[1]陈 璟,虞继敏.基于果蝇—广义回归神经网络优化的WSN节点定位算法[J].南京师范大学学报(自然科学版),2017,40(02):31.[doi:10.3969/j.issn.1001-4616.2017.02.006]
 Chen Jing,Yu Jimin.Node Localization Algorithm of WSN Based on Fruit Flies Optimizationand Generalized Regression Neural Network[J].Journal of Nanjing Normal University(Natural Science Edition),2017,40(02):31.[doi:10.3969/j.issn.1001-4616.2017.02.006]
点击复制

基于果蝇—广义回归神经网络优化的WSN节点定位算法()
分享到:

《南京师范大学学报》(自然科学版)[ISSN:1001-4616/CN:32-1239/N]

卷:
第40卷
期数:
2017年02期
页码:
31
栏目:
·数学·
出版日期:
2017-06-29

文章信息/Info

Title:
Node Localization Algorithm of WSN Based on Fruit Flies Optimizationand Generalized Regression Neural Network
文章编号:
1001-4616(2017)02-0031-08
作者:
陈 璟1虞继敏2
(1.广西科技师范学院数学与计算机科学学院,广西 来宾 546199)(2.重庆邮电大学工业物联网与网络化控制教育部重点实验室,重庆 400065)
Author(s):
Chen Jing1Yu Jimin2
(1.College of Mathematics and Computer Science,Guangxi Science & Technology Normal University,Laibin 546199,China)(2.Key Laboratory of Industrial Internet of Things & Network Control,MOE,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)
关键词:
无线传感器网络节点定位广义回归神经网络果蝇优化算法
Keywords:
wireless sensor networksnode localizationgeneralized regression neural networksfruit fly optimization algorithm
分类号:
TP391.9
DOI:
10.3969/j.issn.1001-4616.2017.02.006
文献标志码:
A
摘要:
针对无线传感器网络(WSN)基于测距的定位算法中,利用节点坐标计算方法获得的节点坐标位置存在较大误差的问题,提出一种无需进行坐标计算的果蝇—广义回归神经网络(FOA-GRNN)优化的WSN节点定位算法. 该算法利用广义回归神经网络(GRNN)较快的学习速度和较强的逼近能力建立WSN节点定位模型,通过果蝇优化算法(FOA)调整广义回归神经网络的平滑参数,降低调整平滑参数时人为因素的影响,由神经网络直接输出未知节点坐标. 仿真实验表明,通过果蝇算法优化的FOA-GRNN模型的节点定位精度比未经优化的GRNN模型的节点定位精度高. 同时,比较了FOA-GRNN模型与BP神经网络模型、虚拟节点BP网络模型(VNBP)在WSN节点定位中效果,表明FOA-GRNN模型在WSN节点定位精确性方面具有明显优势.
Abstract:
In order to improve the accuracy of WSN node location and avoid the deficiency of the distance measurement based localization algorithm using node coordinates to calculate the location of unknown nodes,a new WSN node localization algorithm of Fruit Flies Optimization-Generalized Regression Neural Network(FOA-GRNN)was presented. The proposed FOA-GRNN algorithm builds WSN positioning model by the fast learning speed and strong approximation ability of Generalized Regression Neural Network(GRNN)and adjusts GRNN’s smoothing parameter by using Fruit Flies Optimization Algorithm(FOA)to reduce the impact of human factors on selecting GRNN smoothing parameter to minimum. Finally,the coordinates of unknown nodes in WSN can be directly obtained from the output of FOA-GRNN model. Simulating results show that the localization accuracy of FOA-GRNN optimized by FOA is better than that of GRNN model. In addition,the FOA-GRNN algorithm was compared with BP algorithm and VNBP algorithm in WSN nodes localization. Simulating results further show the FOA-GRNN algorithm has obvious advantages in the accuracy of WSN node localization.

参考文献/References:

