基于核偏最小二乘法的物联网无线传感网络故障分析与研究

doi:10.11959/j.issn.1000-436x.2017265

通信学报 ›› 2017, Vol. 38 ›› Issue (Z2): 94-98.doi: 10.11959/j.issn.1000-436x.2017265

基于核偏最小二乘法的物联网无线传感网络故障分析与研究

周光海¹,宁兆龙¹,陈志奎¹,钟华¹,胡月明²

¹ 大连理工大学软件学院，辽宁大连 116620
² 华南农业大学自然资源与环境学院，广东广州 510642

出版日期:2017-11-01 发布日期:2018-06-07
作者简介:周光海（1995-），男，贵州织金人，大连理工大学硕士生，主要研究方向为多模态学习、图像标注。|宁兆龙（1986-），男，辽宁沈阳人，博士，大连理工大学讲师、硕士生导师，主要研究方向为网络优化、物联网、社交网络。|陈志奎（1968-），男，辽宁大连人，博士，大连理工大学教授、博士生导师，主要研究方向为大数据计算。|钟华（1992-），男，山西忻州人，大连理工大学硕士生，主要研究方向为多模态学习、跨模态检索、图像标注。|胡月明（1964-），男，广东广州人，博士，华南农业大学教授，博士生导师，主要研究方向为地理信息系统、农业物联网、土地资源。
基金资助:
国家自然科学基金资助项目(61672123);国家自然科学重点基金资助项目(U1301253);广东省重大科技计划基金资助项目(2015B010110006);中央高校基本科研业务基金资助项目(DUT2017TB02)

Fault analysis and research of wireless sensor network based on kernel partial least squares

Guang-hai ZHOU¹,Zhao-long NING¹,Zhi-kui CHEN¹,Hua ZHONG¹,Yue-ming HU²

¹ School of Software,Dalian University of Technology,Dalian 116620,China
² School of Natural Resources and Environment,South China Agricultural University,Guangzhou 510642,China

Online:2017-11-01 Published:2018-06-07
Supported by:
The National Natural Science Foundation of China(61672123);The State Key Program of National Natural Science Foundation of China(U1301253);The Key Science and Technology Planning Project of Guangdong Province(2015B010110006);The Fundamental Research Funds for the Central Universities(DUT2017TB02)

摘要/Abstract

摘要：

随着智能化、网络化传感器技术的日益成熟，无线传感网络在人类生活以及商业等领域有着广泛的应用，无线传感器网络节点通常只携带有限的资源，容易出现因资源不足而导致的故障，对WSN节点进行准确、及时的故障诊断，能够保障获得信息可靠性，从而提高 WSN 可维护性并且延长 WSN 的使用寿命。针对该问题，提出一种使用核偏最小二乘法来预测故障原因的方法，该方法克服了传统线性回归方法的缺陷，在高维的非线性空间对数据进行分析，同时，该方法也吸收了典型相关分析和主成分分析方法的特点，为分析提供了更加深入、丰富的内容，实验结果表明，提出的方法能够有效预测到故障原因。

关键词: 无线传感网, 故障分析, 核偏最小二乘法

Abstract:

With the development of intelligent and networked sensor technology,wireless sensor networks were widely used in human life and commercial fields,because wireless sensor network nodes usually only carry limited resources,it is prone to failures due to insufficient resources,the accurate and timely fault diagnosis of WSN nodes can ensure the reliability of information,thus improving the maintainability of WSN and prolonging the service life of WSN.A method of using kernel partial least squares has been proposed to predict the fault reasons,the method overcomes the defects of traditional linear regression method and the nonlinear high dimensional space for data analysis.Through many experiments,the method can absorb the characteristics of canonical correlation analysis and principal component analysis method,provide a more thorough and rich content analysi,that the reason of the fault can be predicted effectively.

Key words: wireless sensor networks, fault analysis, kernel partial least squares

中图分类号:

TP393

周光海,宁兆龙,陈志奎,钟华,胡月明. 基于核偏最小二乘法的物联网无线传感网络故障分析与研究[J]. 通信学报, 2017, 38(Z2): 94-98.

Guang-hai ZHOU,Zhao-long NING,Zhi-kui CHEN,Hua ZHONG,Yue-ming HU. Fault analysis and research of wireless sensor network based on kernel partial least squares[J]. Journal on Communications, 2017, 38(Z2): 94-98.

