基于支持向量机的无线传感器网络分布式检测  

Support vector machine based distributed detection in wireless sensor networks

作　　者：王莹[1] 尹莉萍[1] 岳殿武[1,2] 何荣希[1] 

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026 [2]东南大学移动通信国家重点实验室,南京210096

出　　处：《大连海事大学学报》2009年第2期68-71,共4页Journal of Dalian Maritime University

基　　金：辽宁省教育厅科技研究项目(2008S024);辽宁省自然科学基金资助项目(20082142);东南大学移动通信国家重点实验室开放研究基金资助项目(W200810)

摘　　要：为减少基于似然比检测的无线传感器网络最优分布式检测方法对信道状态、噪声分布和传感器检测性能等信息的依赖,满足实际系统的需要,提出使用支持向量机实现无线传感器网络分布式信号检测的方法.该方法无需预知信道状态和噪声分布信息,简化了无线传感器的节点功能.该方法将传感器节点测量结果以模拟非编码方式发送至数据中心,数据中心利用训练好的支持向量机对接收到的信号进行判决.仿真结果表明,该方法可获得较高的检测精度.The likelihood ratio test based optimal distributed detection in wireless sensor networks requires information about the channel state, noise distribution and sensors＇ detection performance, which can hardly meet the requirements of the practical applications. Support vector machine（SVM） was adopted to perform distributed detection in wireless sensor networks without knowing the channel state and noise distribution information, therefore the function of the wireless sensor node can be simplified. Each sensor node transmits an amplified version of its measurement to the data fusion center, and the data fusion center makes a final decision by means of a well trained SVM. Simulation results show that the SVM based distributed detection method in wireless sensor network has a very high detection performance.

关 键 词：无线传感器网络 分布式检测 支持向量机(SVM) 似然比检验 

分 类 号：TN911.7[电子电信—通信与信息系统]