计算机科学 ›› 2021, Vol. 48 ›› Issue (5): 86-90.doi: 10.11896/jsjkx.210200055

• 计算机软件* 上一篇    下一篇

基于连续型深度置信神经网络的软件可靠性预测

亓慧1, 史颖1,2, 李灯熬3, 穆晓芳1, 侯明星1   

  1. 1 太原师范学院计算机系 山西 晋中030619
    2 山西大学计算机与信息技术学院 太原030006
    3 太原理工大学大数据学院 山西 晋中030600
  • 收稿日期:2021-02-05 修回日期:2021-04-03 出版日期:2021-05-15 发布日期:2021-05-09
  • 通讯作者: 亓慧(qihui@tynu.edu.cn)
  • 基金资助:
    国家重大科研仪器研制项目(6202780085);国家自然科学基金(62076177);山西省关键核心技术和共性技术研发专项(2020xxx007);山西省科技厅重点研发项目(201803D31055)

Software Reliability Prediction Based on Continuous Deep Confidence Neural Network

QI Hui1, SHI Ying1,2, LI Deng-ao3, MU Xiao-fang1, HOU Ming-xing1   

  1. 1 Department of Computer,Taiyuan Normal University,Jinzhong,Shanxi 030619,China
    2 School of Computer and Information Technology,Shanxi University,Taiyuan 030006,China
    3 College of Data Science,Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
  • Received:2021-02-05 Revised:2021-04-03 Online:2021-05-15 Published:2021-05-09
  • About author:QI Hui,born in 1981,master,associate professor,graduate supervisor.Her main research interests include machine learning and computational intelligence.
  • Supported by:
    National Major Scientific Research Instrument Development Project(6202780085),National Natural Science Foundation of China(62076177),Shanxi Province Key Core Technology and Common Technology R&D Project(2020xxx007) and Key Research and Development Project of Shanxi Province(201803D31055).

摘要: 为了提高软件可靠性智能预测的精度,采用连续型深度置信神经网络算法用于软件可靠性预测。首先提取影响软件可靠性的核心要素样本,并获取样本要素的关键特征;然后建立连续型深度置信神经网络(Deep Belief Network,DBN)的软件可靠性预测模型,输入待预测样本,通过多个受限波尔兹曼机(Restricted Boltzmann Machine,RBM)层的预处理训练,以及多次反向微调迭代获取DBN权重等参数,直到达到最大RBM层数和最大反向微调迭代次数;最后获得稳定的软件可靠性预测模型。实验结果证明,通过合理设置DBN隐藏层节点数和学习速率,可以获得良好的软件可靠性预测准确率和标准差。与常用的软件可靠性预测算法相比,所提算法的预测准确度高且标准差小,在软件可靠性预测方面的适用度较高。

关键词: 软件可靠性, 软件失效, 深度置信神经网络, 学习速率

Abstract: In order to improve the accuracy of intelligent prediction of software reliability,continuous depth confidence neural network algorithm is used for software reliability prediction.Firstly,the core elements samples that affect software reliability are extracted,and the key features of the sample elements are obtained.Then,a software reliability prediction model based on conti-nuous deep belief neural network (DBN) is established.The samples to be predicted are input,and the parameters such as DBN weight are obtained through pre-processing training of multiple Restricted Boltzmann Machine (RBM) layers and multiple reverse fine-tuning iterations until the maximum number of RBM layers and the maximum number of reverse fine-tuning iterations are reached.Finally,a stable software reliability prediction model is obtained.Experiments show that good software reliability prediction accuracy and standard deviation can be obtained by reasonably setting the number of nodes in the hidden layer of DBN and the learning rate.Compared with commonly used software reliability prediction algorithms,this algorithm has high prediction accuracy,small standard deviation and high applicability in software reliability prediction.

Key words: Deep confidence neural network, Learning rate, Software failure, Software reliability

中图分类号: 

