一种改进的边缘层节点健康态势预估方法

doi:10.19665/j.issn1001-2400.2020.03.005

西安电子科技大学学报 ›› 2020, Vol. 47 ›› Issue (3): 32-39.doi: 10.19665/j.issn1001-2400.2020.03.005

一种改进的边缘层节点健康态势预估方法

孙骞^1,²,张家瑞¹(),高岭^2,³(),王宇翔¹,杨建锋¹

1.西北大学现代教育技术中心,陕西西安 710127
2.西北大学信息科学与技术学院,陕西西安 710127
3.西安工程大学计算机科学学院,陕西西安 710048

收稿日期:2019-10-16 出版日期:2020-06-20 发布日期:2020-06-19
通讯作者: 张家瑞,高岭
作者简介:孙骞(1980—),男,高级工程师,博士,E-mail: sq@nwu.edu.cn
基金资助:
国家自然科学基金(61572401);赛尔网络下一代互联网技术创新项目(NGII20150403)

Health prediction algorithm for edge layer nodes

SUN Qian^1,²,ZHANG Jiarui¹(),GAO Ling^2,³(),WANG Yuxiang¹,YANG Jianfeng¹

1. Modern Educational Technology Center, Northwest University, Xi’an 710127, China
2. National Local Joint Engineering Research Center for New Network Intelligent Information Services,Institute of Information Science and Technology, Northwest University, Xi’an 710127, China
3. National Local Joint Engineering Research Center for New Network Intelligent Information Services,Institute of Computer Science, Xi’an Polytechnic University, Xi’an 710048, China

Received:2019-10-16 Online:2020-06-20 Published:2020-06-19
Contact: Jiarui ZHANG,Ling GAO

摘要/Abstract

摘要：

针对现有的基于隐马尔可夫模型的边缘节点状态预估算法存在参数初值选取主观性较强、特征权重设置依赖经验、多维特征节点分析适应性差等问题,提出一种改进的边缘层节点健康状态预估算法。首先在算法的数据处理层,基于聚类实现对模型参数和观测序列量化进行优化;然后在算法的训练层,用多个单特征隐马尔可夫过程对多特征隐马尔可夫模型进行建模;最后在算法优化层,采用基于信息增益的自适应遗传算法对隐马尔可夫模型生成的状态序列进行优化和约简,有效地解决了特征权重设置和参数初值选取主观性强的问题。实验结果表明,与现有算法比较,该算法有效地提高了大规模边缘层节点的高维度健康状态的准确性。

关键词: 边缘节点, k均值聚类, 隐马尔可夫模型, 自适应遗传算法

Abstract:

An improved state prediction algorithm for edge layer nodes is proposed to solve the problem of the existing state prediction algorithm for edge layer nodes based on Hidden Markov, such as the subjectivity of initial parameter selection, the dependence of feature weights setting on experience, and the bad adaptability of multidimension feature node analysis. At the data processing layer of the algorithm, the parameter of the model and observation sequence are optimized by the method of clustering; and then at the training layer of the algorithm, the single-feature Hidden Markov Model is used to model the multi-feature Hidden Markov Model; finally, an adaptive genetic algorithm based on the information gain is used to optimize and reduce the state sequence generated by the Hidden Markov Model. The problems of feature weight setting and parameter initial value selection are solved effectively. Experimental results show that the proposed algorithm effectively improves the accuracy of the high-dimensional health state of large-scale edge layer nodes compared with the existing algorithms.

Key words: edge layer nodes, k-means, hidden Markov model, adaptive genetic algorithm

中图分类号:

TP311

孙骞,张家瑞,高岭,王宇翔,杨建锋. 一种改进的边缘层节点健康态势预估方法[J]. 西安电子科技大学学报, 2020, 47(3): 32-39.

SUN Qian,ZHANG Jiarui,GAO Ling,WANG Yuxiang,YANG Jianfeng. Health prediction algorithm for edge layer nodes[J]. Journal of Xidian University, 2020, 47(3): 32-39.

