计算机科学 ›› 2017, Vol. 44 ›› Issue (5): 89-94.doi: 10.11896/j.issn.1002-137X.2017.05.016

• 信息安全 • 上一篇    下一篇

基于深度极限学习机的危险源识别算法HIELM

李诗瑶,周良,刘虎   

  1. 南京航空航天大学计算机科学与技术学院 南京210016,南京航空航天大学计算机科学与技术学院 南京210016,南京航空航天大学计算机科学与技术学院 南京210016
  • 出版日期:2018-11-13 发布日期:2018-11-13
  • 基金资助:
    本文受江苏省产学研联合创新资金项目(SBY201320423)资助

Hazard Identification Algorithm Based on Deep Extreme Learning Machine

LI Shi-yao, ZHOU Liang and LIU Hu   

  • Online:2018-11-13 Published:2018-11-13

摘要: 危险源识别是民用航空管理的重要环节之一,危险源识别结果必须高度准确才能确保飞行的安全。为此,提出了一种基于深度极限学习机的危险源识别算法HIELM(Hazard Identification Algorithm Based on Extreme Lear-ning Machine),设计了一种由多个深层栈式极限学习机(S-ELM)和一个单隐藏层极限学习机(ELM)构成的深层网络结构。算法中,多个深层S-ELM使用平行结构,各自可以拥有不同的隐藏结点个数,按照危险源领域分类接受危险源状态信息完成预学习,并结合识别特征改进网络输入权重的产生方式。在单隐藏层ELM中,深层ELM的预学习结果作为其输入,改进了反向传播算法,提高了网络识别的精确度。同时,分别训练各深层S-ELM,缓解了高维数据训练的内存压力和节点过多产生的过拟合现象。

关键词: 危险源识别,深度学习,极限学习机(ELM),分类

Abstract: Hazard identification plays an important role in aviation safety management.The results of hazard identification must be highly accurate to ensure the safety of the flight.To this end,a hazard identification algorithm based on deep extreme learning machine (HIELM) was proposed,which consists of multiple deep stacked ELMs and a single ELM.There are a parallel structure and different number of hidden nodes among these deep ELMs,and the hazard information is gotten to produce deep features according to the hazard area.In addition,the way of generating input weights has been enhanced with recognition features.The single ELM receives the results as its input.With the help of the improved back propagation algorithm,the network can achieve much better accuracy.The thought that deep ELMs are trained respectively alleviates the memory pressure and the over fitting phenomenon when facing the high-dimensional datasets.

Key words: Hazards identification,Deep learning,Extreme learning machine (ELM),Clas sification

[1] HUANG G B,WANG D H,LAN Y.Extreme Learning Ma-chines:a Survey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122.
[2] SMITH B E,DE-JONG H H,EVERDIJ M H C.A Prognostic Method to Identify Hazards for Future Aviation Concepts[C]∥ICAS Secretariat-26th Congress of International Council of the Aeronautical Sciences.ICAS Secretariat,2008:3950-3965.
[3] GROTH K,WANG C D,MOOSLEH A.Hybrid Causal Metho-dology And Software Platform For Probabilistic Risk Assessment And Safety Monitoring Of Socio-Technical Systems[J].Reliability Engineering & System Safety,2010,95(12):1276-1285.
[4] CUI L,SHU Y D,WANG Z H,et al.HASILT:An Intelligent Software Platform for HAZOP,LOPA,SRS and SIL Verification[J].Reliability Engineering & System Safety,2012,108:56-64.
[5] XU X Z,WANG G Y,DING S F,et al.A New Method For Constructing Granular Neural Networks Based On Rule Extraction And Extreme Learning Machine[J].Pattern Recognition Letters,2015,67:138-144.
[6] DARAAMOLA O,STALHANE T,MOSER T,et al.A Conceptual Framework for Semantic Case-based Safety Analysis[C]∥Emerging Technologies & Factory Automation (ETFA).IEEE,2011:1-8.
[7] ZHANG Y J,SUN Y C.Safety Risk Assessment of Human-machine Interaction Behavior in Cockpit[C]∥Computational Intelligence and Design (ISCID).IEEE,2014:39-42.
[8] ZHOU H M,HUANG G B,LIN Z P,et al.Stacked Extreme Learning Machines[J].IEEE Transactions on Cybernetics,2015,45(9):2013-2025.
[9] LIANG N Y,HUANG G B,SARATCHADRAN P,et al.AFast and Accurate Online Sequential Learning Algorithm for Feedforward Networks[J].IEEE Transactions on Neural Networks,2006,17(6):1411-1423.
[10] JAVED K,GOURIVEAU R,ZERHOUNI N.A New Multiva-riate Approach for Prognostics Based on Extreme Learning Machine and Fuzzy Clustering[J].IEEE Transactions on Cyberne-tics,2015,45(12):2626-2639.
[11] ZHANG N,DING S F,SHI Z Z.Denoising Laplacian Multi-La-yer Extreme Learning Machine[J].Neurocomputing,2016,171:1066-1074.
[12] MCDONNELL M D,TISSERA M D,VLADUSICH T,et al.Fast,Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm[J].Plos One,2015,10(8).
[13] DENG W Y,ZHENG Q H,CHEN L,et al.Research On Extreme Learning of Neural Networks[J].Chinese Journal of Computers,2010,33(2):279-287.(in Chinese) 邓万宇,郑庆华,陈琳,等.神经网络急速学习方法研究[J].计算机学报,2010,3(2):279-287.
[14] BUENO-CRESPO A,GARCIA-LAENCINA P J,SANCHO-GO-MEZ J L,et al.Neural Architecture Design Based On Extreme Learning Machine[J].Neural Networks,2013,48:19-24.
[15] JOLLIFFE I T.Principal Component Analysis[M].New York:Wiley Online Library,2010.
[16] MOZAFFARI A,LASHGARIAN A N,FATHI A.Regularized Machine Learning Through Constraint Swarm And Evolutionary Computation Applied To Regression Problems[J].International Journal of Intelligent Computing and Cybernetics,2014,7(4):346-381.
[17] ZHU W T,MIAO J,QING L Y.Constrained Extreme Learning Machine:a Novel Highly Discriminative Random Feedforward Neural Network[C]∥Proceedings of The 2014 International Joint Conference On Neural Networks.IEEE,2014:800-807.
[18] ZHAO R,MAO K Z.Semi-Random Projection for Dimensionality Reduction and Extreme Learning Machine in High-Dimensional Space[J].IEEE Computational Intelligence Magazine,2015,10(3):30-41.
[19] LI C,RENE-VINICIO S,ZURITA G,et al.Multimodal DeepSupport Vector Classification With Homologous Features And Its Application To Gearbox Fault Diagnosis[J].Neurocompu-ting,2015,8:119-27.
[20] LIU B,XIA S X,MENG F R,et al.Manifold regularized extreme learning machine[J].Neural Computing and Applications,2016,27(2):255-269.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!