by face extractor algorithm,and feeds these face frames into the two-branch network model.The frequency branch decomposes the spectrum of images with three combined filters that provide additional learnable parts.In the RGB branch,the first three layers of the backbone network extract shallow features including texture information etc.Then the attention module makes the model attend to the shallow information from different local areas.The shallow information is then fed to the attention pooling layer to aggregate with the high-level semantic features from the rest layers of the backbone network.Finally,the network merges the feature vectors from both the RGB-branch and the frequency branch to obtain the final discriminant result.The combination of these two branches can significantly improve the detection performance of the model in cross database scenes and low-quality video sets.In order to verify the effectiveness of the proposed network structure,a large number of comparative experiments are conducted on three public datasets,including FaceForensics++,Celeb DF and DFDC.In the low-quality part of FaceForensics++ dataset,the AUC(Area Under the Curve) can reach 0.9271.In the video level,the detection accuracy of low-quality and high-quality videos can reach 93.84% and 99.69%,respectively.Experimental results show that the proposed algorithm outperforms the existing detection algorithms in low-quality video sets as well as in cross dataset scenes.It verifies that the combination of dual-stream features including the RGB branch and the frequency branch can improve the robustness of the detection method,especially in low-quality video sets and in cross dataset scenes.

Single-stage 3D Object Detector in Traffic Environment Based on Point Cloud Data

CHE Ai-bo, ZHANG Hui, LI Chen, WANG Yao-nan

Computer Science. 2022, 49 (11A): 210900079-6. doi:10.11896/jsjkx.210900079

Abstract

PDF(3342KB) ( 331 )

References | Related Articles | Metrics

Based on CIA-SSD single-stage 3D object detection model,this paper improves the spatial semantic feature fusion method of the model.A multi-channel fusion module based on attention mechanism is used to fuse the two features.The single-stage detection method TFAF-SSD(two-feature attentional fusion single-stage object detector) is proposed.After extracting the sparse features of point cloud by manifold sparse convolution network,the spatial semantic features of the detected objects are extracted by the spatial semantic convolution layer.After fusion,the output features are predicted.Finally,the final detection frame is output by the detection head.At the same time,different from the previous methods,this paper also uses the data enhancement method to enhance the generalization performance of the model to improve the detection accuracy.The proposed method is verified on KITTI 3D open data set,and the test result of vehicle detection in test set is 83.77%,which is 3.49 % higher than the 80.28% of CIA-SSD model.

Continuous Sign Language Recognition Method Based on Improved Transformer

WANG Shuai, ZHANG Shu-jun, YE Kang, GUO Qi

Computer Science. 2022, 49 (11A): 211200198-6. doi:10.11896/jsjkx.211200198

Abstract

PDF(1457KB) ( 478 )

References | Related Articles | Metrics

Continuous sign language recognition is a challenging task.Most current models ignore the overall modeling ability of long sequences,resulting in lower accuracy of recognition and translation of longer sign language videos.The unique codec structure of Transformer model can be used for sign language recognition,but its position coding method and multi-head self-attention mechanism still need to be improved.Therefore,this paper proposes a continuous sign language recognition method based on the improved Transformer model.Through multiple multiplexed position codes with parameters,each word vector in the continuous hand sentence is calculated multiple times to accurately grasp the position information between each word,add learnable memory key-value pairs to the attention module to form a persistent memory module,and expand the number of attention heads and embedding dimensions through linear high-dimensional mapping and the like,to maximize the multi-head attention mechanism of the Transformer model,and the overall modeling ability of long sign language sequences,in-depth mining of key information in each frame of the video.The proposed method achieves competitive recognition results on the most authoritative continuous sign language data sets PHOENIX-Weather2014^[1] and PHOENIX-Weather2014-T^[2].

Non-contact Heart Rate Detection Based on Facial Video

ZENG Zi-lin, HU Zhi-gang, SHANG Peng, WANG Xin-zheng, FU Dong-liao

Computer Science. 2022, 49 (11A): 211000182-6. doi:10.11896/jsjkx.211000182

Abstract

PDF(3134KB) ( 406 )

References | Related Articles | Metrics

Non-contact facial heart rate detection based on video is susceptible to interference from ambient light and motion artifacts,and the accuracy of heart rate detection results is low.To address the above problems,this paper proposes an adaptive thresholding denoising method which combines ensemble empirical mode decomposition(EEMD) and standardized Euclidean distance to reduce external interference and improve accuracy.Firstly,the green channel pixel mean is selected as PPG signal from RGB image model recorded by camera,and then the signal is preprocessed with a filter to eliminate the signals outside the heart rate range.Secondly,the EEMD is combined with standardized Euclidean distance to threshold and reconstruct the intrinsic modal function.Finally,power spectrum analysis with Fourier transform is performed to calculate the heart rate.Experiments show that,compared with the methods based on wavelet transform and empirical mode decomposition with adaptive,this method has better stability and accuracy in denoising of non-contact facial heart rate detection,improves the robustness of heart rate detection,which is suitable for daily non-contact real-time heart rate monitoring.

Feature Extraction of Flotation Foam Moving Speed Based on Improved GMS Feature Matching Algorithm

LIU Hui-zhong, YU Hua-fu, PENG Zhi-long

Computer Science. 2022, 49 (11A): 211000064-6. doi:10.11896/jsjkx.211000064

Abstract

PDF(5852KB) ( 337 )

References | Related Articles | Metrics

In the process of mineral flotation,there is a great correlation between the moving speed of flotation foam and the control of flotation process.If the dynamic characteristics such as the moving speed of flotation foam can be accurately obtained in real time,it can provide a basis for the optimization and adjustment of control parameters such as liquid level,charging amount and aeration amount in the flotation process.In order to obtain the moving speed of flotation foam effectively,a feature extraction method based on improved GMS feature matching algorithm is proposed in this paper.Firstly,the ORB algorithm is used to extract and describe the foam feature points,and then the GMS feature matching algorithm is used to complete the fast matching of feature point pairs.On the basis of the above,the RANSAC algorithm is used to eliminate the false matching points in the feature matching results.Finally,the foam moving speed is obtained by calculating the displacement of the foam feature points.The application test of the collected industrial image data shows that the proposed algorithm not only solves the problem that there are many false matching points in the flotation foam image feature extraction of traditional algorithm,but also effectively improves the efficiency and stability of flotation foam feature extraction.

High-resolution Remote Sensing Sea Ice Image Segmentation Based on Combination of ImprovedSLIC Algorithm and Clustering Algorithm

QI Ying, CHAI Yan-mei

Computer Science. 2022, 49 (11A): 211200100-6. doi:10.11896/jsjkx.211200100

Abstract

PDF(3763KB) ( 324 )

References | Related Articles | Metrics

Sea ice floe segmentation is an import topic in remote sensing.Due to the large high-resolution remotely sensed sea ice image,the simple linear iterative clustering(SLIC) algorithm is used to construct superpixel blocks,which can capture image redundancy and greatly reduce the complexity of subsequent image processing tasks.Although SLIC can generate super-pixel blocks with regular and uniform shapes,but there are still some problems to be used in sea ice floe segmentation.For example,the initial seed points of the algorithm are sensitive to noise,the segmentation accuracy is not high and the running speed is not very quick.Therefore,an improved SLIC combining clustering algorithm is proposed to segment high-resolution remote sensing sea ice image.Aiming at the problem of noise sensitivity,anisotropic diffusion filtering is used to preprocess the image to ensure the integrity of the image while removing noise.Then the L-p norm is used to substitute and expand the traditional Euclidean distance in the SLIC algorithm.Finally,on the basis of SLIC superpixel block,DBSCAN and K-Means clustering algorithms are separately used to precisely segment the sea ice images,and the optimal result is obtained through performance comparison.Experiments show that the improved SLIC combined with K-Means segmentation method is better than Markov tandom field(MRF) algorithm and the improved SLIC combined with DBSCAN.It can obtain quite good segmentation results.

Study on Solar Radio Burst Event Detection Based on Transfer Learning

GUO Jun-cheng, WAN Gang, HU Xin-jie, WANG Shuai, YAN Fa-bao

Computer Science. 2022, 49 (11A): 210900198-7. doi:10.11896/jsjkx.210900198

Abstract

PDF(4433KB) ( 340 )

References | Related Articles | Metrics

Solar radio burst events are closely related to a variety of solar activities.The study of different types of radio burst events will help to improve the understanding of the physical mechanism of solar activities and strengthen the ability to interpret space weather.In order to solve the problems of small sample data,slow detection speed,low positioning accuracy and large interference of human factors in the traditional radio burst event detection methods,a small sample target detection method based on deep learning is proposed to automatically identify and locate different radio burst events in the solar radio spectrum.Firstly,due to the lack of public radio burst event detection data set,based on the radio spectrum data observed by the green bank solar radio burst spectrometer in United States,a small sample domain target detection data set with three burst types and 745 images is constructed.Then,the small sample learning method based on transfer learning is used to solve the problem of small sample data in radio burst event detection data set.Experimental results show that the proposed method is feasible and effective.

Speech-driven Personal Style Gesture Generation Method Based on Spatio-Temporal GraphConvolutional Networks

ZHANG Bin, LIU Chang-hong, ZENG Sheng, JIE An-quan

Computer Science. 2022, 49 (11A): 210900094-5. doi:10.11896/jsjkx.210900094

Abstract

PDF(2611KB) ( 328 )

References | Related Articles | Metrics

People’s gestures in speaking often have their own unique personal style.Researchers have proposed a speech-driven personal style gesture generation method based on generative adversarial networks.However,the generated actions are unnatural for temporal discontinuity.To solve this problem,this paper proposes a speech-driven personal style gesture generation method based on the spatio-temporal graph convolutional networks,which adds the temporal dynamic discriminator based on spatio-temporal graph convolutional network.The spatial and temporal structural relationships between gesture joint points is firstly constructed,and then the spatial correlation of gesture joint points is captured and the dynamic characteristics in time sequence are extracted through the spatio-temporal graph convolution network(STGCN),so that the generated gestures maintain the consistency in time sequenceand are more consistent with the behavior and structure of real gestures.The proposed method is verified on the speech and gesture dataset constructed by Ginosar et al.Compared with relevant methods,the percentage of correct keypoints improves by about 2%~5%,and the generated gestures are more natural.

