联合改进核FCM与智能优化SVR的WSNs链路质量预测

doi:10.3969/j.issn.0372-2112.2018.01.013

摘要
图/表
参考文献(0)
相关文章 (15)

全文: PDF (1450 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要为提高无线传感器网络（WSNs）链路质量预测精度和降低噪声影响，提出了一种联合改进核FCM与智能优化SVR （improved kernel furry c-means and intelligent support vector regression，IKFCM-ISVR）的WSNs链路质量预测方案.首先将基于紧致度和离散度的有效性指数引入核FCM方法，实现样本集聚类个数自动划分；然后采用改进核FCM方法对链路质量样本数据进行处理，获得样本聚类隶属度；在此基础上，构建群居蜘蛛优化SVR预测模型，采用基于"动态折射"学习机制的群集蜘蛛对模型参数进行优化，得到不同聚类最佳SVR参数组合；最后采用IKFCM-ISVR算法对不同实验场景下的WSNs链路数据进行预测评估.仿真结果表明，同其它预测算法相比，该算法预测精度提高了36.8~68.4%.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘洲洲
	李士宁
	张筱
	郭文强

关键词 ：链路质量预测, 核模糊C-均值聚类, 支持向量回归(SVR), 群居蜘蛛优化

Abstract：In order to improve the prediction accuracy and reduce the noise influence of link quality for wireless sensor network (WSNs),a link quality prediction algorithm based on improved kernel FCM and intelligent SVR (IKFCM-ISVR) is proposed.Firstly,the validity index based on compactness and dispersion is introduced into the kernel FCM (KFCM) method,which realizes the automatic division of cluster number for samples.Then the improved kernel FCM method is used to process the data of link quality,and the membership degree of sample clustering is obtained.On this basis,the SVR prediction model based on social spider optimization (SSO) algorithm is constructed,and the SSO based on dynamic refraction learning mechanism is used to optimize the parameters,getting the best combination of SVR parameters for different clustering.Finally the IKFCM-ISVR algorithm is used to predict the WSNs link data in different experimental scenarios.The simulation results show that,compared with other prediction algorithms,the prediction accuracy of the algorithm is improved by 36.8~68.4%.

Key words： link quality prediction kernel fuzzy C-means clustering support vector regression (SVR) social spider optimization

收稿日期: 2016-12-20

ZTFLH:

TP393

基金资助:国家自然科学基金（No.61601365）；陕西省教育厅科研计划（No.16JK1395）；陕西省自然科学基础研究计划面上项目（No.2017JM6096）

作者简介: 刘洲洲,男,1981年出生,陕西延安人,西北工业大学博士后,西安航空学院副教授.主要研究方向为无线传感器网络、智能优化算法、不确定性推理.E-mail:nazi2005@126.com;李士宁,男,1967年出生,陕西延安人,博士、博士生导师,西北工业大学计算机学院教授,主要研究方向为智能计算、无线传感器网络.E-mail:lishining@nwpu.edu.cn;张筱,女,1992年出生,陕西渭南人,硕士研究生,主要研究方向智能系统、移动机器人.E-mail:eexiaox@163.com;郭文强,男,1971年生,陕西咸阳人,博士、副教授、硕士生导师,主要研究方向:电子信息、智能系统.E-mail:375330770@qq.com

引用本文:

刘洲洲, 李士宁, 张筱, 郭文强. 联合改进核FCM与智能优化SVR的WSNs链路质量预测[J]. 电子学报, 2018, 46(1): 90-97. LIU Zhou-zhou, LI Shi-ning, ZHANG Xiao, GUO Wen-qiang. Link Quality Prediction Algorithm Based on Improved Kernel FCM and Intelligent SVR for WSNs. Acta Electronica Sinica, 2018, 46(1): 90-97.