图/表 2

参考文献 17

[1]	刘敏钰, 吴泳, 伍卫国 . 无线传感网络 (WSN) 研究[J]. 微电子学与计算机, 2005,22(7): 58-61.
	LIU M Y , WU Y , WU W G . Wireless sensor network[J]. Microelec-tronics and Computer, 2005,22(7): 58-61.
[2]	ZHANG Q C , ZHU C S , YANG L T ,et al. An incremental CFS algorithm for clustering large data in industrial internet of things[J]. IEEE Transactions on Industrial Information. 2017,13(3): 1193-1201.
[3]	刘凯 . 无线传感器网络节点故障诊断算法研究[J]. 江南大学, 2011: 1-2.
	LIU K . The research on node fault diagnosis algorithm of wireless sensor network[J]. Jiangnan University, 2011: 1-2.
[4]	HARRISON D C , SEAH W K G , RAYUDU R . Rare event detection and propagation in wireless sensor networks[J]. ACM Computing Surveys (CSUR), 2016,48(4):58.
[5]	LIU Y , DONG M , OTA K ,et al. ActiveTrust:secure and trustable routing in wireless sensor networks[J]. IEEE Transactions on Information Forensics and Security, 2016,11(9): 2013-2027.
[6]	ZHANG Q C , CHEN Z K , YANG L T . A node scheduling model based on markov chain prediction for big data,international[J]. Journal of Communication Systems, 2015,28(9): 1610-1619.
[7]	余成波, 李芮, 何强 ,等. 基于粒子群算法及高斯分布的 WSN 节点故障诊断[J]. 振动.测试与诊断, 2013(1): 149-152.
	YU C B , LI R , HE Q . Fault diagnosis of nodes in WSN based on par-ticle swarm optimization and Gaussian distribution[J]. Journal of Vi-bration,Measurement and Diagnosis, 2013(1): 149-152.
[8]	毛乐琦 . 基于隐马尔科夫模型的无线传感网节点故障诊断算法[J]. 计算机应用与软件, 2014,31(1): 132-135.
	MAO L Q . WSN nodes fault diagnosis algorithm based on hidden markov model[J]. Computer Applications and Software, 2014,31(1): 132-135.
[9]	蒋鹏 . 一种改进的 DFD 无线传感器网络节点故障诊断算法研究[J]. 传感技术学报, 2008,21(8): 1417-1421.
	JIANG P . Research on an improved distributed fault detection algo-rithm for node failure diagnosis in wireless sensor networks[J]. Chi-nese Journal of Sensors and Actuators, 2008,21(8): 1417-1421.
[10]	高建良, 徐勇军, 李晓维 . 基于加权中值的分布式传感器网络故障检测[D]. 软件学报, 2017,18(5): 1208-1217.
	GAO J L , XU Y J , LI X W . Weighted-Median based distributed fault detection for wireless sensor networks[J]. Journal of Software, 2017,18(5): 1208-1217.
[11]	ROSIPAL R . Nonlinear partial least squares:an overview[J]. Chemo in for Maniocs and Advanced Machine Learning Perspectives:Complex Amputation Methods and Collaborative Techniques, 2010: 169-189.
[12]	HENSELER J , RINGLE C M , SARSTEDT M . Testing measurement invariance of composites using partial least squares[J]. International Marketing Review, 2016,33(3): 405-431.
[13]	KANEKO H , FUNATSU K . Ensemble locally weighted partial least squares as a just-in-time modeling method[J]. AIChE Journal, 2016,62(3): 717-725.
[14]	ROSIPAL R . Kernel partial least squares for nonlinear regression and discrimination[J]. Neural Network World, 2003,13(3): 291-300.
[15]	WONG E , PALANDE S , WANG B ,et al. Kernel partial least squares regression for relating functional brain network topology to clinical measures of behavior[C]// 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI). 2016: 1303-1306.
[16]	JIA Q , ZHANG Y . Quality-related fault detection approach based on dynamic kernel partial least squares[J]. Chemical Engineering Research and Design, 2016,106: 242-252.
[17]	ZHANG Q C , ZHU C S , YANG L T ,et al. An incremental CFS algorithm for clustering large data in industrial internet of things[J]. IEEE Transactions on Industrial Informatics, 2017,13(3): 1193-1201.

