基于集成学习的复杂仿真模型验证方法
|
摘要
针对复杂仿真模型验证中海量数据的相似性分析问题,提出了一种基于集成学习的仿真模型验证方法。将仿真时间序列与参考时间序列的相似性分析问题转换为相似性等级分类问题,进而利用神经网络、支持向量机、集成学习等机器学习方法,设计了一种集成分类系统对时间序列的相似性等级进行分类。为了增强基分类器的多样性,提出了基于惩罚因子的多样性筛选准则;通过挑选具有最大差异性的基分类器,构造高性能集成分类系统。最后利用相关数据,对所提出的方法进行应用研究,验证了方法的有效性。
To resolve the similarity analysis of massive datasets,a complex simulation model validation method based on ensemble learning is proposed.The similarity analysis between simulated time series and observed time series is formulated as a similarity degree classification problem.Machine learning techniques,including back propagation neural network,error correcting output coding support vector machine(ECOC SVM)and ensemble learning,are utilized to construct an ensemble classification system(ECS).Improve the diversity among base classifiers is essential for building high performance ECS.A screening criterion based on the punish factor is designed to choose base classifiers with maximum diversity.Finally,the proposed model validation method is examined with an application example.
To resolve the similarity analysis of massive datasets,a complex simulation model validation method based on ensemble learning is proposed.The similarity analysis between simulated time series and observed time series is formulated as a similarity degree classification problem.Machine learning techniques,including back propagation neural network,error correcting output coding support vector machine(ECOC SVM)and ensemble learning,are utilized to construct an ensemble classification system(ECS).Improve the diversity among base classifiers is essential for building high performance ECS.A screening criterion based on the punish factor is designed to choose base classifiers with maximum diversity.Finally,the proposed model validation method is examined with an application example.
引文
[1]SARGENT R G.Verification and validation of simulation models[J].Journal of Simulation,2013,7(1):12-24.
[2]SARIN H,KOKKOLARAS M,HULBERT G,et al.Comparing time histories for validation of simulation models:error measures and metrics[J].Journal of Dynamic Systems,Measurement,and Control,2010,132(6):768-778.
[3]CROCHEMORE L,PERRIN C,ANDREASSIAN V,et al.Comparing expert judgement and numerical criteria for hydrograph evaluation[J].Hydrological Sciences Journal,2015,60(3):402-423.
[4]HAUDUC H,NEUMANN M B,MUSCHALLA D,et al.Efficiency criteria for environmental model quality assessment:areview and its application to wastewater treatment[J].Environmental Modelling&Software,2015,68(C):196-204.
[5]SAGREBIN M,GOERKE N.Learning time-series similarity with a neural network by combining similarity measures[C]∥Proc.of the 16th International Conference on Artificial Neural Networks,2006:123-132.
[6]TEFERRA K,SHIELDS M D,HAPIJ A,et al.Mapping model validation metrics to subject matter expert scores for model adequacy assessment[J].Reliability Engineering&System Safety,2014,132(132):9-19.
[7]MCKENNY J L.Critique of verification of computer simulation models[J].Management Science,1967,14(2):102-103.
[8]方可,马萍,杨明.用于虚拟样机系统可信度评估的多属性决策网方法[J].计算机集成制造系统,2012,18(5):1054-1060.FANG K,MA P,YANG M.MAD network for virtual protocol systems credibility evaluation[J].Computer Integrated Manufacturing Systems,2012,18(5):1054-1060.
[9]MURPHY K P.Machine learning:aprobabilistic perspective[M].Cambridge:The MIT Press,2012.
[10]雷蕾,王晓丹,罗玺,等.ECOC多类分类研究综述[J].电子学报,2014,42(9):1794-1800.LEI L,WANG X D,LUO X,et al.An overview of multi-classification based on error correcting output codes[J].Acta Electronica Sinica,2014,42(9):1794-1800.
[11]NIELSON R H.Theory of the back-propagation neural network[C]∥Proc.of the International Joint Conference on Neural Networks,1989:583-604.
[12]甘俊英,张有为.基于BP神经网络的人脸识别[J].系统工程与电子技术,2003,25(1):113-115.GAN J Y,ZHANG Y W.Face recognition based on BP neural network[J].Systems Engineering and Electronics,2003,25(1):113-115.
[13]HATAMI N.Thinned-ECOC ensemble based on sequential code shrinking[J].Expert Systems with Applications,2012,39(1):936-947.
[14]方敏.集成学习的多分类器动态融合方法研究[J].系统工程与电子技术,2006,28(11):1759-1769.FANG M.Study of integration method for multiple classifiers on ensemble learning[J].Systems Engineering and Electronics,2006,28(11):1759-1769.