Wood Surface Defect Recognition Based on ViT Convolutional Neural Network

GUO Wen-long, LIU Fang-hua, WU Wan-yi, LI Chong, XIAO Peng, LIU Chao

Computer Science. 2022, 49 (11A): 211100090-6. doi:10.11896/jsjkx.211100090

Abstract

PDF(3382KB) ( 304 )

References | Related Articles | Metrics

There are some problems in manual detection because it is necessary to grade the wood board through its surface defects.In order to solve the problem of wood surface defect recognition,a convolution neural network model integrating ViT is proposed to improve the accuracy of defect recognition.For this purpose,four kinds of wood surface defect pictures of crack,wormhole,knot and texture are collected,in which the number of crack and wormhole pictures is far less than that of knot and texture.In order to solve the problem of sample imbalance in model training,ProGAN is used to train crack and wormhole pictures and generate pictures of the same type of defects,so as to increase their number and keep the number of four kinds of pictures balanced.Before the experiment,the data of defect images are enhanced and salt and pepper noise is added to sort out the required image data set.Based on the convolutional neural network model fused with ViT,two models with different activation functions are tested by using the data set.It is found that the model using GELU as the activation function has higher perfor-mance.The model performance at different transformer depths is tested,and the highest accuracy of model defect identification can reach 98.54%.Experiments show that the convolutional neural network model fused with ViT is feasible,which provides a new idea for the automatic detection of wood surface defects.

Multi-font Printed Uyghur-Kazakh-Kirghiz Keyword Image Recognition

SARDAR Parhat, ABDURAHMAN Kadir, ALIMJAN Yasin

Computer Science. 2022, 49 (11A): 211100038-6. doi:10.11896/jsjkx.211100038

Abstract

PDF(3348KB) ( 272 )

References | Related Articles | Metrics

Aiming at the problems of single font type,small size of recognition data,indistinguishable recognition fields and lack of research on Kazakh and Kirghiz printed character recognition,a multi-font printed Uyghur-Kazakh-Kirghiz keyword recognition method based on convolutional neural network(CNN) is proposed.Firstly,aiming at the problem of lack of Uyghur-Kazakh-Kirghiz printed image corpus,based on image synthesis technique,a Uyghur-Kazakh-Kirghiz keyword image data set including 32 font type is constructed.Secondly,using data augmentation technology to add different level of noise,rotation and distortion effects on these images to further reflect the natural scene features of the data set.Thirdly,using a multi-layer CNN network to train the image recognition model on this data set,and obtaining the recognition accuracy over 96.5%,and the accuracy of about 96% is obtained in the actual print image recognition task including 3 commonly used fonts.This method has fewer pre-proces-sing steps and it outperforms previous recognition approaches within the classical machine learning framework.Experimental results show that the recognition method based on synthetic image data can better realize the task of multi-font printed Uyghur-Kazakh-Kirghiz image recognition.

Study on Voiceprint Recognition Based on Mixed Features of LFBank and FBank

CUI Lin, WANG Zhi-yue

Computer Science. 2022, 49 (11A): 211000194-5. doi:10.11896/jsjkx.211000194

Abstract

PDF(2144KB) ( 312 )

References | Related Articles | Metrics

Speech feature extraction is an important step in the process of voiceprint recognition.There is a large gap between men and women in the distribution of sound frequency,but the existing feature extraction algorithms have not made correspon-ding improvements for the sound frequency characteristics of different genders.To solve the above problems,a speech feature extraction algorithm LFBank designed for female voiceprint recognition is proposed.The linear filter banks is introduced into the feature extraction process,and its linear distribution is used to make up for the deficiency of the traditional Mel filter banks in extracting high-frequency region information.On the other hand,in order to break through the limitation of single gender and broaden the application scenarios,combining the advantages of linear filter banks and Mel filter banks,LFBank and FBank features are combined to obtain mixed feature vectors for voiceprint recognition.The LFBank is compared with the commonly used feature FBank and MFCC,and experimental results show that the feature vector based on linear filter bank has more advantages in recognizing female voice.For mixed features,in the comparison experiment with single features,they can achieve better recognition effect than single features and have a wider range of application scenarios.

Handwritten Digit Recognition Based on Attention Mechanism

LI Bo-yan, ZHANG Yong, YUAN De-rong, XIONG Tang-tang, HE Lang

Computer Science. 2022, 49 (11A): 211100009-5. doi:10.11896/jsjkx.211100009

Abstract

PDF(2900KB) ( 352 )

References | Related Articles | Metrics

As an important branch of pattern recognition,handwritten digit recognition is in an unprecedented upsurge,and con-volutional neural networks are also widely used in related research.In view of the problem that gradient explosion and gradient dispersion are prone to occur in the training process of handwritten digit recognition,which leads to low image recognition accuracy,a model embedded with convolutional block attention module(CBAM)is newly proposed for handwritten digit recognition.The CBAM is embedded in the convolutional neural network in order to screen out effective features from the channel and spatial dimensions respectively,suppress irrelevant features,enhance the expression ability of features,and improve the recognition accuracy of the model.In order to further improve the accuracy of network identification,the batch normalization(BN) algorithm is fully applied in the entire network architecture to speed up the model convergence,in this way,the anti-over-fitting ability of the model gets improved.The results of experiments which are conducted on the MNIST dataset show that the overall recognition accuracy of the embedded CBAM attention module network is up to 99.87%,and compared with some traditional convolutional neural network models,its recognition accuracy is significantly improved.

Sentiment Analysis Framework Based on Multimodal Representation Learning

HU Xin-rong, CHEN Zhi-heng, LIU Jun-ping, PENG Tao, YE Peng, ZHU Qiang

Computer Science. 2022, 49 (11A): 210900107-6. doi:10.11896/jsjkx.210900107

Abstract

PDF(2371KB) ( 408 )

References | Related Articles | Metrics

In the process of learning the overall loss of multimodal representations,the dependence of reconstruction loss on the model is relatively less,resulting in hidden representations that cannot effectively capture the details of their respective modalities.This paper proposes a multi-subspace sentiment analysis framework.Firstly,the framework projects each modality to two distinct utterance representations:modality-invariant and modality-specific.We construct the main shared subspace and the auxi-liary shared subspace that helps the main subspace to reduce the modality gap in the modality-invariant representation.Also,construct the private subspaces in the modality-specific representation to capture the characteristic features of each modality.We take the hidden vectors in all subspaces as the input of the decoder function and reconstruct the modal vector to achieve optimization of reconstruction loss.Secondly,in the fusion procedure,we perform a multi-headed self-attention based on Transformer on these representations,so that each cross-modal representation can induce potential information from fellow representations that have a synergistic effect on the overall emotional orientation.Finally,we construct a joint-vector by using concatenation and use fully connected layers to generate task predictions.Experimental results on both MOSI and MOSEI datasets show that the proposed framework outperforms the baselines in most evaluation criteria.

R-YOLOv5:Auto-cutting,Rotated Text Detection Model

RAN Yu, ZHANG Li

Computer Science. 2022, 49 (11A): 210900185-6. doi:10.11896/jsjkx.210900185

Abstract

PDF(3223KB) ( 336 )

References | Related Articles | Metrics

YOLOv5 model is currently one of the best models for object detection.To solve the problem of different lengths of text lines,the inclination of text,light and shadow in natural scenes,etc.the R-YOLOv5(Rotated-YOLOv5) text detection model is proposed,which improves the YOLOv5 model to deal with the weakness in text detection.Firstly,the text segmentation model based on affine algorithm is incorporated.According to the length of the string and the shape of the text area,the text area of the picture is cut into multiple single-character blocks in equal proportions to solve the problem of poor effect of YOLOv5 model caused by the text objects without closed contour lines.Then,using the rotated convolutional neural network layer,rotated max-pooling layer and improved anchor box,we propose a rotated intersection over union(RIoU) loss function that strengthens angle learning to achieve the extraction of rotation and tilt features.The original model and the improved model are tested on ICDAR2019-LSVT.Experimental results show that the detection effect of R-YOLOv5 are significantly improved.However,due to the deepening of model layers,the training efficiency and detection efficiency are slightly reduced compared with the original mo-del.Compared with other models,due to the advantages of YOLOv5,the detection effect and efficiency of R-YOLOv5 are much better than that of other models.

Human-Object Interaction Recognition Integrating Multi-level Visual Features

LI Bao-zhen, ZHANG Jin, WANG Bao-lu, YU Ping

Computer Science. 2022, 49 (11A): 220700012-8. doi:10.11896/jsjkx.220700012

Abstract

PDF(3879KB) ( 360 )

References | Related Articles | Metrics

Computer vision based human action recognition technique has a broad application in the fields of video surveillance,intelligent driving,human-computer interaction,multimedia content audit,etc.More importantly,human-object interaction is one of the core components in human action recognition.Most of the existing human-object interaction action recognition models,which are based on multi-stream convolutional neural networks,only capturing the visual features superficially.They fail to fully explore the key areas of human body and the deep semantic relationship between human and objects.To solve this problem,this paper proposes a hierarchical graph neural network(HGNN) model.HGNN explicitly models the critical areas of the human body and the interaction of human-object in the scene from local to global,and uses an attention pooling mechanism(AttPool) to eliminate redundant information and noise in the graph.Then,the deep semantic relationship between graph nodes are captured by the graph convolution network,and the initial features extracted by convolutional neural network are aggregated and optimized.In this way,the feature representation which reflects the essential character of human-object interaction can be obtained.In addition,the interim supervised classification in the middle graph can also constrain the model to better learn the human patterns of interactive actions,and avoid the model to produce “bias” on the interactive objects.Finally,a multi-task loss function is designed for the HGNN to effectively train the model.To test and verify the effectiveness of the proposed HGNN model,extensive experimental evaluations on the famous public benchmark V-COCO have been conducted.The results show that the proposed HGNN model is adaptive and robust for human-object interaction detection,which outperforms the previous graph neural network based me-thods by a large margin,and also performs better than most of the latest convolutional neural network based models.