链接本文:

http://www.ejournal.org.cn/CN/10.3969/j.issn.0372-2112.2018.01.013 或 http://www.ejournal.org.cn/CN/Y2018/V46/I1/90

[1] KOLAR V,RAZAK S,MAHONEN P,et al.Measurement and analysis of link quality in wireless networks:an application perspective[A].IEEE Second International Workshop on Carrier-grade Wireless Mesh Networks[C].San Diego,USA:IEEE,2010.1-6.
[2] 侯建军,朱明强,刘颖.一种强背景噪声下的WSN目标定位算法[J].北京理工大学学报,2016,36(5):535-540. HOU Jian-jun,ZHU Ming-qiang,LIU Ying.An algorithm for WSN target location under strong background noise[J].Journal of Beijing Institute of Technology,2016,36(5):535-540.(in Chinese)
[3] 汪成亮,王强.基于活动预测和能耗均衡的WSNs路由算法[J].北京航空航天大学学报,2014,40(1):10-17. WANG Cheng-liang,WANG Qiang.WSNs routing algorithm based on activity prediction and energy balance[J].Journal of Beihang University,2014,40(1):10-17.(in Chinese)
[4] LEE Seung-joon,BHATTACHARJEE B,BANERJEE S,et al.A general framework for efficient geographic routing in wireless networks[J].Computer Networks,2010,54(5):844-861.
[5] 舒坚,汤津,刘琳岚,等.基于模糊支持向量回归机的WSNs链路质量预测[J].计算机研究与发展,2015,52(8):1842-1851. SHU Jian,TANG Jin,LIU Lin-lan,et al.Fuzzy support vector regression-based link quality prediction model for wireless sensor networks[J].Journal of Computer Research and Development,2015,52(8):1842-1851.(in Chinese)
[6] 郭志强,王沁,万亚东,等.基于综合性评估的无线链路质量分类预测机制[J].计算机研究与发展,2013,50(6):1227-1238. GUO Zhi-qiang,WANG Qin,WAN Ya-dong,et al.A classification prediction mechanism based on comprehensive assessment for wireless link quality[J].Journal of Computer Research and Development,2013,50(6):1227-1238.(in Chinese)
[7] 商强,杨兆升,李志林,等.基于相空间重构和RELM的短时交通流量预测[J].华南理工大学学报(自然科学版),2016,44(4):109-114. SHANG Qiang,YANG Zhao-sheng,LI Zhi-lin,et al.Short term traffic flow forecasting based on phase space reconstruction and RELM[J].Journal of South China University of Technology (Natural Science Edition),2016,44(4):109-114.(in Chinese)
[8] LIU T,CERPA A E.Foresee (4C):Wireless link prediction using link features[A].Proc of the 10th Int Conf on Information Processing in Sensor Networks[C].Piscataway,NJ:IEEE,2011.294-305.
[9] 朴尚哲,超木日力格,于剑.模糊C均值算法的聚类有效性评价[J].模式识别与人工智能,2015,28(5):452-461. PIAO Shang-Zhe,Chaomurilige,YU Jian.Cluster validity indexes for FCM clustering algorithm[J].Pattern Recognition and Artificial Intelligence,2015,28(5):452-461.(in Chinese)
[10] CHENG M Y,HOANG N D,ROY A F V,et al.A novel time-depended evolutionary fuzzy SVM inference model for estimating construction project at completion[J].Engineering Application of Artificial Intelligence,2012,25(4):744-752.
[11] LIU T,CERPA A E.Data-driven link quality prediction using link features[J].ACM Trans on Sensor Networks,2014,10(2):37-72.
[12] 尚凤军,龚文娟,耿哲.基于链路预测和网络编码的MAC机制[J].通信学报,2016,37(1):17-27. SHANG Feng-jun,GONG Wen-juan,GENG Zhe.MAC mechanism based on link prediction and network coding[J].Journal of Communication,2016,37(1):17-27.(in Chinese)
[13] MA Ai-long,ZHONG Yan-fei,ZHANG Liang-pei.Adaptive multiplicative meme-tic fuzzy clustering algorithm for remote sensing imagery[J].IEEE Trans on Geoscience and Remote Sensing,2015,53(8):4202-4217.
[14] SAHA I,SARKAR J P,MAULIK U.Ensemble based rough fuzzy clustering for categorical data[J].Knowledge Based Systems,2015,77:114-127.
[15] 孙力娟,陈小东,韩崇,等.一种新的数据流模糊聚类方法[J].电子与信息学报,2015,37(7):1620-1625. SUN Li-juan,CHEN Xiao-dong,HAN Chong,et al.New fuzzy-clustering algorithm for data stream[J].Journal of Electronics & Information Technology,2015,37(7):1620-1625.(in Chinese)
[16] VAPNIK V N.The Nature of Statistical Learning Theory[M].New York:Springer,1995.
[17] CUEVAS E,CIENFUEGOS M,ZALDVIA D,et al.A swarm optimization algorithm inspired in the behavior of the social spider[J].Expert System with Applications,2013,40(16):6374-6384.