基于机器学习的军用软件过时淘汰评估方法研究
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Military Software Obsolescence Evaluation Based on Machine Learning
  • 作者:帅勇 ; 宋太亮 ; 郑玉杰 ; 郑雪松 ; 唐浩
  • 英文作者:Shuai Yong;Song Tailiang;Zheng Yujie;Zeng Xuesong;Tang Hao;Chongqing Ceprei Industrial Technology Research Institute;Chongqing Engineering Research Center of Electronic Information Products Reliability;China Defense Science & Technology Information Center;
  • 关键词:军用软件过时淘汰 ; 机器学习 ; 主成分分析 ; 支持向量机 ; 评估
  • 英文关键词:military software obsolescence;;machine learning;;principe component analysis;;support vector machine;;evaluation
  • 中文刊名:JZCK
  • 英文刊名:Computer Measurement & Control
  • 机构:重庆赛宝工业技术研究院;重庆市电子信息产品可靠性工程技术研究中心;中国国防科技信息中心;
  • 出版日期:2019-05-25
  • 出版单位:计算机测量与控制
  • 年:2019
  • 期:v.27;No.248
  • 基金:武器装备预先研究基金(9140A19030314JB35275);; 省部级科研项目(2016YYF0203604,MGY1704040,MGY1804040);; 重庆市技术创新与应用示范重点研发项目(cstc2018jszxcyzd0634)
  • 语种:中文;
  • 页:JZCK201905030
  • 页数:5
  • CN:05
  • ISSN:11-4762/TP
  • 分类号:137-141
摘要
为了对军用软件进行科学系统的过时淘汰评估,提出基于机器学习的软件过时淘汰评估模型;首先使用机器学习预处理与缩放技术处理相关的特征数据,然后基于主成分分析模型进行特征提取和降维,消除特征数据中的噪音值并选择重要的军用软件过时淘汰特征数据,使用由粒子群优化算法改进的支持向量机模型进行分类和评估建模,并使用混淆矩阵的精度评估模型,最后通过案例验证模型有效性、适用性和科学性。
        To evaluate military software obsolescence scientifically and systematically,the model of software obsolescence evaluation based on machine learning is pointed.Firstly,the machine learning preprocessing and scaling techniques are used to process the related feature data,then the principal component analysis model is used to extract feature and reduce dimension,eliminate the noise value in the feature data and select important military software obsolete feature data,use particle swarm optimization algorithm to optimize support vector machine parameters and build SVM classification and evaluation model,use confusion matrix accuracy to evaluate the machine model,finally the test results showed the model is effective,applicable,and scientific.
引文
[1]帅勇,宋太亮.基于模糊贝叶斯网络的软件过时淘汰影响研究[J].计算机测量与控制,2014,35(12):4207-4212.
    [2]Rajagopala S,Erkoyuncu J A,Roy R.Software obsolescence in defence[A].3rd CIRP Global Web Conference[C].2014,22(10):76-80.
    [3]Kouroush Jenab,Kourosh Noori,Philip D.Weinsier,Sam Khoury.Reliability Paper:A dynamic model for hardware/software obsolescence[J].International Journal of Quality&Reliability Management,2014,31(5):1-13.
    [4]Erich Schmid,George Kosugi,Jorge Ibsen,Morgan Griffith.Don’t get taken by surprise:planning for software obsolescence management at the ALMA Observatory[J].Proceedings of the SPIE,2016,9913(46):1-11.
    [5]Bjoern Bartels,Ulrich Ermel,Michael Pecht,Peter Sandborn.Strategies to the Prediction,Mitigation and Management of Product Obsolescence[M].John Wiley&Sons Inc,2012:143-155.
    [6]Rajagopal S,Erkoyuncu J A,Roy R.Impact of software obsolescence in defence manufacturing sectors[J].3rd CIRP Global Web Conference,2015,28:197-201.
    [7]Darling,Green.Decision software as applied to obsolescence[A].AIAA’s 3rd Annual Aviation Technology,Integration,and Operations(ATIO)[C].2003,11:1-10.
    [8]Raul Gonzzlez Munuz,Essam Shehab,Martin Weinitzke,Chris Fowler,Paul Baguley.Software Obsolescence Drivers in Aerospace:An Industry Analysis[J].World Academy of Science,Engineering and Technology International Journal of Computer,Electrical,Automation,Control and Information Engineering,2017,11(9):961-966.
    [9]Cathleen R.Kennedy.Software replacement of test module adapters for depot instrumentation due to obsolescence[J].Aerospace and Electronic Systems Magazine,2004,19(7):25-30.
    [10]Leigh Merola.The COTS Software Obsolescence Threat[J].Proceedings of the Fifth International Conference on Commercial-off-the-Shelf(COTS)-Based Software Systems(IC-CBSS 2006),2006,6:127-132.
    [11]Brian J.Giovannoni,Carole Boyles.Hidden Costs of Unsupported Software,Obsolescence and Non-Standards;The Importance and Value of a Multi-Mission Software Program[A].SpaceOps Conferences[C].2016,5:1-8.
    [12]John Ahmet Erkoyuncu,Stanley Ononiwu,Rajkumar Roy.Mitigating the Risk of Software Obsolescence in the Oil and Gas Sector[A].3rd International Conference on Throughlife Engineering Services[C].2014,22:81-86.
    [13]Raúl González Mu1oza,Essam Shehaba,Martin Weinitzkeb,Rachel Bencec,Chris Fowlerc,Stephen Tothillc,Paul Baguleya.Key Challenges in Software Application Complexity and Obsolescence Management within Aerospace Industry[Z].CIRPe 2015Understanding the life cycle implications of manufacturing,2015,37:24-29.
    [14]Dov Dori;Somwang Thipphayathetthana.Model-based guidelines for user‐centric satellite control software development[J].International Journal of Satellite Communications and Networking,2015,34(7):295-319.
    [15]Andreas C.Muller,Sarah Guido.Introduction to Machine Learning with Python[M].O’Reilly Media,2016,5.
    [16]帅勇,宋太亮,王建平.考虑全过程优化的支持向量机预测方法[J].系统工程与电子技术,2017,39(4):931-940.
    [17]Shuai Yong,Song Tailiang,Wang Jianping,Zhan Wenbin.Hybrid Reliability Parameter Selection Method Based on Text Mining,Frequent Pattern Growth algorithm and Fuzzy Bayesian Network[J].Journal of Shanghai Jiao Tong University(Science),2018,23(3):423-428.
    [18]Guzzetti F,Peruccacci S,Rossi M,et al.The Rainfall Intensity-duration Control of Shallow Landslides and Debris Flows:an Update[J].Landslides,2008,5(1):3-17.
    [19]Shuai Yong,Song Tailiang,Wang Jianping.An integrated parallel forecasting model based on fuzzy time series and SVM[J].Journal of Systems Engineering and Electronics,2017,28(7):766-775.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700