Generation and Application of Adversarial Network Traffic:A Survey

WANG Jue, LU Bin, ZHU Yue-fei

Computer Science. 2022, 49 (11A): 211000039-11. doi:10.11896/jsjkx.211000039

Abstract

PDF(2327KB) ( 517 )

References | Related Articles | Metrics

The spurt of artificial intelligence technology is profoundly affecting the strategic landscape of cyberspace security,showing great potential in the field of intrusion detection.Recent research finds that machine learning models have severe vulnerabilities,and the adversarial samples derived from this vulnerability can significantly reduce the correctness of model detection by adding some minor perturbations to the original samples.The generation and application of adversarial images has been extensively and intensively studied by academics in the field of computer vision.However,in the field of intrusion detection,the exploration of adversarial network traffic continues to evolve.Based on an introduction to the basic concepts,threat models and evaluation metrics of adversarial network traffic,the research works on adversarial network traffic in recent years are summarized,and the generation methods are classified into five categories according to their generation methods and principles:1) gradient-based generation method;2) optimization-based generation method;3)GAN-based generation method;4) decision-based generation me-thod;5) migration-based generation method.Through the discussion of related issues,an outlook on the development trend of this technology is presented.

Survey of Adversarial Attacks and Defense Methods for Deep Neural Networks

ZHAO Hong, CHANG You-kang, WANG Wei-jie

Computer Science. 2022, 49 (11A): 210900163-11. doi:10.11896/jsjkx.210900163

Abstract

PDF(2758KB) ( 527 )

References | Related Articles | Metrics

Deep neural networks are leading a new round of high tide of artificial intelligence development,and have made remar-kable achievements in many fields.However,recent studies have pointed out that deep neural networks are vulnerable to adversa-rial attacks,resulting in incorrect network outputs,and their security has attracted great attention.This paper summarizes the current state of research on adversarial attacks and defense methods from the perspective of deep neural network security.Firstly,it briefly describes the related concepts and existence explanations around the adversarial attacks of deep neural networks.Secondly,it introduces adversarial attacks from the perspectives of gradient-based adversarial attacks,optimization-based adversarial attacks,migration-based adversarial attacks,GAN-based adversarial attacks and decision boundary-based adversarial attacks,and analyses the characteristics of each adversarial attack method,analyzing the characteristics of each attack method.Again,the defense methods of adversarial attacks are explained from three aspects,including data-based pre-processing,enhancing the robustness of deep neural network models and detecting adversarial samples.Then,from the fields of semantic segmentation,audio,text recognition,target detection,face recognition,reinforcement learning,examples of adversarial attacks and defenses are listed.Finally,the development trend of adversarial attacks and defenses in deep neural networks is forcasted through the analysis of adversarial attacks and defense methods.

Heuristic Method for Building Internet Multilayer Network Model

CHENG Qiu-yun, LIU Jing-ju, YANG Guo-zheng, LUO Zhi-hao

Computer Science. 2022, 49 (11A): 210800249-6. doi:10.11896/jsjkx.210800249

Abstract

PDF(2285KB) ( 280 )

References | Related Articles | Metrics

With the continuous expansion of network scale,the characteristics of hierarchical and modular network structures are increasingly prominent.Traditional single-layer network research paradigm has some limitations in representing the complex relationships among various network systems.The characteristic analysis and model construction of multilayer networks have gradually become an important direction of complex network research.Aiming at the characteristics of multilayer network structure presented in the application of Internet,this paper puts forward the multilayer network model for the Internet and the significance of constructing a multilayer network model in the field of Internet.By analyzing the characteristics of Internet data,this paper designs a multilayer network model covering three types of networks,namely,the Internet infrastructure layer,the business application layer,and the user account layer.This paper proposes a heuristic single-layer network generation model to solve the problem that the current network generation model based on node degree cannot describe the distribution of network cores.Based on the generation model of a single-layer network,the interlayer association method of a multilayer network is designed to realize the model construction of a multilayer network.

Distributed Encrypted Voting System Based on Blockchain

ZHANG Bo-jun, LI Jie, HU Kai, ZENG Jun-hao

Computer Science. 2022, 49 (11A): 211000212-6. doi:10.11896/jsjkx.211000212

Abstract

PDF(2322KB) ( 315 )

References | Related Articles | Metrics

With the development and progress of society,many application scenarios require voting.The current electronic voting system has the characteristics of centralization,the voting process is difficult to be open and transparent,voters cannot verify the results of the ballot,and a trusted third-party vote-counting agency is required to participate in the voting.In response to the above problems,in order to better adapt to the increasingly abundant application scenarios,this paper studies and proposes a distributed encrypted voting system based on blockchain.The ElGamal encryption algorithm in a distributed environment ensures the security and confidentiality of the entire voting process,and no one or organization can crack the intermediate results of obtaining votes.The automatic execution mechanism of blockchain smart contract replaces the traditional third-party trusted ticket counting agency to realize automatic ticket counting.Since all voting information is stored on blockchain,it further ensures that the voting process is transparent and open,and the results can be verified and traceable.Experimental verification shows that the bottleneck of the voting system is the accumulative multiplication algorithm in the voting process.In order to improve computing efficiency,the method of on-chain and off-chain collaborative computing is further adopted.Under the premise of ensuring the security of bills,the off-chain speed of calculation is accelerated through parallel computing.Finally,the security and performance analysis shows that the mechanism has good scalability and is a practical and safe electronic voting system design scheme.

Study on Formal Verification of EAP-TLS Protocol

CHEN Li-ping, XU Peng, WANG Dan-chen, XU Yang

Computer Science. 2022, 49 (11A): 211100111-5. doi:10.11896/jsjkx.211100111

Abstract

PDF(2863KB) ( 302 )

References | Related Articles | Metrics

EAP-TLS is a security protocol defined under the 5G standard that provides key services in a specific IoT environment.However,the EAP-TLS protocol cannot provide mutual authentication between user equipment and the network.A protocol with design flaws will endanger the security of the system during operation.Therefore,it is a very necessary process to analyze its security before the implementation of the protocol,try to find potential flaws and improve them.This paper studies theformal model of EAP-TLS protocol and security properties based on Proverif,and verifies the security properties such as the mutual authentication between user equipment and network,confidentiality between KSEAF(security anchor key) and subscriber permanent identity(SUPI).Verification results find that there are some security flaws in the EAP-TLS protocol in terms of authentication under insecure channels,and the user equipment fails to authenticate the network.Analytical results further confirm the reasons of security flaws,and the corresponding attacks are also given.Finally,the possibility of improving security flaws is discussed based on asymmetric key encryption and random numbers in cryptography.

Mimic Firewall Executor Scheduling Algorithm Based on Executor Defense Ability

LIU Wen-he, JIA Hong-yong, PAN Yun-fei

Computer Science. 2022, 49 (11A): 211200296-6. doi:10.11896/jsjkx.211200296

Abstract

PDF(2888KB) ( 381 )

References | Related Articles | Metrics

Mimic defense technology is an effective means to solve the easy to attack but difficult to defend situation in existing network environment.Mimic defense technology builds a safe and reliable system by improving the dynamics,heterogeneity and randomness of the system.The scheduling of heterogeneous executive bodies is the key link of mimic defense.Existing scheduling algorithms lack of situational awareness and can only schedule the executor according to the existing strategy,which has the problem of poor applicability.For this reason,DCOE,a scheduling algorithm based on the comprehensive defense capability of the executive body is proposed.Based on the classic traffic monitoring algorithm,DCOE identifies the threat type and threat level of the current traffic,and dynamically adjusts the types and numbers of heterogeneous executives according to the defense capabilities of each executive against the current traffic.Simulation experiments show that,the DCOE algorithm can reduce the failure rate and escape rate of the system on the basis of reducing the number of scheduling heterogeneous executives,that is,improve the overall defense level of the system on the premise of reducing the system overhead,and increase the difficulty of the adversary’s attack.

Efficient Routing Strategy for IoT Data Transaction Based on Payment Channel Network

LI Dun-feng, XIAO Yao, FENG Yong

Computer Science. 2022, 49 (11A): 211100010-5. doi:10.11896/jsjkx.211100010

Abstract

PDF(2743KB) ( 308 )

References | Related Articles | Metrics

In order to improve the efficiency of data transactions in Internet of Things,an efficient routing strategy based on payment channel network(PCN) is proposed.This strategy improves the defects of PCN network from two aspects:gateway selection and large-value transaction splitting.By calculating the payment and receiving fund flow ratios of different gateways,the appropriate gateways are selected for transactions to ensure the balance of the network,which increases the stability of the network.In order to solve the problem of insufficient channel capacity in large-value transactions,a single transaction is split into multiple transaction units,and path selection is performed through a multi-channel equalization algorithm,which reduces the number of transactions on the chain and improves the transaction efficiency of the network.Simulation results show that the program has a higher transaction success rate and lower transaction delay.