距离	PLS			KPLS
距离	Top 1	Top 3	Top 5	Top 1	Top 3	Top 5
NC	0.094 0	0.100 7	0.091 2	0.210 0	0.131 3	0.090 0
L1	0.060 0	0.048 7	0.074 0	0.002 0	0.018 7	0.018 4
L2	0.056 0	0.048 0	0.073 2	0.002 0	0.018 7	0.018 4
KL	0.060 0	0.100 7	0.101 6	0.220 0	0.145 3	0.103 6

迭代次数	PLS			KPLS
迭代次数	Top 1	Top 3	Top 5	Top 1	Top 3	Top 5
ncomp=1	0.056 0	0.094 7	0.101 6	0.222 0	0.150 0	0.104 8
ncomp=3	0.062 0	0.096 7	0.101 6	0.224 0	0.146 7	0.103 2
ncomp=5	0.060 0	0.100 7	0.101 6	0.220 0	0.145 3	0.103 6
ncomp=10	0.060 0	0.106 7	0.101 6	0.194 0	0.135 3	0.098 0
ncomp=15	0.060 0	0.110 0	0.101 6	0.224 0	0.143 3	0.104 4

基于核偏最小二乘法的物联网无线传感网络故障分析与研究

Fault analysis and research of wireless sensor network based on kernel partial least squares

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 2

参考文献 17

相关文章 15

Metrics

推荐阅读 0

[1]	李玮, 刘春, 谷大武, 孙文倩, 高建宁, 秦梦洋. Saturnin-Short轻量级认证加密算法的统计无效故障分析[J]. 通信学报, 2023, 44(4): 167-175.
[2]	李玮, 汪梦林, 谷大武, 李嘉耀, 蔡天培, 徐光伟. 轻量级密码算法TWINE的唯密文故障分析[J]. 通信学报, 2021, 42(3): 135-149.
[3]	王田,沈雪微,罗皓,陈柏生,王国军,贾维嘉. 基于雾计算的可信传感云研究进展[J]. 通信学报, 2019, 40(3): 170-181.
[4]	沈煜,李玮,谷大武,吴益鑫,曹珊,刘亚,刘志强,周志洪. ARIA密码的积分故障分析[J]. 通信学报, 2019, 40(2): 164-173.
[5]	李玮,吴益鑫,谷大武,李嘉耀,曹珊,汪梦林,蔡天培,丁祥武,刘志强. SIMON轻量级密码算法的唯密文故障分析[J]. 通信学报, 2019, 40(11): 122-137.
[6]	梁俊斌,周翔,李陶深. 移动低占空比无线传感网中低能耗的主动邻居发现算法[J]. 通信学报, 2018, 39(4): 45-55.
[7]	王田,李洋,贾维嘉,王国军,彭绍亮. 传感云安全研究进展[J]. 通信学报, 2018, 39(3): 35-52.
[8]	张策,李鸥,童昕,杨延平. 基于压缩感知与矩阵补全技术的WSN数据收集算法[J]. 通信学报, 2018, 39(2): 164-173.
[9]	纪祥敏,赵波,刘金会,贾建卫,张焕国,向騻. 基于对称矩阵分解的无线传感网密钥恢复攻击[J]. 通信学报, 2018, 39(10): 87-96.
[10]	王天舒,张功萱,杨曦晨. 基于ZigBee的无线传感网可信溶液监测系统[J]. 通信学报, 2017, 38(Z2): 67-77.
[11]	蔡青松,陈希厚. 无线传感网中基于谱矩的链路优化策略[J]. 通信学报, 2017, 38(Z2): 170-177.
[12]	舒坚,刘满兰,郑巍. 基于AdaBoost的链路质量预测机制研究[J]. 通信学报, 2017, 38(Z1): 39-45.
[13]	张策,张霞,李鸥,梅关林,韩哲,张大龙,刘广怡. 不可靠链路下基于压缩感知的WSN数据收集算法[J]. 通信学报, 2016, 37(9): 131-141.
[14]	牛晓光,魏川博,姚亚兰. 传感网中能量均衡高效的源位置隐私保护协议[J]. 通信学报, 2016, 37(4): 23-33.
[15]	徐琨,刘宏立,詹杰,马子骥. 容忍恶意攻击的无线传感网络安全定位算法[J]. 通信学报, 2016, 37(12): 95-102.