Transmission range determination and antenna deployment to recognise fitness actions using Wi-Fi signals. (5th October 2022)

• Record Type: Journal Article
• Authors: Liang, Wei-Che; Chao, Chih-Min; Lin, Chih-Yu; Yeh, Chun-Chao
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 41:Number 4(2022)
• Page Start: 221
• Page End: 231
• Publication Date: 2022-10-05
• Subjects: channel state information -- CSI -- fitness action recognition -- wireless signal -- device-free sensing; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

To help users exercise effectively at home, many studies have used the radio channel state information (CSI) of Wi-Fi signals to recognise human motions. However, these studies do not address how to determine an appropriate distance between the Wi-Fi transceivers to achieve a target recognition accuracy. In this paper, we design WiFitness to recognise fitness actions and to find out the upper and lower bounds of the distance between the Wi-Fi transceivers for different fitness actions. Based on the fact that the strongest wireless signal occurs in the first Fresnel zone, WiFitness finds out the distance limit between two transceivers such that the first Fresnel zone covers the range of a particular fitness action and the required recognition accuracy of the fitness action is satisfied. Besides determining the distance limit, in WiFitness, the way to deploy the antennas are also proposed to enlarge the sensing range.