Discovery of Unknown UDP Reflection Amplification Protocol Based on Traffic Analysis

LU Xuan-ting, CAI Rui-jie, LIU Sheng-li

Computer Science. 2022, 49 (11A): 211000089-5. doi:10.11896/jsjkx.211000089

Abstract

PDF(2225KB) ( 381 )

References | Related Articles | Metrics

In recent years,the frequency and scale of DDOS attacks have increased,which has posed great challenges to network security.Among them,UDP reflection amplification attacks have become the attack method favored by hackers due to their low attack cost,huge attack traffic,and difficulty in tracing the source.Most of the current filtering and defense strategies are derived from the analysis and review after the attack,and there is a certain degree of passivity and lag in the face of the endless new UDP reflection attacks.This paper proposes a method based on traffic analysis to discover undisclosed protocols with the potential of UDP reflection amplification.Based on the two fundamental characteristics of magnification and reflectivity,this method selects traffic samples that meet the characteristics of reflective amplification from daily network traffic.Then,the replay attack is used to verify whether the samples are repeatable,and the qualified samples are recorded for research on related service protocols.Finally,a new type of undisclosed reflection amplification protocol is successfully discovered.The detection program constructed with this method has been tested for accuracy and processing rate in the experimental environment and the Internet respectively,and a variety of reflection amplification protocols are found to proactively defend against possible reflection amplification attacks.

State Synchronization Scheme Supporting Multiple Rounds of PBFT VerificationAlgorithm in Sharding

GAO Dong-xue, LI Zhi-huai, DUAN Pei-pei, CHEN Yu-hua

Computer Science. 2022, 49 (11A): 211000125-7. doi:10.11896/jsjkx.211000125

Abstract

PDF(3472KB) ( 267 )

References | Related Articles | Metrics

Sharding is one of the on-chain solutions for blockchain scalability.State sharding can solve the scalability problem of the public chain without reducing security.Each state sharding only maintains a part of the state.There is a certain probability that the proportion of Byzantine nodes will exceed one third in a single sharding,even if the probability of Byzantine nodes is no more than one third in all nodes with PBFT consensus algorithm,resulting in the failure of verifying the consensus.Therefore,the nodes in the sharding need to be reconfigured periodically,and multi-round PBFT consensus verification algorithm with small time slots can effectively solve this problem.However,stateless nodes cannot work effectively,and new nodes need to synchronize the state of the sharding.The state synchronization scheme based on candidate nodes queue for multi-round PBFT consensus verification algorithm is proposed to solve this problem.Nodes that are in synchronized state first enter the queue of candidate nodes,and different candidate nodes are provided for each round of PBFT consensus verification.At the same time,a node gets a corresponding credits based on its historical behavior record during status synchronization to help optimizing the subsequent algorithm.Finally,experiment shows that the proposed scheme not only solves the problem of state synchronization,but also improves the efficiency of consensus verification and the throughput of the system.

Reentrancy Vulnerability Detection Based on Pre-training Technology and Expert Knowledge

CHEN Qiao-song, HE Xiao-yang, XU Wen-jie, DENG Xin, WANG Jin, PIAO Chang-hao

Computer Science. 2022, 49 (11A): 211200182-8. doi:10.11896/jsjkx.211200182

Abstract

PDF(3917KB) ( 415 )

References | Related Articles | Metrics

As the security issues of smart contracts in blockchain become increasingly prominent,the vulnerability detection tasks of smart contracts have gradually become a research hotspot.However,the current smart contract reentrancy vulnerability detection technologies are mainly traditional detection methods such as symbolic execution,static analysis,formal verification and fuzzing.These detection methods not only have high false positive rate and false negative rate,but also have low detection accuracy.At the same time,methods based on deep learning also have their unique limitations.In response to these problems,this paper proposes a detection method that combines pre-training technology and traditional expert knowledge,and at the same time slices smart contracts to reduce the impact of irrelevant data on the model.This paper focuses on the detection of reentrancy vulnerability and conducts experiments on 203716 contract data sets.Experimental results show that the smart contract reentrancy vulnerability detection method based on pre-training technology and expert knowledge has an accuracy rate of 96.2%,a recall rate of 97.7% and a F1 score of 96.9%,which are better than existing detection methods.

Adversarial Character CAPTCHA Generation Method Based on Differential Evolution Algorithm

YANG Hao, YAN Qiao

Computer Science. 2022, 49 (11A): 211100074-5. doi:10.11896/jsjkx.211100074

Abstract

PDF(2127KB) ( 295 )

References | Related Articles | Metrics

CAPTCHA is widely used in the registration and login process of websites and applications to distinguish normal users from programs.However,with the advancement of deep learning,many deep learning recognition methods for CAPTCHA have been proposed.CAPTCHA can no longer distinguish human users from computer programs effectively,and its security has been greatly challenged.The adversarial example can make the output result of neural network completely different from its original predicted result.Recent researches find that combining adversarial example with CAPTCHA is an effective method to resist the attack of deep learning recognition system.Researchers use adversarial example generation methods to generate adversarial chara-cter CAPTCHA to defend against deep learning methods.Existing adversarial character CAPTCHA generation methods are white-box methods that require knowledge of the structural parameter information of the attacking network.However,practical CAPTCHA application scenarios usually do not know the information of the attacking network,so robust CAPTCHA should be able to perform well without knowing the attack information.In this paper,a character-based adversarial CAPTCHA generation method(ACoDE) based on differential evolution algorithm is proposed to improve the solving ability of the algorithm by optimizing the scaling factor in the mutation process and the population evolution strategy.Without knowing the information of the attacking network,the adversarial examples generated by the proposed method are more capable of misleading the neural network.The adversarial example generation method is used for the character CAPTCHA dataset,and the success rate of the current state-of-the-art CNN character-based CAPTCHA recognition system reduce to less than 30%.The visual effect of the adversarial CAPTCHA is satisfactory when compare with other white-box methods.

Vector Representation and Computation Based Dynamic Access Control in Open Environment

WANG Qing-xu, DONG Li-jun, JIA Wei, LIU Chao, YANG Guang, WU Tie-jun

Computer Science. 2022, 49 (11A): 210900217-7. doi:10.11896/jsjkx.210900217

Abstract

PDF(3171KB) ( 342 )

References | Related Articles | Metrics

Access control is the basic technology of network security.With the development of big data technology and open networks,the access behavior of Internet users has become more and more flexible.Traditional access control mechanisms mainly improve the efficiency of access control from two aspects:automatic rule generation and rule matching optimization.Most of them use the traversal matching mechanism,which has problems of large amount of calculation and low efficiency,and it is difficult to meet the dynamic and efficient demand of access control in an open environment.Inspired by the distributed embedded technology in the field of artificial intelligence,this paper proposes vector representation and computation based access control(VRCAC) model based on vector representation and computation.Firstly,the access control rules are converted into numerical vectors,so that the computer can realize fast access judgment by numerical calculation.The positional relationship between the user vector and the permission vector can be expressed by the inner product value of the two,and the inner product value is related to the relationship threshold.Thus,the relationship between users and permissions can be quickly determined.This method reduces the time complexity of access control execution,thereby improving the execution efficiency of access control in an open big data environment.Finally,on two real data sets,a comparison experiment is carried out using multiple evaluation indicators such as accuracy rate and false alarm rate,which verifies the effectiveness of the proposed method.

Detection of Malicious Behavior in Encrypted Traffic Based on Heuristic Search Feature Selection

YU Sai-sai, WANG Xiao-juan, ZHANG Qian-qian

Computer Science. 2022, 49 (11A): 210800237-6. doi:10.11896/jsjkx.210800237

Abstract

PDF(2230KB) ( 313 )

References | Related Articles | Metrics

With the proportion of encrypted traffic in the network increasing,there are more and more malicious behaviors hidden in the encrypted traffic,which makes the situation of network security more and more serious.Encrypted traffic with some malicious behavior contains a variety of traffic characteristics,among which there is some redundancy.Redundant features will increase the detection time and reduce the efficiency of model detection.Based on the principle of heuristic search strategy,this paper selects many different features of encrypted traffic and finds out the representative combination of features.Firstly,the feature importance is sorted according to the random forest algorithm,and the features that have a great impact on the classification results are selected.Then,the similarity between all features is calculated by Pearson correlation coefficient,and the relatively independent feature combinations are selected.Experimental results on the data set CTU-13 show that,by screening representative feature combinations,detection time is reduced and the detection efficiency of encrypted traffic malicious behavior can be improved without decreasing the detection accuracy.

Application of Improved Feature Selection Algorithm in Spam Filtering

LI Yong-hong, WANG Ying, LI La-quan, ZHAO Zhi-qiang

Computer Science. 2022, 49 (11A): 211000028-5. doi:10.11896/jsjkx.211000028

Abstract

PDF(1869KB) ( 311 )

References | Related Articles | Metrics

Spam usually refers to e-mails with promotional materials,viruses and other contents that are forcibly sent to the user’se-mail address without user’s request.It has the characteristics of batch sending,and will cause great harm on the Internet.Therefore,it is very important to filter out these spams for users.The essence of the spam filtering problem is a text classification problem,which has a very high features dimension.But not all features contribute to classification,so choosing a suitable subset of features that can reflect the entire data set is the basis for constructing a good email classifier.Existing feature selection me-thods have some limitations,such as redundancy between features,unstable result of feature reduction and high computational cost.By studying and analyzing some of the advantages and disadvantages of the existing spam processing methods,a new integrated feature selection method based on the information gain method and the granular ball neighborhood rough set method is proposed,named IGBNRS algorithm.Through the experimental comparison on different classification models,the proposed algorithm simplifies the model and has a good performance.

Study on Office Password Recovery Vectorization Technology Based on Sunway Many-core Processor

LI Hui, HAN Lin, TAO Hong-wei, DONG Ben-song

Computer Science. 2022, 49 (11A): 210900176-5. doi:10.11896/jsjkx.210900176

Abstract

PDF(2302KB) ( 311 )

References | Related Articles | Metrics

In order to meet the needs of data security in agricultural and rural big data applications,the paper combines the hot computing issues in Office password recovery and uses Sunway many-core processors as the hardware platform to provide a vectorized password solution method.The analysis of SHA-1 and AES functions is the core part of the method.Firstly,using the characteristics of Sunway many-core processors to conduct automatic vectorization research.Secondly,through dependency analysis,the manual vectorization process between plaintext blocks is described,and the feasibility conclusion of the method theory is given.Finally,to verify the correctness and effectiveness of the method,the encrypted documents of each version of Office are used as use cases,and multiple data tests are carried out.The test results are compared with the traditional password recovery tool and the open-source Hashcat password recovery tool.Experimental results show that the method can effectively improve the performance of password recovery.