  • TP311.5
[1]ZHANG D P,LIU G Q,ZHANG K.Software defect prediction model based on GMDH causality [J].Computer Science,2016(7):171-176.
[2]XU L.Software Reliability Model Considering Incomplete Error Removal and Degradation of Detection Rate[J].Journal of Chongqing University of Technology(Natural Science),2019,33(8):132-137.
[3]JAIN R,SHARMA A.Assessing software reliability using genetic algorithms[J].Journal of Engineering Research,2019,16(1):11-17.
[4]JABEEN G,LUO P,AFZAL W.An improved software reliability prediction model by using high precision error iterative analysis method[J].Software Testing,Verification and Reliability,2019(29):67-75.
[5]GONG L,JIANG S,BO L,et al.A Novel Class-ImbalanceLearning Approach for Both Within-Project and Cross-Project Defect Prediction[J].IEEE Transactions on Reliability,2020,69(1):40-54.
[6]COTRONEO D,PIETRANTUONO R,RUSSO S.RELAI Testing:A Technique to Assess and Improve Software Reliability[J].IEEE Transactions on Software Engineering,2016,42(5):452-475.
[7]TAMURA Y,YAMADA S.Software Reliability Model Selec-tion Based on Deep Learning with Application to the Optimal Release Problem[J].Journal of Industrial Engineering and Management Science,2016,2016(1):43-58.
[8]LIU J,WU N Q,QIAO Y,et al.Short-Term Traffic Flow Forecasting Using Ensemble Approach Based on Deep Belief Networks[J].IEEE Transactions on Intelligent Transportation Systems,2020(99):1-14.
[9]QIAO J,PAN G,HAN H.A regularization-reinforced DBN for digital recognition[J].Natural Computing,2019,18(4):721-733.
[10]YU L,ZHOU R,TANG L,et al.A DBN-based resampling SVMensemble learning paradigm for credit classification with imbalanced data[J].Applied Soft Computing,2018(69):192-202.
[11]ABDEL-ZAHER A M,ELDEIB A M.Breast cancer classification using deep belief networks[J].Expert Systems with Applications,2016(46):139-144.
[12]WEN C L,LU F Y.Review on Deep Learning Based Fault Diagnosis [J].Journal of Electronics & Information Technology,2020,42(1):234-248.
[13]ZHENG J,FU X,ZHANG G.Research on exchange rate forecasting based on deep belief network[J].Neural Computing & Applications,2019,31(1):573-582.
[14]LIANG H,LIU Y,SHENG G,et al.Fault-cause identification method based on adaptive deep belief network and time-frequency characteristics of travelling wave[J].Generation,Transmission & Distribution,IET,2019,13(5):724-732.
[15]LIANG H T,XU J L.Software Reliability Prediction ModelBased on Hybrid Kernels RVM[J].Computer Science,2016,43(11):257-259.
[16]RAY S,BHATTACHARYYA B,PAL S.Statistical Modeling and Forecasting of Food Grain in Effects on Public Distribution System:An application of ARIMA Model[J].Indian Journal of Economics and Development,2020,12(4):739.
[17]PRATIK,ROY,GHANSHAYM,et al.Forecasting of Software Reliability Using Neighborhood Fuzzy Particle Swarm Optimization Based Novel Neural Network[J].IEEE/CAA Journal of Automatica Sinica,2019,6(6):78-96.
[18]CHEN L Q,LIU W,HE X.Reliability prediction of CPS software based on LSTM neural network [J].Computer Engineering and Design,2019,40(5):1343-1348.
[1] 陈媛, 惠燕, 胡秀华.
一种自适应尺度与学习速率调整的背景感知相关滤波跟踪算法
Background-aware Correlation Filter Tracking Algorithm with Adaptive Scaling and Learning Rate Adjustment
计算机科学, 2021, 48(5): 177-183. https://doi.org/10.11896/jsjkx.200300109
[2] 王慧妍, 徐经纬, 许畅.
环境感知自适应软件的运行时输入验证技术综述
Survey on Runtime Input Validation for Context-aware Adaptive Software
计算机科学, 2020, 47(6): 1-7. https://doi.org/10.11896/jsjkx.200400081
[3] 弋泽龙,温玉梅,林燕敏,陈伟庭,吕冠宇.
多层缺陷关联效应对软件可靠性增长过程的影响
Impacts of Correlation Effects among Multi-layer Faults on Software Reliability Growth Processes
计算机科学, 2018, 45(2): 241-248. https://doi.org/10.11896/j.issn.1002-137X.2018.02.042
[4] 刘凯, 梁欣, 张俊萍.
基于软硬系统综合方法的软件失效问题分析
Analysis on Technical Support Equipments’ Software Invalidation Based on Soft and Hard Integrated System Methodology
计算机科学, 2018, 45(11A): 494-496.
[5] 张晓风,张德平.
基于拟似然估计方法的软件失效预测模型
Software Failure Prediction Model Based on Quasi-likelihood Method
计算机科学, 2016, 43(Z11): 486-489. https://doi.org/10.11896/j.issn.1002-137X.2016.11A.109
[6] 张婷婷,张德平,刘国强.
基于EM方法的隐Markov软件可靠性模型
Hidden Markov Software Reliability Model with EM Method
计算机科学, 2016, 43(8): 159-164. https://doi.org/10.11896/j.issn.1002-137X.2016.08.033
[7] 王宗会,周勇,张德平.
基于改进的非参数方法的软件失效预测模型
Software Failure Prediction Model Based on Improved Nonparametric Method
计算机科学, 2016, 43(6): 156-159. https://doi.org/10.11896/j.issn.1002-137X.2016.06.032
[8] 王珣,王轶辰.
软件系统故障传播模型研究进展
Research Progress on Error Propagation Model in Software System
计算机科学, 2016, 43(6): 1-9. https://doi.org/10.11896/j.issn.1002-137X.2016.06.001
[9] 梁宏涛,徐建良,许可.
组合核相关向量机的软件可靠性预测模型
Software Reliability Prediction Model Based on Hybrid Kernels RVM
计算机科学, 2016, 43(11): 257-259. https://doi.org/10.11896/j.issn.1002-137X.2016.11.050
[10] 王二威,吴祈宗.
基于泛函网络的软件可靠性多模型综合预测方法
Multi-model Synthesis Prediction of Software Reliability Based on Functional Networks
计算机科学, 2015, 42(10): 175-179.
[11] 费琪,刘春裕.
基于NHPP类软件可靠性通用模型研究与应用
General NHPP Software Reliability Research and Application
计算机科学, 2014, 41(Z11): 379-381.
[12] 张柯,张德平,汪帅.
软件可靠性混沌神经网络模型
Chaotic Neural Network Model for Software Reliability
计算机科学, 2014, 41(4): 172-177.
[13] 张德平,汪帅,周吴杰.
基于EMD和GEP的软件可靠性预测模型
Software Reliability Forecasting Model Based on Empirical Mode Decomposition and Gene Expression Programming
计算机科学, 2013, 40(4): 164-168.
[14] 黄抚群,刘 斌,王轶辰.
软件心理学研究综述
Review of Software Psychology
计算机科学, 2013, 40(3): 1-7.
[15] 刘逻,郭立红,肖辉,王建军,王改革.
基于参数动态调整的动态模糊神经网络的软件可靠性增长模型
Software Reliability Growth Model Based on Dynamic Fuzzy Neural Network with Parameters Dynamic Adjustment
计算机科学, 2013, 40(2): 186-190.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!