图/表 6

图1

图2

图3

图4

图5

图6

参考文献 21

[1]	ARMBRUST M, FOX A, GRIFFITH R, et al. A View of Cloud Computing[J]. Communcations of the ACM, 2010,53(4):50-58.
[2]	SHI W, CAO J, ZHANG Q, et al. Edge Computing: Vision and Challenges[J]. IEEE Internet of Things Journal, 2016,3(5):637-646. doi: 10.1109/JIOT.2016.2579198
[3]	龚俭, 臧小东, 苏琪, 等. 网络安全态势感知综述[J]. 软件学报, 2017,28(4):1010-1206.
	GONG Jian, JIAN Xiaodong, SU Qi, et al. Survey of Network Security Situation Awareness[J]. Journal of Software, 2017,28(4):1010-1206.
[4]	RAFEI A, PASHA E, JAMSHIDI ORAK R. Tuberculosis Surveillance Using a Hidden Markov Model[J]. Iranian Journal of Public Health, 2012,41(10):87-96.
[5]	NIKDELFAZ O, JALILI S. Disease Genes Prediction by HMM Based PU-learning Using Gene Expression Profiles[J]. Journal of Biomedical Informatics, 2018,81:102-111. doi: 10.1016/j.jbi.2018.03.006
[6]	SATORI H, ZEALOUK O, SATORI K, et al. Voice Comparison between Smokers and Non-smokers Using HMM Speech Recognition System[J]. International Journal of Speech Technology, 2017,20(4):771-777. doi: 10.1007/s10772-017-9442-0
[7]	KUMAR P, GAUBA H, ROY P P, et al. Coupled HMM-based Multi-sensor Data Fusion for Sign Language Recognition[J]. Pattern Recognition Letters, 2017,86:1-8. doi: 10.1016/j.patrec.2016.12.004
[8]	ZEINALI H, SAMETI H, BURGET L. HMM-based Phrase-independent i-vector Extractor for Text-dependent Speaker Verification[J]. IEEE/ACM Transactions on Audio, Speech and Language Processing, 2017,25(7):1421-1435. doi: 10.1109/TASLP.2017.2694708
[9]	LI T H S, KAO M C, KUO P H. Recognition System for Home-service-related Sign Language Using Entropy-based-Means Algorithm and ABC-based HMM[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2016,46(1):150-162. doi: 10.1109/TSMC.2015.2435702
[10]	RICHTER W, KRUGER P S. REXS: A Financial Risk Diagnostic Expert System[J]. South African Journal of Industrial Engineering, 1989,3(1):54-68.
[11]	ROY A, HALEVI T, MEMON N. An HMM-based Behavior Modeling Approach for Continuous Mobile Authentication [C]//Proceedings of the 2014 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2014: 3789-3793.
[12]	LI W J, LIU T S. Time Varying and Condition Adaptive Hidden Markov Model for Tool Wear State Estimation and Remaining Useful Life Prediction in Micro-milling[J]. Mechanical Systems and Signal Processing, 2019,131:689-702. doi: 10.1016/j.ymssp.2019.06.021
[13]	GAO Y, VILLECCO F, LI M, et al. Multi-scale Permutation Entropy Based on Improved LMD and HMM for Rolling Bearing Diagnosis[J]. Entropy, 2017,19(4):176. doi: 10.3390/e19040176
[14]	文志诚, 陈志刚, 唐军. 基于时间序列分析的网络安全态势预测[J]. 华南理工大学学报(自然科学版), 2016,44(5):137-143, 150.
	WEN Zhicheng, CHEN Zhigang, TANG Jun. Prediction of Network Security Situation on the Basis of Time Series Analysis[J]. Journal of South China University of Technology(Natural Science Edition), 2016,44(5):137-143, 150.
[15]	李慧, 马建峰. 一种情感极性感知的信任模型[J]. 西安电子科技大学学报, 2015,42(2):193-198. doi: 10.3969/j.issn.1001-2400.2015.02.032
	LI Hui, MA Jianfeng. Sentiment Polarity-awareness Trust model[J]. Journal of Xidian University, 2015,42(2):193-198. doi: 10.3969/j.issn.1001-2400.2015.02.032
[16]	GOLDBERG D E. Genetic Algorithms in Search, Optimization and Machine Learning[M]. New Jersey: Addison-Wesley Longman Publishing, 1989.
[17]	KENNEDY J, EBERHART R. Particle Swarm Optimization [C]//Proceedings of 1995 IEEE International Conference Neural Networks: 4. Piscataway: IEEE, 1995: 1942-1948.
[18]	慕彩红, 柴文壹, 刘逸, 等. 一种改进的网络鲁棒性与有效性增强方法[J]. 西安电子科技大学学报, 2018,45(4):6-11.
	MU Caihong, CHAI Wenyi, LIU Yi, et al. Improved Approach to Enhancing the Robustness and Effectiveness of Networks[J]. Journal of Xidian University, 2018,45(4):6-11.
[19]	AARTS E, KORST J. Simulated Annealing and Boltzmann Machines[M]. Hoboken: Wiley, 1989.
[20]	JATOTH C, GANGADHARAN G R, BUYYA R. Optimal Fitness Aware Cloud Service Composition Using an Adaptive Genotypes Evolution Based Genetic Algorithm[J]. Future Generation Computer Systems, 2019,94:185-198. doi: 10.1016/j.future.2018.11.022
[21]	ZHANG L, LV H, TAN D, et al. Adaptive Quantum Genetic Algorithm for Task Sequence Planning of Complex Assembly Systems[J]. Electronics Letters, 2018,54(14):870-872. doi: 10.1049/el.2018.0609

一种改进的边缘层节点健康态势预估方法

Health prediction algorithm for edge layer nodes

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 21

相关文章 10

Metrics

本文评价

推荐阅读 10

[1]	张春祥,周雪松,高雪瑶,刘欢. 融合k均值聚类与LSTM网络的半监督词义消歧[J]. 西安电子科技大学学报, 2021, 48(6): 161-171.
[2]	李钊,袁文浩,任崇广,黄程程,董霄霄. 跨层精度自动调节的k均值聚类近似计算方法[J]. 西安电子科技大学学报, 2020, 47(3): 50-57.
[3]	陈丹;刘明骞;张阳;胡晔. 低信噪比下突发信号的检测方法[J]. 西安电子科技大学学报, 2016, 43(6): 164-169.
[4]	汪云飞;毕笃彦;刘华伟;刘凌;赵晓林. 一种局部受限的规则聚类超像素算法[J]. 西安电子科技大学学报, 2016, 43(3): 95-100.
[5]	李慧;马建峰. 一种情感极性感知的信任模型 [J]. J4, 2015, 42(2): 193-198.
[6]	陈昌红;赵恒;梁继民;焦李成. 特征选择对FHMM性能影响研究[J]. J4, 2010, 37(5): 934-940.
[7]	田小林;焦李成;缑水平. 加权空间函数优化FCM的SAR图像分割 [J]. J4, 2008, 35(5): 846-852.
[8]	赵曙光1;焦李成1;王宇平2;杨万海1. 基于多目标遗传算法的模拟电路进化设计方法[J]. J4, 2004, 31(3): 342-346.
[9]	乔向东;王宝树;李涛. 基于EM算法的杂波环境下机动目标跟踪研究[J]. J4, 2003, 30(4): 514-519.
[10]	赵曙光1;刘贵喜2;杨万海1. 利用自适应遗传算法实现模拟电路自动设计[J]. J4, 2003, 30(3): 298-301.