Power Internet of Things Device Access Management Based on Cryptographic Accumulator

CHEN Bin, XU Huan, XI Jian-fei, LEI Mei-lian, ZHANG Rui, QIN Shi-han

Computer Science. 2022, 49 (11A): 210900218-6. doi:10.11896/jsjkx.210900218

Abstract

PDF(2492KB) ( 382 )

References | Related Articles | Metrics

Device access is the first line of defense for the security protection of the power Internet of Things,and it is the pre-mise for realizing security mechanisms such as access control and intrusion detection.Complete device access management covers two key links:trusted authentication and secure revocation.Most existing systems rely on PKI to establish trusted infrastructure,and realize access management through the issuance,verification and revocation of public key certificates.However,in the scenario of power Internet of Things,this scheme brings extra overhead burden and efficiency problems to a large number of devices with limited resources.The lightweight authentication scheme has realized the optimization of overhead and efficiency,but it is not functional enough to realize the key link of safe revocation.In view of the above shortcomings,this paper proposes an access ma-nagement scheme for power Internet of Things devices based on cryptography accumulator and Bloom filter,which simultaneously realizes trusted authentication and security revocation of devices,and effectively considers both functions and efficiency.Through security analysis,this scheme realizes anonymous authentication of gateway,unforgeability of identity certificate and security of forced revocation.Experimental results show that,compared with the mainstream PKI-based device access management scheme,this scheme greatly reduces the communication overhead and storage overhead in the process of device authentication and revocation,and has higher practicability in the power Internet of Things scene.

Overview of Android GUI Automated Testing

YANG Yi, WANG Xi, ZHAO Chun-lei, BU Zhi-liang

Computer Science. 2022, 49 (11A): 210900231-10. doi:10.11896/jsjkx.210900231

Abstract

PDF(2078KB) ( 584 )

References | Related Articles | Metrics

With the increasing number of new types and versions of mobile apps,the traditional manual testing methods can’t cater for the demand.Therefore,more effective automated testing methods need to be proposed.In the process of automated testing,the GUI (Graphical User Interface) of Android apps plays an extremely important role.GUI automated testing has become the focus of researchers because of its excellent test coverage and ability of crash detection.In this paper,the current research on GUI automated testing is sorted out and summarized,and the representative automated testing framework is chosen for detailed analysis.The selected automated testing tools are classified,analyzed and compared from the aspects of testing strategy,exploration strategy,crash report,whether to support replay,testing environment,supported event type,whether to use source code,whether open source,and system event identification method.At the same time,some representative automated testing frameworks are selected for contrast experiments to explore the testing efficiency and their advantages and disadvantages.Finally,the challenges faced by the current research and the future development prospects are proposed.

Review on Technologies of Requirement Engineering of Software

WANG Hao-yu

Computer Science. 2022, 49 (11A): 210900132-14. doi:10.11896/jsjkx.210900132

Abstract

PDF(2197KB) ( 614 )

References | Related Articles | Metrics

As the first process of software project,requirements engineering’s implementation quality can determine whether a software project can success or not.Requirements engineering was put forward in the 1980s the first time,and the model used also transited from the earliest process oriented model to the object-oriented model widely used in industry,and then to the service-oriented model proposed and gradually promoted after 2004.In addition,with the rapid improvement of hardware performance and the resurgence of artificial intelligence,the efficiency and scale of natural language processing are increasing,which makes it easier for requirements engineering to use natural language processing to analyze large amounts of text data.The emergence of IoT,edge computing and big data makes it easier for investors and developers to obtain a large amount of user data and business information.As a new concept,data-driven requirements engineering is gradually known by the industry.This paper reviews the development history of requirements engineering at first,including requirements engineering methodology,object-oriented modeling,requirements engineering based on ontology and facial features,and automatic requirements extraction technology related to machine learning.Then it focuses on three research directions of requirements engineering,including the natural language processing methods and some supported language types,the development history,tools and methods proposed in recent years of agile requirements engineering,as well as the concept,necessity and process,the main methods and practices of data-driven requirements engineering in recent years.Finally,based on the reports on the development situations of requirements engineering in some countries,this paper analyzes the difficulties and challenges of requirements engineering in recent years,and prospects the future development of requirements engineering.

Multi-source Cross-project Defect Prediction with Data Selection

DENG Jian-hua, WANG Wei

Computer Science. 2022, 49 (11A): 210800160-7. doi:10.11896/jsjkx.210800160

Abstract

PDF(2632KB) ( 281 )

References | Related Articles | Metrics

Multi-sources cross project defect prediction(MCPDP) aims to use multiple historical data from other projects(source projects) to predict the likelihood of defects in software modules in the target project.The research solves the cold start problem of defect prediction modeling and provides a solution for establishing defect prediction model for new software or software system lacking historical data.Source data selection is considered to be an effective way to further improve the accuracy of cross-project defect prediction.Therefore,a multi-source cross-project defect prediction method for data selection is studied in this paper.The method includes two steps:1) feature alignment of source data;2) improve the maximum mean measure to realize source data screening.In order to verify the effectiveness of the proposed method,experiments are carried out on four public data sets,namely AEEEM,Relink,NASA and SOFTLAB.The results show that the proposed method improves the F-measure index by 4% and 5% respectively compared with the baseline method,which proves that the proposed method has good performance.

Web Service Modeling Based on Model-driven and Three-stage Model Transformation Method

WANG Chang-jing, DING Xi-long, CHEN Xi, LUO Hai-mei, ZUO Zheng-kang

Computer Science. 2022, 49 (11A): 211100055-14. doi:10.11896/jsjkx.211100055

Abstract

PDF(2072KB) ( 398 )

References | Related Articles | Metrics

Describing the semantics of web services accurately plays a crucial role in service discovery,execution,dynamic composition and interaction.In order to support web service modeling,this paper proposes four models from abstract to concrete:Radl-WS service requirement model,Apla service design model,Java executable code,and WSDL/RESTful API.To suppor model transformation,a three-phase method that generates an executable code by transformation is further proposed.The first stage transforms the Radl-WS service requirement modeling language into the Apla service design language,the second stage uses the Apla service design language to generate executable codes through related conversion tools,the third stage encapsulates the executable codes into services.Then the semantic correctness of the three-stage model transformation is studied.Through examples,the actual effect of the proposed method is demonstrated.

Code Similarity Measurement Based on Graph Embedding

LIANG Yao, XIE Chun-li, WANG Wen-jie

Computer Science. 2022, 49 (11A): 211000186-6. doi:10.11896/jsjkx.211000186

Abstract

PDF(2503KB) ( 333 )

References | Related Articles | Metrics

In recent years,code similarity detection has been a hot topic in the field of software engineering,which can help code clone detection,code defect prediction,and reduce the cost of software maintenance.At present,most popular code similarity detection methods build language processing model to extract the text,syntax,structure and other feature information of source code from tokens,AST and other code representations,and map them to real value vectors in continuous space.Then,obtain the similar value of the code comparison by calculating the Euclidean distance and cosine value of the extracted features or by the shallow neural network model.These methods have achieved better results than the traditional static analysis program.However,most of these methods are based on the grammar level of source code,which can not make full use of the semantic information of source code.Although Doc2Vec and Word2Vec can extract the lexical semantic information of code,they are powerless to handle the execution semantic information of code.To solve this problem,control flow graph(CFG) is proposed to represent the execution semantics of code,and the graph embedding method based on random walk is used to learn and reason the semantic information of the code,and then judge the functional similarity of the source code.Compared with Doc2Vec and Word2Vec methods,experimental results show that the model can accurately detect the functional similarity of source code,and its F1 value improves by 16.01% and 18.72% compared with Doc2Vec and Word2Vec methods,respectively.

Survey of Research on Task Offloading in Mobile Edge Computing

GAO Yue-hong, CHEN Lu

Computer Science. 2022, 49 (11A): 220400161-7. doi:10.11896/jsjkx.220400161

Abstract

PDF(1964KB) ( 534 )

References | Related Articles | Metrics

With the popularity of the Internet of things and the development of wireless communication technologies such as 5G,various new services emerge one after another,and mobile data traffic is also growing exponentially.In order to guarantee the quality of service,the mobile computing model has changed from traditional cloud computing to mobile edge computing(MEC).The main feature of mobile edge computing is setting network resources at the edge of the network to meet the needs of delay-sensitive and computation-intensive tasks and provide users with better services.Task offloading is one of the main research problems in mobile edge computing.This paper summarizes the research status of task offloa-ding in MEC in recent years.Firstly,the basic concept,framework and typical application scenarios of MEC are introduced.Then it expounds the problem of task offloading,analyzes and summarizes the existing research results from minimum delay,minimum energy consumption and minimum weighted sum of delay and energy consumption respectively.Finally,the future research directions are prospected from four aspects:data dependency,user mobility,resource fairness and information security.

Workflow Scheduling Strategy for Deadline Constrained and Cost Optimization in Cloud

WANG Zi-jian, LU Zheng-hao, PAN Ji-kui, SUN Fu-quan

Computer Science. 2022, 49 (11A): 210800154-6. doi:10.11896/jsjkx.210800154

Abstract

PDF(2700KB) ( 281 )

References | Related Articles | Metrics

Workflow scheduling in cloud is one of the most challenging issues today.It focuses on executing workflow applications with interdependent tasks mapped to virtual machines under specified quality of service requirements.Cloud service provi-ders offer virtual machines with different performances at different prices.The same workflow with different virtual machines can result in different makespan and cost.One of the main problems of workflow scheduling in cloud is to find a cheaper scheduling method on the premise of meeting the deadline.The proposed deadline constrained cost optimization algorithm for workflow scheduling in cloud DCCO can solve the above problems.It assigns deadlines based on δ-alap and also considers cases where two tasks may be assigned to the same virtual machine.Experiments show that compared with other classical scheduling algorithms,DCCO has the highest success rate under different types of workflow tests,meets the deadline constraint,and can optimize the exe-cution cost.

