摘要
针对无源目标分类系统中精度和费用之间不平衡、采用手工提取特征的方法进行特征提取工作量较大的问题,提出了一种基于误差逆传播(BP)神经网络的信道状态信息(CSI)无源目标分类方法.通过提取WiFi信号的CSI作基信号,并结合具有自主学习数据特征能力的神经网络方法,设计了BP神经网络的训练模型,减少了手工提取特征带来的开销.实验结果表明,以身高分类为例,所提方法能够区分4个不同身高段,且平均分类准确度可以达到90%以上.
Aim at the imbalance between accuracy and expense,the heavy workload of manually extracting features in current device-free target classification systems,a channel state information(CSI)device-free target classification method based on error back propagation(BP)neural network is proposed.By extracting the CSI of the WiFi signal as the base signal and combining the neural network method with the characteristic of autonomous learning data features,the BP neural network training model is designed,which reduces the overhead caused by the manual extraction feature.Taking the height classification as an example,an experiment is carried out,and it is shown that the proposed method can distinguish four different height segments,and the average classification accuracy can reach more than 90%.
作者
蒋芳
张南飞
胡艳军
王翊
JIANG Fang;ZHANG Nan-fei;HU Yan-jun;WANG Yi(Key Laboratory of Intelligent Computing and Signal Processing(Anhui University),Ministry of Education,Hefei 230601,China)
出处
《北京邮电大学学报》
EI
CAS
CSCD
北大核心
2020年第1期40-45,共6页
Journal of Beijing University of Posts and Telecommunications
基金
国家自然科学基金项目(61501002)
安徽省高等学校自然科学研究项目(KJ2018A0019)
安徽大学博士科研启动基金项目.
关键词
信道状态信息
误差逆传播神经网络
无源目标分类
channel state information
error back propagation neural network
device-free target classification
