基于改进的PSO-SVM室内走廊环境WSN信道建模  

WSN Channel Modeling of Indoor Corridor Environment Based on Improved PSO-SVM

作　　者：祁恩召 李春树 QI En-zhao;LI Chun-shu(School of Physics and Electronic-Electrical Engineering,Ningxia University,Yinchuan Ningxia 750021,China;Ningxia Key Laboratory of Intelligent Sensing for Desert Information,Yinchuan Ningxia 750021,China)

机构地区：[1]宁夏大学物理与电子电气工程学院,宁夏银川750021 [2]宁夏沙漠信息智能感知重点实验室,宁夏银川750021

出　　处：《计算机仿真》2020年第2期323-328,共6页Computer Simulation

基　　金：宁夏自然科学基金(NZ17051);宁夏大学研究生创新项目资助(GIP2018074)。

摘　　要：随着无线传感器在室内的应用越来越普及,无线传感器网络(WSN)室内信道模型的研究成为了通信行业的一个热点。针对室内走廊环境进行了无线传感器网络的信号传输衰落特性测试,并根据测试所得数据利用粒子群算法优化支持向量机(PSO-SVM)进行了数据回归分析,通过选取交叉验证折数来提高精度,建立了PSO-SVM无线电波路径损耗模型。模型与双折线对数距离路径损耗模型进行对比分析,实验结果表明PSO-SVM模型预测精度优于双折线对数距离路径损耗模型,能很好的表征室内走廊环境下的WSN电波衰落特性。Wireless sensor is more and more widely used in the indoor environment,the research of wireless sensor network channel indoor model has become a hot spot in the communications industry.Therefore,for the indoor corridor environments,the fading characteristics of channel transmission for wireless sensor network are tested,and regression analysis of the testing data is carried out by support vector machine combined with particle swarm algorithm optimization(PSO-SVM),and by selecting folds of cross validation to improve precision,the PSO-SVM radio wave path loss model is established.The model is compared and evaluated with two-slope log-distance model,the results show that the PSO-SVM model has better accuracy,and can well characterize the WSN wave fading characteristics in the indoor corridor environment.

关 键 词：无线传感器 走廊环境 粒子群 支持向量机 交叉验证 衰落特性 

分 类 号：N945.12[自然科学总论—系统科学]