25 October 2016 WiFi-based person identification
Author Affiliations +
Proceedings Volume 10158, Optical Communication, Optical Fiber Sensors, and Optical Memories for Big Data Storage; 101580I (2016) https://doi.org/10.1117/12.2245812
Event: International Symposium on Optoelectronic Technology and Application 2016, 2016, Beijing, China
Abstract
There has been increased interest in WIFI devices equipped with multiple antennas, which brings various wireless sensing applications such as localization, gesture identification and motion tracking. WIFI-based sensing has a lot of benefits such as device Free, which has shown great potential in smart scenarios. In this paper, we present WIP, a system that can distinguish a person from a small group of people. We prove that Channel State Information (CSI) can identify a person’s gait. From the related-work, different people have different gait features. Thus the CSI-based gait features can be used to identify a person. We then proposed a machine-learning model-ANN to classify different person. The results show that ANN has a good performance in our scenario.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jing Yuan, Jing Yuan, } " WiFi-based person identification", Proc. SPIE 10158, Optical Communication, Optical Fiber Sensors, and Optical Memories for Big Data Storage, 101580I (25 October 2016); doi: 10.1117/12.2245812; https://doi.org/10.1117/12.2245812
PROCEEDINGS
7 PAGES


SHARE
Back to Top