[1] 陈龙,张可,罗配明. 改进的Elman神经网络在WSNs距离预测中的应用[J]. 传感器与微系统,2013,32(1):149-152.
[2]田莹,张淑芳. 基于SOM的WSN节点定位算法与仿真实现[J]. 系统仿真学报,2011,23(6):1 166-1 172.
[3]李牧东,熊伟,梁青. 基于人工蜂群改进算法的无线传感器网络定位算法[J]. 传感技术学报,2013,26(3):241-245.
[4]PRINCE S,SUNIL A. TDOA based node localization in WSN using neural network[C]//2013 International Conference on Communication Systems and Network Technologies(CSNT). Hainan,China,2013:400-404.
[5]ASHISH P,RAI C S,REDDY B V R. Comparative analysis of Bayesian regularization and levenberg-marquardt training algorithm for localization in wireless sensor network[C]//2013 15th International Conference on Advanced Communication Technology. Adelaide,South Australia,2013:191-194.
[6]LIU R J,SUN K,SHEN J Y. BP localization algorithm based on virtual nodes in wireless sensor network[C]//2010 6th International Conference on Wireless Communications,Networking and Mobile Computing. Chengdu,China,2010:1-4.
[7]PAN W T. Using fruit fly optimization algorithm optimized general regression neural network to construct the operating performance of enterprises model[J]. Journal of Taiyuan university of technology,2011,29(4):1-4.
[8]贾义鹏,吕庆,尚岳全. 基于粒子群算法和广义回归神经网络的岩爆预测[J]. 岩石力学与工程学报,2013,32(2):343-348.
[9]LIU C L,ZHANG L L,WANG J Q. Application of FOA-GRNN to prediction of moisture content in crude oil of wellheat metering[J]. Computer-simulation,2012,29(11):243-246.
[10]王海军,涂凯,闫晓荣. 基于果蝇优化算法的GRNN模型在边坡稳定预测中的应用[J]. 水电能源科学,2015(1):24-27.
[11]PAN W T. A new fruit fly optimization algorithm:taking the financial distress model as an example[J]. Knowledge-based systems,2012,26:69-74.
[12]SHI D Y,LU J,LU L J. A judge model of the impact of lane closure incident on individual vehicles on freeways based on RFID technology and FOA-GRNN method[J]. Journal of Wuhan university of technology,2012,34(3):63-68.
[13]张燕君,刘文哲,付兴虎,等. 基于自适应变异果蝇优化算法和广义回归神经网络的布里渊散射谱特征提取[J]. 光谱学与光谱分析,2015(10):2 916-2 923.
[14]邹兵,陈西宏,薛伦生,等. 果蝇优化算法优化灰色神经网络的卫星钟差预报[J]. 测绘科学,2014(9):44-48.
[15]LI H Z,GUO S,LI C J. A hybrid annual power load forecasting model based on generalized regression neural network with fruit fly optimization algorithm[J]. Knowledge-based systems,2013,37:378-387.
[16]PAN W T. A new evolutionary computation approach:fruit fly optimization algorithm[C]//2011 Conference of Digital Technology and innovation Management. Taipei,2011.

相似文献/References:

[1]张丽虹.无线传感网络改进混合移动代理路由的研究[J].南京师范大学学报(自然科学版),2012,35(04):145.
 Zhang Lihong.Study on Improved Hybrid Mobile Agent Routing in Wireless Sensor Networks[J].Journal of Nanjing Normal University(Natural Science Edition),2012,35(02):145.
[2]李致远,朱求志,吴永焜,等.基于小波分析的无线传感网实时异常检测算法[J].南京师范大学学报(自然科学版),2014,37(01):87.
 Li Zhiyuan,Zhu Qiuzhi,Wu Yongkun,et al.Wavelet Analysis-Based Real-Time Anomaly Detection Algorithm for Wireless Sensor Network[J].Journal of Nanjing Normal University(Natural Science Edition),2014,37(02):87.
[3]李 江,刘学军,章 玮.基于门限路由的源节点位置隐私保护协议[J].南京师范大学学报(自然科学版),2014,37(01):117.
 Li Jiang,Liu Xuejun,Zhang Wei.Threshold Routing for Source-Location Privacy Protection in Wireless Sensor Networks[J].Journal of Nanjing Normal University(Natural Science Edition),2014,37(02):117.
[4]徐晓菊,唐 翔,黄为勇.一种基于RSSI的煤矿井下WSN节点快速定位算法[J].南京师范大学学报(自然科学版),2014,37(04):158.
 Xu Xiaoju,Tang Xiang,Huang Weiyong.A Fast Node Localization Algorithm for Coal-mine UndergroundBased on RSSI[J].Journal of Nanjing Normal University(Natural Science Edition),2014,37(02):158.

备注/Memo

备注/Memo:
收稿日期:2016-05-18.
基金项目:2014年度广西高校科学技术研究项目(LX2014489)、2016年广西高校重点实验室建设项目、重庆市自然科学基金(cstc2013jcyjC0013).
通讯联系人:陈璟,副教授,研究方向:控制理论、智能算法. E-mail:lzszcj@163.com
更新日期/Last Update: 2017-06-30