融合多视图注意力机制的城市交通流量补全

doi:10.11896/jsjkx.200800077

摘要/Abstract

摘要： 交通流量信息是智能交通系统和城市计算的重要基础。交通流量数据作为新型时序数据,由于数据的采集方式和外部复杂因素的影响,使得数据缺失现象是常见且无法避免的。如何有效地挖掘交通流量数据的时空特性和数据间的关联成为了提高缺失数据补全精度的关键。传统的统计学方法不能满足日益增长的数据需求,深度学习的应用推动了缺失数据的补全方法向更高的精确度发展。文中深入分析了交通流量的时间特性和空间分布,对交通流量的缺失情况进行了假设,提出了一种UMAtNet(U-net with Multi-View Attention Mechanisms)交通流量补全模型。该模型将短期的、趋势的、周期的时间数据与空间数据融合,同时采用不同的数据相关性测量方法,融合了一种多视图注意力机制,能够优化模型对缺失部分数据空间相关性的影响。为了验证模型的有效性,文中使用北京交通轨迹开源数据集进行实验,并在实验中详细地分析了模型各部分和损失函数对补全精度的影响,实验结果表明,UMAtNet和相应组件融合能进一步提高补全精度。

关键词: U-Net, 多视图, 交通流量补全, 时空特征, 注意力机制

Abstract: Traffic flow information is an important basis for intelligent transportation systems and urban computing.Traffic flow data is a new type of time series data.Due to the data collection method and the influence of external complex factors,the phenomenon of data loss is common and unavoidable.How to effectively mine the spatial-temporal characteristics of traffic flow data and the correlation between the data becomes the key to improve the missing data completion accuracy.Traditional statistical methods cannot meet the increasingly complex data requirements,and the application of deep learning promotes the development of missing data completion methods to higher accuracy.The article deeply analyzes the spatial-temporal characteristics of traffic flow,makes assumptions about the missing traffic flow,and proposes a UMAtNet (U-net with Multi-view Attention Mechanisms) traffic flow complement model.The model fuses closeness,trend and period time data with spatial data,and adopts diffe-rent data correlation measurement methods to fuse a multi-view attention mechanism,which can optimize the impact of the model on the spatial correlation of missing data.In order to verify the model,we use the open source data set of Beijing traffic data in the experiment,and analyzes in detail the influence of each part of the model and the loss function on the completion accuracy.The experimental results show that the fusion of UMAtNet and corresponding components can further improve the completion accuracy.

Key words: Attention mechanism, Completion of traffic flow, Multi-view, Spatial-temporal characteristics, U-Net

中图分类号:

TP311

康雁, 陈铁, 李浩, 杨兵, 张亚钏, 卜荣景. 融合多视图注意力机制的城市交通流量补全[J]. 计算机科学, 2021, 48(10): 177-184. https://doi.org/10.11896/jsjkx.200800077

KANG Yan, CHEN Tie, LI Hao, YANG Bing, ZHANG Ya-chuan, BU Rong-jing. Urban Traffic Flow Completion with Multi-view Attention Mechanism[J]. Computer Science, 2021, 48(10): 177-184. https://doi.org/10.11896/jsjkx.200800077