Cost-aware IoT Data Processing in Edge-Cloud Collaborative Computing

WANG Chen-hua, HOU Shou-lu, LIU Xiu-lei

Computer Science. 2022, 49 (11A): 211000101-7. doi:10.11896/jsjkx.211000101

Abstract

PDF(2295KB) ( 256 )

References | Related Articles | Metrics

With the networking of Internet of Things(IoT) terminal devices,a large number of computation-intensive tasks appear.This paper proposes a cost-optimized big data processing method in the edge-cloud collaborative computing environment.Firstly,the proposed algorithm considers the constraints of network transmission bandwidth and computer resources,jointly optimizes bandwidth resources,and calculates resource distribution and dynamic offloading strategies.Secondly,based on the MapReduce framework,it establishes an edge-cloud collaborative computing model.According to Lyapunov optimization theory,it splits the target formula into four subproblems which can be solved separately.Comparative experiments results indicate that using the power of the edge rationally,the data processing efficiency of cloud computing can be improved and the expense of service provi-ders can be reduced.At the same time,the algorithm can improve the cost performance(the ratio of queue length to operating cost).In processing IoT data,is of great significance to reduce operating costs by utilizing edge-cloud collaborative computing methods.

SDN Oriented Mobile Network Reliability Evaluation Algorithm

BAO Chun-hui, ZHUANG Yi, GUO Li-ye

Computer Science. 2022, 49 (11A): 211000080-8. doi:10.11896/jsjkx.211000080

Abstract

PDF(2794KB) ( 275 )

References | Related Articles | Metrics

Aiming at the problems that existing reliability evaluation algorithms can not be directly applied to software defined network(SDN),and it is difficult to reasonably set the expert weight in the traditional network reliability evaluation process,a SDN oriented mobile network reliability evaluation algorithm is proposed,a fine-grained expert weight adaptive adjustment me-thod is designed,and the network reliability evaluation process is given in detail.Firstly,the reliability of mobile network node equipment in SDN is evaluated,and the expert evaluation fuzzy number is introduced in the evaluation process to adaptively adjust the expert weight in a finer granularity.Secondly,according to the mobile network topology based on SDN,the critical importance of mobile network nodes is analyzed to measure the critical degree of different types of node devices in network function services,so as to calculate the impact of nodes on the overall reliability of the network.Finally,based on the above two results,the reliabi-lity of the whole network is analyzed and evaluated.The effectiveness of the proposed algorithm is verified by examples and simulation experiments.Compared with similar algorithms,the proposed algorithm can achieve higher evaluation accuracy.

Inconsistency Elimination Algorithm Based on SPA and QoX

XING Qing-hua, XU Hong-ji, LIU Qiang, FAN Shi-di, LI Tian-kuo, CHEN Min

Computer Science. 2022, 49 (11A): 210700122-7. doi:10.11896/jsjkx.210700122

Abstract

PDF(3060KB) ( 338 )

References | Related Articles | Metrics

In the research and application of context-aware computing(CAC),it is inevitable to face the problems of uncertainty for context information.Context inconsistency is the most difficult problem to solve in the uncertainty problems.How to deal with context inconsistency reasonably and effectively is an important problem that must be solved.In this paper,a new inconsis-tency elimination algorithm based on set pair analysis(SPA) and quality of comprehensive indexes(QoX) is proposed to solve the inconsistency problem.The algorithm uses some parameters of QoX to evaluate the overall quality of contexts collected by the context sources,which improves the completeness and accuracy of the evaluation of overall quality of context.In addition,the algorithm uses SPA to quantitatively analyze the quality index from the similarity,opposition and difference,and takes into account the comprehensiveness in the calculation process of quality of context.Experimental results show that the proposed algorithm has higher accuracy than traditional processing algorithms.

Lossless Data Compression Method Based on Edge Computing

ZHANG Xiao-mei, CAO Ying, LOU Ping, JIANG Xue-mei, YAN Jun-wei, LI Da

Computer Science. 2022, 49 (11A): 210500195-6. doi:10.11896/jsjkx.210500195

Abstract

PDF(2671KB) ( 374 )

References | Related Articles | Metrics

Through the Industrial Internet of Things(IIoT),various industrial equipments,monitoring instruments and sensors can be connected to each other.The operating status of equipment can be fully sensed through monitoring instruments and sensors,and the equipment status can be analyzed and predicted based on sensing data.However,the analysis and processing of massive amounts of sensing data requires a lot of storage space and computing power.Sending it to the cloud platform will inevitably take up a lot of bandwidth and cause a large delay.It is difficult to meet the requirements for real-time analysis and diagnosis of device status.Therefore,for the state-aware data of industrial equipment,a lossless compression method based on optimal diffe-rential and linear fitting entropy reduction transform is proposed,and the perceptual data is compressed losslessly at the edge of data collection,so that the transmission efficiency is greatly improved and the perceptual data can be quickly transmitted to the cloud platform for analysis and processing.This method selects an effective entropy reduction transform from the optimal diffe-rence and curve fitting difference according to the variance of data difference sequence and the acquisition frequency,and uses Lempel-Ziv-Oberhumer(LZO) compression algorithm for secondary compression.The new method is tested on two different data sets.Experimental results show that the lowest and highest compression rate of this method can reach 77% and 93%,respectively.At the same time,the characteristics of its lossless reconstruction are verified.

UAV Base Station Deployment Method for Mobile Edge Computing

LIU Fang-zheng, MA Bo-wen, LYU Bo-feng, HUANG Ji-wei

Computer Science. 2022, 49 (11A): 220200089-7. doi:10.11896/jsjkx.220200089

Abstract

PDF(2846KB) ( 345 )

References | Related Articles | Metrics

In mobile edge computing (MEC),local devices can offload tasks to edge servers for execution to improve the quality of service (QoS).However,in disaster-stricken areas or in emergencies,ground-fixed base stations may be paralyzed on a large scale.For emergency communications,mobile edge computing systems supported by unmanned aerial vehicles (UAV) have emerged.As an emerging means of emergency communication,drones can carry edge servers,and ground user equipment can offload their computing tasks to the drones for execution.However,it is challenging to deploy multiple UAV base stations in a multi-user network.To this end,this paper focuses on the strategic deployment of UAV base stations,modeling the problem as a multi-objective optimization problem,which aims to balance the workload among UAV base stations and minimize the access delay between ground users and UAV base stations.Compared with single-objective optimization problems,multi-objectives interact with each other and the solutions are not unique,which brings certain difficulties to model solving.For this reason,this paper proposes a Pareto boundary search algorithm based on K-medoids to solve the problem,and then further proposes to use the principal component analysis algorithm (PCA) to find the most suitable solution from the Pareto boundary as the final deployment strategy for UAV base stations.The experiment in this paper uses real data sets and compares the performance with several other baseline methods to verify the effectiveness of the proposed solution.

Intelligent Jammers Localization Scheme Under Sensor Sleep-Wakeup Mechanism

YANG Si-xing, LI Ning, GUO Yan, YANG Yan-yu

Computer Science. 2022, 49 (11A): 211000165-6. doi:10.11896/jsjkx.211000165

Abstract

PDF(2800KB) ( 255 )

References | Related Articles | Metrics

Intelligent jammer can change its transmitting power to improve the jamming effect adaptively with the developing artificial intelligence(AI) technique,making the traditional localization scheme out of work.Therefore,this paper investigates the block compressive sensing(BCS) based multi-jammer localization scheme under sensor wake-up mechanism.Firstly,the sensor nodes are periodically awakened to prolong the lifetime of the network and to collect more accurate localization information.Se-condly,this paper introduces the reference power to avoid the issue that the relationship between the distance and the varying power are unknown.Thirdly,we utilize the compressive sensing(CS) theory to build the localization issue as a BCS recovery problem.Finally,a novel Wake-VBEM algorithm under the variational Bayesian mean-expect is proposed by exploring the power variation law.Simulations show that the proposed method can simultaneously estimate the location of multi-jammers and prolong the lifetime of the network even the power of the jammer is unknown and varying.

vSDN Fault Recovery Algorithm Based on Minimum Spanning Tree

CHEN Gang, MENG Xiang-ru, KANG Qiao-yan, ZHAI Dong

Computer Science. 2022, 49 (11A): 211200034-7. doi:10.11896/jsjkx.211200034

Abstract

PDF(3533KB) ( 246 )

References | Related Articles | Metrics

Aiming at the problem of fault recovery of virtual software-defined network,a fault recovery algorithm of virtual software-defined network based on minimum spanning tree is proposed to solve the difficulty of long recovery time of virtual software-defined network.On the one hand,the algorithm sets the importance of nodes and links according to the resources and topological attributes of nodes and links,and classifies nodes and links accordingly.On this basis,according to different physical networks,adjusting the ratio of backup and migration,improving the request acceptance rate and reducing the full recovery time after failure,so as to make full use of physical network resources.On the other hand,it analyzes the connectivity of virtual network,and uses the minimum spanning tree algorithm to restore the connectivity of virtual network first,and then completes the fault recovery of the remaining links,further reducing the fault recovery time on the basis of ensuring the connectivity of virtual network.Simulation results show that the algorithm can reduce the recovery time of virtual network on the basis of ensuring high request acceptance rate and recovery rate.