[15]Department of Defense—Systems Management College.Systems engineering fundamentals[M].Fort Belvoir:Defense Acquisition University Press,2001:45-48.
[16]李大喜,杨建军,许勇,等.基于IDEF0和UML的空基反导军事概念模型[J].系统仿真学报,2014,26(5):969-974.LI D X,YANG J J,XU Y,et al.Military conceptual model of airborne anti-missile based on IDEF0and UML[J].Journal of System Simulation,2014,26(5):969-974.
[17]张忠,方可,杨明.基于群组AHP的复杂仿真系统可信度评估方法[J].系统工程与电子技术,2011,33(11):2569-2572.ZHANG Z,FANG K,YANG M.Method for complex simulation credibility evaluation based on group AHP[J].Systems Engineering and Electronics,2011,33(11):2569-2572.
[18]ZHOU Y C.FANG K,MA P,et al.An intelligent model validation method based on ECOC SVM[C]∥Proc.of the International Conference on Computer Modeling and Simulation,2018:67-71.
[2]SARIN H,KOKKOLARAS M,HULBERT G,et al.Comparing time histories for validation of simulation models:error measures and metrics[J].Journal of Dynamic Systems,Measurement,and Control,2010,132(6):768-778.
[3]CROCHEMORE L,PERRIN C,ANDREASSIAN V,et al.Comparing expert judgement and numerical criteria for hydrograph evaluation[J].Hydrological Sciences Journal,2015,60(3):402-423.
[4]HAUDUC H,NEUMANN M B,MUSCHALLA D,et al.Efficiency criteria for environmental model quality assessment:areview and its application to wastewater treatment[J].Environmental Modelling&Software,2015,68(C):196-204.
[5]SAGREBIN M,GOERKE N.Learning time-series similarity with a neural network by combining similarity measures[C]∥Proc.of the 16th International Conference on Artificial Neural Networks,2006:123-132.
[6]TEFERRA K,SHIELDS M D,HAPIJ A,et al.Mapping model validation metrics to subject matter expert scores for model adequacy assessment[J].Reliability Engineering&System Safety,2014,132(132):9-19.
[7]MCKENNY J L.Critique of verification of computer simulation models[J].Management Science,1967,14(2):102-103.
[8]方可,马萍,杨明.用于虚拟样机系统可信度评估的多属性决策网方法[J].计算机集成制造系统,2012,18(5):1054-1060.FANG K,MA P,YANG M.MAD network for virtual protocol systems credibility evaluation[J].Computer Integrated Manufacturing Systems,2012,18(5):1054-1060.
[9]MURPHY K P.Machine learning:aprobabilistic perspective[M].Cambridge:The MIT Press,2012.
[10]雷蕾,王晓丹,罗玺,等.ECOC多类分类研究综述[J].电子学报,2014,42(9):1794-1800.LEI L,WANG X D,LUO X,et al.An overview of multi-classification based on error correcting output codes[J].Acta Electronica Sinica,2014,42(9):1794-1800.
[11]NIELSON R H.Theory of the back-propagation neural network[C]∥Proc.of the International Joint Conference on Neural Networks,1989:583-604.
[12]甘俊英,张有为.基于BP神经网络的人脸识别[J].系统工程与电子技术,2003,25(1):113-115.GAN J Y,ZHANG Y W.Face recognition based on BP neural network[J].Systems Engineering and Electronics,2003,25(1):113-115.
[13]HATAMI N.Thinned-ECOC ensemble based on sequential code shrinking[J].Expert Systems with Applications,2012,39(1):936-947.
[14]方敏.集成学习的多分类器动态融合方法研究[J].系统工程与电子技术,2006,28(11):1759-1769.FANG M.Study of integration method for multiple classifiers on ensemble learning[J].Systems Engineering and Electronics,2006,28(11):1759-1769.
[15]Department of Defense—Systems Management College.Systems engineering fundamentals[M].Fort Belvoir:Defense Acquisition University Press,2001:45-48.
[16]李大喜,杨建军,许勇,等.基于IDEF0和UML的空基反导军事概念模型[J].系统仿真学报,2014,26(5):969-974.LI D X,YANG J J,XU Y,et al.Military conceptual model of airborne anti-missile based on IDEF0and UML[J].Journal of System Simulation,2014,26(5):969-974.
[17]张忠,方可,杨明.基于群组AHP的复杂仿真系统可信度评估方法[J].系统工程与电子技术,2011,33(11):2569-2572.ZHANG Z,FANG K,YANG M.Method for complex simulation credibility evaluation based on group AHP[J].Systems Engineering and Electronics,2011,33(11):2569-2572.
[18]ZHOU Y C.FANG K,MA P,et al.An intelligent model validation method based on ECOC SVM[C]∥Proc.of the International Conference on Computer Modeling and Simulation,2018:67-71.
© 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 |