计算机技术与发展2018，Vol.28Issue(5)：86-89,4.DOI:10.3969/j.issn.1673-629X.2018.05.020
无线感知网络中动作识别的滤波算法
Filtering Algorithm for Motion Recognition in Wireless Sensor Networks
摘要
Abstract
Recently,the human activity recognition systems based on WiFi have been proposed.Their common characteristic is to use the CSI (channel state information) which is the information of the 30 subcarriers running under the 802.11 protocol,and as the sampling of the frequency response of the channel state information at some point,is the mathematical expression of multipath effect to a certain ex-tent.However,even in a static environment,CSI values in WiFi signals fluctuate because WiFi devices are susceptible to surrounding elec-tromagnetic noises.General denoising methods,such as low-pass filters or mean filters,do not perform well in removing these impulse and bursty noises.For this,we propose a method combines the low pass filter and principal component analysis simultaneously,removing the noise in the CSI,while reducing the dimension of the CSI data and improving the efficiency of the system.Experiments show that the extracted features of the PCA method are more obvious than that of the traditional methods,which greatly enhance the accuracy and preci-sion of the recognition system.关键词
信道状态信息/主成分分析/低通滤波/均值滤波Key words
channel state information/principal component analysis/low pass filter/mean filter分类
信息技术与安全科学引用本文复制引用
吴春香,张建明..无线感知网络中动作识别的滤波算法[J].计算机技术与发展,2018,28(5):86-89,4.基金项目
江苏省自然科学基金(BK2011789) （BK2011789）