Evaluation Method for Multi-state Network Reliability Under Cost Constraint

XU Xiu-zhen, WU Guo-lin, ZHANG Yuan-yuan, NIU Yi-feng

Computer Science. 2022, 49 (11A): 211200259-7. doi:10.11896/jsjkx.211200259

Abstract

PDF(1952KB) ( 289 )

References | Related Articles | Metrics

Multi-state networks are composed of multi-state components that have different performance levels,and multi-state network model has been extensively used to describe the complex behaviors of many technological networks.Multi-state network reliability under cost constraint,denoted by Rel_(d,b),is defined as the probability that the network is able to transmit d units of flow from the source to the destination while satisfying the condition that the total transportation cost is within a given budget b,and can be computed in terms of minimal capacity vector with budget constraint(called(d,b)-MCV for short).Solving(d,b)-MCVs is an NP-hard problem,which means the computational time will exponentially increases with the network scale.In order to enhance the efficiency of solving(d,b)-MCVs,this paper constructs an improved model by introducing lower capacity bounds of arcs,and theoretically demonstrates the merit of the model.Furthermore,this paper employs the concept of transcendental number to establish a one-to-one mapping relationship between(d,b)-MCV and real number,based on which a novel method is proposed to remove duplicate(d,b)-MCVs.It is demonstrated from the viewpoint of time complexity that the proposed method is more practical and efficient in comparison with the existing ones.The performance of the proposed (d,b)-MCV algorithm is tes-ted by numerical experiments,and the results indicate that the algorithm is more efficient in solving(d,b)-MCVs and thus provides a new method for computing Rel_(d,b).

Optimal Scheduling of Cloud Task Based on Three-way Clustering

MA Xin-yu, JIANG Chun-mao, HUANG Chun-mei

Computer Science. 2022, 49 (11A): 211100139-7. doi:10.11896/jsjkx.211100139

Abstract

PDF(3216KB) ( 303 )

References | Related Articles | Metrics

Cloud computing is an important infrastructure supporting many high-tech developments.Furthermore,cloud task scheduling technology is directly related to the task completion time and energy consumption in the cloud computing system.In order to ensure the efficient scheduling of cloud tasks in the infrastructure and services mode,this paper proposes a three-way clustering optimal scheduling programming algorithm(TWOCP).According to the diversified characteristics of cloud task attri-butes,the overlapping and fuzzy tasks are granularly combined with three-way clustering algorithms,and the core region and boundary region tasks of each cluster are scheduled in turn.A dynamic programming algorithm is used to optimize the scheduling of granular-task to minimize the task completion time.Experimental simulation results in Cloudsimplus show that the proposed algorithm can reduce task completion time,energy consumption and effectively guarantee the availability of cloud data center.

Improved Particle Swarm Monte Carlo WSN Node Location Algorithm

WANG Ling-jiao, FANG Kai-peng, GUO Hua

Computer Science. 2022, 49 (11A): 210900156-5. doi:10.11896/jsjkx.210900156

Abstract

PDF(2653KB) ( 379 )

References | Related Articles | Metrics

Wireless sensor network(WSN) is a self-organizing network that is composed of nodes within the monitoring range and can communicate with each other.In view of the long location time and low location accuracy of the traditional particle swarm Monte Carlo algorithm,an improved particle swarm Monte Carlo positioning algorithm is proposed.(IPSOMCL).The Monte Carlo algorithm is used to obtain the estimated coordinates of the node to be located,and the particle swarm algorithm is used to correct the error between the estimated distance and the measured distance.Toimprove the filtering stage,extracting the number of hops of anchor node information to obtain a more accurate sampling area instead of the traditional algorithm to determine the sampling area through the communication radius to filter.The introduction of cross mutation enables the algorithm to jump out of the local optimal solution and find a more accurate position coordinate node,which improves the efficiency and accuracy of positioning.

Communication Satellite Task Relaxation Scheduling Method Based on Improved Hyper-heuristic Algorithm

LIU Wen-wen, XIONG Wei, HAN Chi

Computer Science. 2022, 49 (11A): 210900125-6. doi:10.11896/jsjkx.210900125

Abstract

PDF(2605KB) ( 269 )

References | Related Articles | Metrics

Under the background of increasing satellite communication support pressure,it is necessary to continuously improve the efficiency of communication satellite task scheduling.Task scheduling conflicts are mainly concentrated in communications task application time and bandwidth resource conflict,this article through the way of relaxation task application conditions,establish communication satellite relaxation model of task scheduling,with less time and bandwidth adjustment,reduce the conflicts between tasks,increase the likelihood of task for the satellite resources,improve the task can be enforced.On this basis,a super-heuristic algorithm based on artificial bee colony was proposed to solve the model.The artificial bee colony algorithm was used as the high-level selection strategy,and according to the characteristics of the satellite resource scheduling problem,seven low level heuristic operators are selected for sequence optimization,and simulated annealing is used as acceptance criterion to avoid falling into local optimum.Finally,the effectiveness of the proposed relaxation model and algorithm is verified by simulation experiment and improved algorithm comparison.

Traffic Prediction for Wireless Communication Networks with Multi-source and Cross-domain Data Fusion

MA Ji, LIN Shang-jing, LI Yue-ying, ZHUANG Bei, JIA Rui, TIAN Jin

Computer Science. 2022, 49 (11A): 210800165-7. doi:10.11896/jsjkx.210800165

Abstract

PDF(4545KB) ( 458 )

References | Related Articles | Metrics

Precise prediction of wireless communication network traffic can assist operators in fine-tuned operations to efficiently allocate and deploy base station resources,and cater to a large number of emerging business needs.However,the highly complex temporal-spatial dependence and the influence of multi-source and cross-domain factors make accurate prediction of wireless communication traffic face huge challenges.Firstly,the correlation analysis of wireless communication traffic from temporal,spatial,social and natural attributes shows that wireless communication traffic has multi-source and cross-domain characteristics.Secondly,this paper proposes an improved dense fully connected network model MST-DenseNet.The model uses the convolution operation of a single DenseUnit structure to capture the spatial correlation of traffic,and uses multiple parallel DenseUnit structures to capture the temporal correlation of traffic on different scales.At the same time,considering the impact of cross-domain dataset on wireless traffic,this model integrates the temporal and spatial characteristics of communication traffic itself with the social and natural characteristics of cross-domain dataset to achieve accurate prediction of wireless communication traffic.Experiments show that,on the actual cellular dataset,MST-DenseNet has higher prediction accuracy compared with existing model.

Summary and Analysis of Research on ManyCore Processor Technologies

SONG Li-guo, HU Cheng-xiu, WANG Liang

Computer Science. 2022, 49 (11A): 211000012-7. doi:10.11896/jsjkx.211000012

Abstract

PDF(1774KB) ( 570 )

References | Related Articles | Metrics

Processors have been developing from single-core to manycore.The latest research results abroad on manycore are comprehensively analyzed.The development status of many-core processors is first introduced,and then the related recent papers are summarized and retrieved from three aspects:architecture,on-chip storage and software.The main contributions and basic ideas of these papers are analyzed from the perspectives of energy efficiency,performance and reliability.Finally,combined with the development trend of integrated circuits in the post Moore era,two main technical direction are expounded which are the emerging adaptive architecture technology and three-dimensional integration technology of manycore processors.

Fault Diagnosis Based on Channel Splitting CLAHE and Adaptive Threshold Residual NetworkUnder Variable Operating Conditions

HUANG Xiao-ling, ZHANG De-ping

Computer Science. 2022, 49 (11A): 211100122-7. doi:10.11896/jsjkx.211100122

Abstract

PDF(2628KB) ( 268 )

References | Related Articles | Metrics

Driven by the development of big data,fault diagnosis method based on deep learning has gradually become a research hotspot in the field of fault diagnosis in recent years.However,in the real industrial field,deep learning fault diagnosis still has two limitations:1)Early fault features are weak and fault information extraction is insufficient.2)The distribution of fault data collected under variable conditions is inconsistent.The two points lead to the problems of low fault recognition rate and poor domain adaptability in deep learning fault diagnosis.In order to solve the problems above,a fault diagnosis method based on channel splitting CLAHE and adaptive threshold residual network(FEResNet) under variable operating conditions is proposed,which starts from the two perspectives of enhancing important features and deleting redundant features.Firstly,Morlet wavelet transform is employed for excavating discriminative time-frequency information hidden in vibration signals under variable operation conditions.Then,CLAHE with channel splitting is designed to improve the contrast and clarity of the time-frequency diagram to enhance fault information.Finally,the time-frequency diagram after feature enhancement is input to the designed adaptive thres-hold residual network to remove redundant features.Experimental results on CWRU dataset show that the prediction accuracy of the proposed method under the same working condition is up to 100%,the average prediction accuracy under different working conditions is up to 99.03%,and the domain adaptability is strong.

Classical Simulation Realization of HHL Algorithm Based on OpenMP Parallel Model

XIE Hao-shan, LIU Xiao-nan, ZHAO Chen-yan, HE Ming, SONG Hui-chao

Computer Science. 2022, 49 (11A): 211200028-5. doi:10.11896/jsjkx.211200028

Abstract

PDF(1946KB) ( 294 )

References | Related Articles | Metrics

Due to its natural superposition and entanglement,quantum computing has parallel computing capability that is incomparable to classical computing technologies.Based on the powerful parallel capability of quantum computing,some known quantum algorithms are faster than classical algorithms in processing problems.However,at this stage,because quantum computers is still in the development stage,the demand for algorithm experiments on quantum computers cannot be met.Therefore,quantum algorithms can be classically simulated on classical computers.HHL algorithm is used to solve the equation problem of linear system and it is widely used in data processing,numerical calculation,optimization problem and other fields.Based on the classic computer platform,HHL algorithm is simulated with C++,and the parallel programming model of OpenMP is used to accele-rate the algorithm.Realizing the HHL algorithm simulation to solve the linear equations of 4×4,8×8,16×16 matrix and realize the acceleration of the algorithm.

Acceleration Method for Multidimensional Function Optimization Based on Artificial Bee Colony Algorithm

LI Hui, HAN Lin, YU Zhe, WANG Wei

Computer Science. 2022, 49 (11A): 211200075-6. doi:10.11896/jsjkx.211200075

Abstract

PDF(3726KB) ( 237 )

References | Related Articles | Metrics

The artificial bee colony algorithm is widely used in the development of agricultural and rural big data applications,the serial artificial bee colony algorithm has a high time complexity and is not suitable for solving multi-dimensional problems quic-kly.According to the serial artificial bee colony algorithm,the problem of low execution efficiency of multi-dimensional function solving is analyzed,a multi-dimensional function optimization method based on the artificial bee colony algorithm is proposed after analyzing the multi-dimensional function and determining the artificial dependency relationship,which consists of task allocation,data distribution,synchronization operations and task parallelism.To demonstrate the efficacy of the proposed method,the Haiguang processor is used as a hardware test platform to compare and test four multi-dimensional functions.Experimental results show that the proposed method significantly outperforms the serial artificial bee colony algorithm in solving four multidimensional functions.