参考文献

[1]LU Y,HU J,XU J,et al.Urban Traffic Flow Forecasting Based on Adaptive Hinging Hyperplanes[C]//International Confe-rence on Artificial Intelligence and Computational Intelligence.Berlin,Heidelberg:Springer,2009:658-667.
[2]LV Y,DUAN Y,KANG W,et al.Traffic Flow Prediction With Big Data:A Deep Learning Approach[J].IEEE Transactions on Intelligent Transportation Systems,2015,16(2):865-873.
[3]SMITH B,SCHERER W,CCONKLIN J.Exploring ImputationTechniques for Missing Data in Transportation Management Systems[J].Transportation Research Record Journal of the Transportation Research Board,2003,1836:132-142.
[4]HAN W G,WANG J F,HU J J.Interpolation Method of Mis-sing Value in Traffic Flow Data[J].Journal of Transport information and safety,2005,23(1):39-42.
[5]BOX G E P,JENKINS G M,REINSELG C,et al.Time Series Analysis:Forecasting and Control,5th Edition[J].Journal of the Operational Research Society,2015,22(2):199-201.
[6]MING Z,SATISH S,PAWAN L.Matching Patterns for Updating Missing Values of Traffic Counts[J].Transportation Planning and Technology,2006,29:141-156.
[7]ZHONG M,LINGRAS P,SHARMA S.Estimation of missing traffic counts using factor,genetic,neural,and regression techniques[J].Transportation Research Part C Emerging Technologies,2004,12(2):139-166.
[8]TAN H,FENG G,FENG J,et al.A Tensor Based Method for Missing Traffic Data Completion[J].Transportation Research Part Cemerging Technologies,2013,12(2):139-166.
[9]RAN B,TAN H,WU Y,et al.Tensor based missing traffic data completion with spatial-temporal correlation[J].Statistical Mechanics and its Applications,2016,446:54-63.
[10]TIAN Y,ZHANG K,LI J,et al.LSTM-based traffic flow prediction with missing data[J].Neurocomputing,2018,318(27):297-305.
[11]KU W C,JAGADEESH G R,PRAKASH A,et al.A Clustering-Based Approach for Data-Driven Imputation of Missing Traffic Data[C]//IEEE Forum on Integrated and Sustainable Transportation Systems.IEEE,2016.
[12]YU F,WEI D,ZHANG S,et al.3D CNN-based Accurate Prediction for Large-scale Traffic Flow[C]//2019 4th International Conference on Intelligent Transportation Engineering (ICITE).2019:99-103.
[13]LI Z,ZHENG H,FENG X.3D Convolutional Generative Adversarial Networks for Missing Traffic Data Completion[C]//2018 10th International Conference on Wireless Communications and Signal Processing (WCSP).2018.
[14]WANG L,LI M,YAN J Q,et al,Urban Traffic Flow Data Recovery Method Based on Generative Adversarial Network[J].Journal of Transportation Systems Engineering and Information Technology.2018,18(6):63-71.
[15]YUAN Y Y,KANG Y,LI H,et al.Timing traffic flow datacompletion based on ST-DCGAN[J].Computer Engineering and Applications,2020,56(15):140-146.
[16]HONG Y L,BIN J,YI X,et al.Coherent Semantic Attention for Image Inpainting [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision.2019:4170-4179.
[17]GUILIN L,FITSUM A,KEVIN J,et al.Image Inpainting forIrregular Holes Using Partial Convolutions[C]//European Con-ference on Computer Vision.2018(11):89-105.
[18]WEN X,LI T,HAN Z,et al.Point Cloud Completion by Skip-attention Network with Hierarchical Folding[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE,2020.
[19]OLAF R,PHILIPP F,THOMAS B.U-Net:Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing and Computer-assisted Intervention.Springer,Cham,2015:234-241.
[20]ZHANG J,ZHENG Y,QI D,et al.Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks[J].Artificial Intelligence,2018,259:147-166.
[21]WANG L,GENG X,MA X,et al.Crowd Flow Prediction byDeep Spatio-Temporal Transfer Learning[J].arXiv:1802.00386,2018.
[22]VU D L,VU N T.Vietnamese speech recognition using Dyna-mic Time Warping and Coefficient of Correlation[C]//International Conference on Control,Automation and Information Sciences (ICCAIS).2013:64-67.
[23]TANG R,KANAMORI R,YAMAMOTO T.Short-Term Ur-ban Link Travel Time Prediction using Dynamic Time Warping with Disaggregate Probe Data[J].IEEE Access,2019,99:1.
[24]ASHISH V,NOAM S,NIKI P,et al.Attention is All you Need[C]//Conference and Workshop on Neural Information Proces-sing Systems.2017:5998-6008.
[25]AHMED K,KESKAR N S,SOCHER R.Weighted transformer network for machine translation[J].arXiv:1711.02132,2017.
[26]ZHU G,ZHANG L,SHEN P,et al.Continuous Gesture Segmentation and Recognition Using 3DCNN and Convolutional LSTM[J].IEEE Transactions on Multimedia,2018,21:1011-1021.
[27]LEA C,FLYNN M D,VIDAL R,et al.Temporal convolutional networks for action segmentation and detection[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:156-165.
[28]XIONG T,QI Y,ZHANG W B.Short-term Traffic Flow Prediction Based on DCGRU-RF Model for Road Network[J].Computer Science,2020,47(5):84-89.
[29]RONG B,WU Z H,LIU X H,et al.Flow Prediction of Traffic Stations Based on Spatio-Temporal Multi-Graph Convolutional Network[J].Computer Engineering,2020,46(5):26-33.
[30]KONG F Y,ZHOU Y F,CHEN G.Traffic Flow PredictionMethod Based on Spatio-Temporal Feature Mining[J].Compu-ter Science,2019,46(7):322-326.

相关文章 15

[1]	周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2]	戴禹, 许林峰. 基于文本行匹配的跨图文本阅读方法 Cross-image Text Reading Method Based on Text Line Matching 计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
[3]	周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[4]	熊丽琴, 曹雷, 赖俊, 陈希亮. 基于值分解的多智能体深度强化学习综述 Overview of Multi-agent Deep Reinforcement Learning Based on Value Factorization 计算机科学, 2022, 49(9): 172-182. https://doi.org/10.11896/jsjkx.210800112
[5]	饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[6]	朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[7]	孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[8]	闫佳丹, 贾彩燕. 基于双图神经网络信息融合的文本分类方法 Text Classification Method Based on Information Fusion of Dual-graph Neural Network 计算机科学, 2022, 49(8): 230-236. https://doi.org/10.11896/jsjkx.210600042
[9]	姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[10]	汪鸣, 彭舰, 黄飞虎. 基于多时间尺度时空图网络的交通流量预测模型 Multi-time Scale Spatial-Temporal Graph Neural Network for Traffic Flow Prediction 计算机科学, 2022, 49(8): 40-48. https://doi.org/10.11896/jsjkx.220100188
[11]	金方焱, 王秀利. 融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取 Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM 计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[12]	熊罗庚, 郑尚, 邹海涛, 于化龙, 高尚. 融合双向门控循环单元和注意力机制的软件自承认技术债识别方法 Software Self-admitted Technical Debt Identification with Bidirectional Gate Recurrent Unit and Attention Mechanism 计算机科学, 2022, 49(7): 212-219. https://doi.org/10.11896/jsjkx.210500075
[13]	彭双, 伍江江, 陈浩, 杜春, 李军. 基于注意力神经网络的对地观测卫星星上自主任务规划方法 Satellite Onboard Observation Task Planning Based on Attention Neural Network 计算机科学, 2022, 49(7): 242-247. https://doi.org/10.11896/jsjkx.210500093
[14]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[15]	曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed