基于最小二乘支持向量回归机的 无线传感器网络目标定位法

刘桂雄; 张晓平; 周松斌

doi:null

您当前的位置：

首页 >

文章列表页 >

基于最小二乘支持向量回归机的无线传感器网络目标定位法

信息科学 | 更新时间：2020-08-12

- 基于最小二乘支持向量回归机的无线传感器网络目标定位法
- Target localization in wireless sensor networks based on LSSVR
- 光学精密工程 2009年17卷第7期页码：1766-1773
- 作者机构：
  
  华南理工大学机械与汽车工程学院,广东广州,510640
- 作者简介：
- 基金信息：
  
  粤港关键领域重点突破项目(No.2007A30310004)();广东省科技攻关计划项目(No.2007B010400046,No.2006B12407003)();教
- DOI：
  中图分类号： TP301
- 收稿日期：2008-09-02，
  
  修回日期：2008-10-10，
  
  网络出版日期：2009-07-25，
  
  纸质出版日期：2009-07-25
- 稿件说明：
移动端阅览
刘桂雄, 张晓平, 周松斌. 基于最小二乘支持向量回归机的无线传感器网络目标定位法[J]. 光学精密工程, 2009,17(7): 1766-1773

LIU Gui-xiong, ZHANG Xiao-ping, ZHOU Song-bin. Target localization in wireless sensor networks based on LSSVR[J]. Editorial Office of Optics and Precision Engineering, 2009,17(7): 1766-1773
刘桂雄, 张晓平, 周松斌. 基于最小二乘支持向量回归机的无线传感器网络目标定位法[J]. 光学精密工程, 2009,17(7): 1766-1773 DOI：

LIU Gui-xiong, ZHANG Xiao-ping, ZHOU Song-bin. Target localization in wireless sensor networks based on LSSVR[J]. Editorial Office of Optics and Precision Engineering, 2009,17(7): 1766-1773 DOI：

摘要

针对RSSI测距误差直接影响无线传感器网络(WSN)目标定位准确度的问题

从目标位置与目标到传感器节点测距矢量的双射关系入手

建立最小二乘支持向量回归机(LSSVR)目标定位的数学模型

提出了一种基于LSSVR的WSN目标定位方法TL-LSSVR。根据虚拟目标坐标和虚拟目标到传感器节点距离矢量构造出训练样本

通过确定学习区域及网格化采样获得训练样本集

采用LSSVR训练得到定位模型

将测量得到的距离矢量输入定位模型实现目标定位。对不同传感器节点数量以及不同节点分布情况下的WSN目标进行了定位实验。结果显示

对于节点随机分布的情况

TL-LSSVR方法的定位误差比最小二乘法减小21.0%~43.1%;对于节点均匀分布的情况

TL-LSSVR方法的定位误差则减小26.5%~48.7%

表明TL-LSSVR方法能有效减小测距误差对定位结果的影响

提高目标定位准确度。

Abstract

In consideration of the effect of ranging errors of the RSSI method on the target localization accuracy in a Wireless Sensor Networks (WSN)

a mathematical model of target localization based on Least Square Support Vector Regression (LSSVR) is established according to the double mapping between the target's coordinate and the distance vector measured from the target to sensor nodes. Furthermore

the target localization method based on LSSVR in the WSN

TL-LSSVR

is proposed. According to TL-LSSVR

the training samples are formed in accordance with the virtual target coordinate and the distance vector between the virtual target and the sensor nodes

and then the training sample sets are obtained by selecting learning areas and grid sampling. Moreover

the localization model can be trained using LSSVR and the target can be located by inputting the distance vector between the target and the sensor nodes into a localization model. The experiments of target localization in the WSN under different numbers and distributions of sensor nodes are performed. Experimental results show that when sensor node distributes randomly

the target localization errors using the TL-LSSVR are reduced by 21.0%-43.1% compared with that of a least square estimation

and when sensor node distributes uniformly

the target localization errors are reduced by 26.5%-48.7%

which indicates that the target localization errors are reduced evidently

and the accuracy of target localization is improved.

关键词

Keywords

references

马奎, 黄河清, 沈杰, 等. 基于混合汇聚节点的无线传感器网络数据收集方法[J]. 光学精密工程, 2008,16(9):1752-1758. MA K, HUANG H Q, SHEN J, et al.. A data collection method with hybrid sinks in wireless sensor networks[J]. Opt. Presicion Eng., 2008,16(9):1752-1758.(in Chinese)[2] LIU X Q, ZHAO G, MA X L. Target localization and tracking in noisy binary sensor networks with known spatial topology . Proc. of IEEE International Conference on Acoustics, Speech and Signal Processing, Honolulu, HI, 2007,2:1029-1032.[3] LEE J, CHO K, LEE S, et al.. Distributed and energy-efficient target localization and tracking in wireless sensor networks[J]. Computer Communications, 2006,29(13-14):2494-2505.[4] HE T, HUANG C D, BLUM B M, et al.. Range-free localization and its impact on large scale sensor networks[J]. ACM Transactions on Embedded Computing System (TECS), 2005,4(4):877-906.[5] HARA S, ANZAI D. Experimental performance comparison of RSSI and TDOA-based location estimation methods . Proc. of IEEE 2008 Vehicular Technology Conference, Singapore, 2008:2651-2655. [6] NIU R, VARSHNEY P K. Target location estimation in sensor networks with quantized data[J]. IEEE Transactions on Signal Processing, 2006,54(12):4519-4528.[7] HARA S, ANZAI D. Comparison of three estimation methods for RSSI-based localization with multiple transmit antennas . Proc. of Mobile Adhoc and Sensor Systems 2007 IEEE International Conference, Pisa, 2007:1-3.[8] 赵吉文,刘永斌,苏亚辉,等. 新型直线电机支持向量机非线性建模研究[J]. 光学精密工程,2006,14(3):450-455. ZHAO J W,LIU Y B,SU Y H,et al.. Research on SVM model of a novel cylinder linear motor[J]. Opt. Precision Eng., 2006,14(3):450-455. (in Chinese)[9] 赵吉文,刘永斌,孔凡让,等. 基于SVM和遗传算法的新型直线电机结构参数优化[J]. 光学精密工程,2006,14(5):870-875. ZHAO J W,LIU Y B,KONG F R, et al.. Parameter optimization of novel cylinder type linear motor based on SVM and genetic algorithm[J]. Opt. Precision Eng., 2006,14 (5):870-875. (in Chinese)[10] 林伟青, 傅建中, 许亚洲, 等. 基于LS-SVM与遗传算法的数控机床热误差辨识温度传感器优化策略[J]. 光学精密工程, 2008,16 (9):1682-1687. LIN W Q, FU J ZH, XU Y ZH, et al.. Optimal sensor placement for thermal error identification of NC machine tool based on LS-SVM and genetic algorithm[J]. Opt. Precision Eng., 2008,16(9):1682-1687. (in Chinese)[11] IPLIKCI S. Support vector machines-based generalized predictive control[J]. Journal of Robust and Nonlinear Control, 2006,16(17):843-862.[12] WU H L, NG J K, KARL R, et al.. Location estimation via support vector regression [J]. Mobile Computing, 2007,6(3):311-321.[13] 周松斌. 基于SVR回归建模的无线传感器网络定位理论和算法 . 广州: 华南理工大学, 2008. ZHOU S B. WSN localization theory and method based on SVR regression modeling . Guangzhou: South China Univ. of Technology, 2008.[14] ZHANG M G, LI Z M, LI W H. Study on least squares support vector machines algorithm and its application . Proc. of International Conference on Tools with Artificial Intelligence, Hong Kong, China, 2005: 686-688.[15] JIA Y F, DONG T L, SHI J. Analysis on energy cost for wireless sensor networks . Proc. of Second International Conference on Embedded Software and Systems, Xian, China, 2005: 144-151.

浏览量

505

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

利用最小二乘支持向量机实现无线传感器网络的目标定位