Scalable Parallel Computing Method for Conditional Likelihood Probability of Nucleotide Molecular Phylogenetic Tree Based on GPU

HUANG Jia-wei, LI Xiao-peng, LING Cheng

Computer Science. 2022, 49 (11A): 210800189-7. doi:10.11896/jsjkx.210800189

Abstract

PDF(4095KB) ( 280 )

References | Related Articles | Metrics

The efficient implementation of Bayesian and Metropolis Hastings algorithms makes Mrbayes a widely used tool for molecular sequence phylogenetic analysis.However,the increase of molecular sequences and evolutionary parameters leads to the rapid expansion of the sample space of candidate molecular trees,which makes the reconstruction of phylogenetic trees face great computational challenges.In order to reduce the calculation time of conditional likelihood probability of molecular tree in mrbayes phylogenetic analysis and improve the analysis efficiency,a number of parallel acceleration methods based on graphics processor(GPU) have emerged in recent years.In order to improve the scalability of parallel methods,an optimized likelihood probability multithreaded parallel computing method is proposed in this paper.As the calculation of molecular state likelihood probability in the variable evolution rate model between sites needs to correspond to different transition probability matrices,this method further decomposes the parallel calculation of likelihood probability of different sites using multithreading into the calculation of conditional likelihood probability under different transition probability matrices between multiple sites.This strategy optimizes the parallel overlap between threads and improves the parallel efficiency by increasing the number of threads without changing the calculation transmission ratio of a single thread.In addition,because each thread warp only calculates the likelihood probability under the same transition probability matrix,it avoids the synchronization overhead between different warps when using shared memory,and further improves the computing efficiency of the kernel.Calculation results of 4 groups of actual data and 30 groups of simulated data show that the computational performance of this method is 1.78 and 2.04 times higher than that of tgMC³(version 2.0) and nMC³(version 2.1.1) in the calculation acceleration of core likelihood function.

Secondary Modeling of Pollutant Concentration Prediction Based on Deep Neural Networks with Federal Learning

QIAN Dong-wei, CUI Yang-guang, WEI Tong-quan

Computer Science. 2022, 49 (11A): 211200084-5. doi:10.11896/jsjkx.211200084

Abstract

PDF(2114KB) ( 309 )

References | Related Articles | Metrics

In the new century,along with the rapid development of Chinese economy,air pollution in many areas of China is relatively serious,while the government is paying more and more attention to air pollution,and its efforts to control air pollution are increasing.Currently,six pollutants that have the greatest impact on China’s air quality are O₃,SO₂,NO₂,CO,PM₁₀,PM_2.5.Therefore,predicting and forecasting the concentrations of the six pollutants and making corresponding control adjustments in time have become the urgent needs to protect the health of residents and build a beautiful China.At present,the mainstream solution for pollutant prediction is WRF-CMAQ prediction system,which is based on two parts,physical and chemical reaction of pollutants and meteorological simulation.However,due to the current research on the generation mechanism of pollutants such as ozone is still on the way,the prediction of WRF-CMAQ model has large errors.Therefore,this paper adopts a deep neural network for secondary modeling of pollutant concentrations to reduce the prediction error.At the same time,this paper adopts the federal learning method,and uses federal learning for data training for multiple monitoring stations to improve the model generalization ability.Experiment results show that the deep neural network scheme reduces the mean square error value to at most 3.93% compared to the primary prediction results of one WRF-CMAQ.Moreover,the scheme with federal learning improves the perfor-mance by up to 68.89% compared to a single monitoring site in extensive tests.

Empirical Research on Remaining Useful Life Prediction Based on Machine Learning

WANG Jia-chang, ZHENG Dai-wei, TANG Lei, ZHENG Dan-chen, LIU Meng-juan

Computer Science. 2022, 49 (11A): 211100285-9. doi:10.11896/jsjkx.211100285

Abstract

PDF(3894KB) ( 482 )

References | Related Articles | Metrics

Remaining useful life(RUL) prediction is one essential task of the predictive maintenance system.This paper investigates the latest RUL prediction methods,focusing on direct RUL prediction based on machine learning.Firstly,we describe the four representative machine learning models adopted by the RUL prediction methods,including support vector regression(SVR),multilayer perceptron(MLP),convolutional neural network(CNN),and recurrent neural network(RNN).And then,we give the three primary benchmark datasets and two performance evaluation metrics widely used in RUL prediction.The contribution of this paper is to demonstrate the steps and key technical details of how to build the RUL prediction models over the benchmark dataset(C-MAPSS) provided by NASA.We also compare the performance of these representative prediction models in detail and visually analyze the experimental results.Experimental results show that the performance of SVR with a shallow structure is significantly weaker than those based on deep neural networks.CNN and RNN based models have a solid ability for mining complex feature interaction and temporal feature interaction.Finally,we provide an outlook on the future of predictive maintenance technology and discuss the main challenges.

Testing System of Target Recognition Method of Array Screen

PAN Deng, CAI Meng-yun, WANG Zhen-yu, LV Jia-liang

Computer Science. 2022, 49 (11A): 211000109-4. doi:10.11896/jsjkx.211000109

Abstract

PDF(2152KB) ( 304 )

References | Related Articles | Metrics

In order to solve the problem that the existing array screen test system cannot judge and recognize multiple continuous target signals and the unit detection screen is susceptible to external interference,the principle of using the method of similarity coefficient is proposed.To distinguish the real target signal and interference signal of each unit detection screen output,based on the D-S evidence theory,a method to identify the real target signals and eliminate the false targets in the test system of multi photoelectric detection sensors is established.The characteristics of the output target signal which pass through the array screen test system are studied,and the distribution of the reliability function of the output signal target type under the evidence body of four unit detection screens in the array screen test system is given,and then the target recognition result is obtained through fusion processing.So this paper can achieve the goal of eliminating the false targets and signal recognition.

Study on Decision-making for Low-carbon Supply Chain with Capital Constraint and Risk Aversion

LI Li-ying, LIU Guang-an, LI Xiao-bing, WANG Bo

Computer Science. 2022, 49 (11A): 210900104-6. doi:10.11896/jsjkx.210900104

Abstract

PDF(1784KB) ( 282 )

References | Related Articles | Metrics

In order to alleviate the financing difficulties of capital-constrained manufacturers in low-carbon environment,a Stac-kelberg game model is established in government’s cap-and-trade system,which is led by a risk-neutral supplier and followed by a loss-averse manufacturer.Based on the assumption that the manufacturer borrows two loans to execute the ordering decision and make emission reduction investment,the optimal ordering and emission reduction decisions of the risk-neutral and loss-averse manufacturer and the optimal wholesale pricing decision of the supplier are obtained,respectively.Theoretical and numerical ana-lysis show that when the manufacturer is loss-averse,it will make more conservative order decisions,and the supplier will set a higher wholesale price.As a result,the manufacturer reduces the emission reduction level.The impact of loss aversion on the expected utility of the manufacturer is related to carbon cap allocated by the government.When carbon cap is large,the manufactu-rer with higher loss aversion can earn additional gains by selling more remaining emission permits in the carbon permit trading markets.

Fault Diagnosis of Shipboard Zonal Distribution Power System Based on FWA-PSO-MSVM

GAO Ji-hang, ZHANG Yan

Computer Science. 2022, 49 (11A): 210800209-5. doi:10.11896/jsjkx.210800209

Abstract

PDF(4369KB) ( 340 )

References | Related Articles | Metrics

The occurrence of faults will greatly affect the safety of the shipboard zonal distribution power system.In order to ensure the safe operation of ships,10 types of short-circuit faults in the shipboard zonal distribution power system are focused in this paper.MATLAB/Simulink is used to establish the power system simulation model of the shipboard zonal distribution power system,SMOTE oversampling is adopted to preprocess the fault data.Taking the feature vector extracted by principal component analysis(PCA) in fault data as input of multi-class support vector machine(MSVM) for fault diagnosis.In order to optimize the diagnosis results,a firework particle swarm optimization algorithm is presented to optimize the penalty factor C and the kernel function parameter γ of MSVM,which is compared with the results of MSVM fault classification optimized only by the particle swarm optimization algorithm.Simulation results show that the proposed algorithm has higher fault classification accuracy and precision.

New SLAM Method of Multi-layer Lidar Assisted by Rotational Strapdown Inertial NavigationSystem

LYU Run, LI Guan-yu, QI Pei, QIAN Wei-xing, WANG Lan-ze, FENG Tai-ping

Computer Science. 2022, 49 (11A): 211200088-5. doi:10.11896/jsjkx.211200088

Abstract

PDF(2783KB) ( 336 )

References | Related Articles | Metrics

Focusing on the influence of low-accuracy inertial sensor on the performance of lidar/inertial SLAM,an optimized SLAM method by fusing information of multi-layer lidar and rotational strapdown inertial navigation system is studied.In this scheme,the rotating strapdown inertial navigation alignment method based on fuzzy adaptive Kalman filter is discussed,and the real-time correction of carrier attitude and inertial sensor error is completed in the process of carrier motion.Further more,the corrected inertial sensor data and LIDAR point cloud data are fused in tight coupling mode to improve the accuracy and real-time of positioning and mapping when the carrier moves in complex scenes.Experimental results show that the slam scheme based on rotating inertial navigation and multi-layer lidar information fusion not only ensures the real-time operation,but also effectively improves the positioning performance of lidar / inertial odometry and the accuracy of point cloud map.