Wi-Wheat+:Contact-free wheat moisture sensing with commodity WiFi based on entropy

作     者：Weidong Yang Erbo Shen Xuyu Wang Shiwen Mao Yuehong Gong Pengming Hu Weidong Yang;Erbo Shen;Xuyu Wang;Shiwen Mao;Yuehong Gong;Pengming Hu

作者机构：College of Information Science and EngineeringHenan University of TechnologyZhengzhou450001China Henan Key Laboratory of Grain Photoelectric Detection and ControlZhengzhou450001China College of International EducationKaifeng UniversityKaifengHenan475004China Knight Foundation School of Computing&Information SciencesFlorida International UniversityMiamiFL33199USA Department of Electrical and Computer EngineeringAuburn UniversityAuburnAL36849-5201USA 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2023年第9卷第3期

页      面：698-709页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081001[工学-通信与信息系统] 

基　　金：supported in part by the Program for Science&Technology Innovation Talents in Universities of Henan Province(19HASTIT027) National Natural Science Foundation of China(62172141) Zhengzhou Major Scientific and Technological Innovation Project(2019CXZX0086) Youth Innovative Talents Cultivation Fund Project of Kaifeng University in 2020(KDQN-2020-GK002) the National Key Research and Development Program of China(2017YFD0401001) the NSFC(61741107),the NSF(CNS-2105416) by the Wireless Engineering Research and Education Center at Auburn University 

主　　题：Channel state information(CSI) WiFi Multi-scale entropy Multi-class support vector machine(SVM) Radio frequency(RF)sensing 

摘      要：In this paper,we propose a contact-free wheat moisture monitoring system,termed Wi-Wheatþ,to address the several limitations of the existing grain moisture detection technologies,such as time-consuming process,expensive equipment,low accuracy,and difficulty in real-time *** proposed system is based on Commodity WiFi and is easy to *** WiFi CSI data,this paper proposes a feature extraction method based on multi-scale and multi-channel *** feasibility and stability of the system are validated through experiments in both Line-Of-Sight(LOS)and Non-Line-Of-Sight(NLOS)scenarios,where ten types of wheat moisture content are tested using multi-class Support Vector Machine(SVM).Compared with the Wi-Wheat system proposed in our prior work,Wi-Wheatþhas higher efficiency,requiring only a simple training process,and can sense more wheat moisture content levels.