Human activity recognition with commercial WiFi signals

Chen Tian; Yue Tian; Xianling Wang; Yau Hee Kho; Zhenzhe Zhong; Wenda Li; Baiyun Xiao

doi:10.1109/access.2022.3223437

Human activity recognition with commercial WiFi signals

Chen Tian
, Yue Tian (Lead / Corresponding author)
, Xianling Wang (Lead / Corresponding author)
, Yau Hee Kho
, Zhenzhe Zhong
, Wenda Li
, Baiyun Xiao

Research output: Contribution to journal › Article › peer-review

10 Citations (Scopus)

208 Downloads (Pure)

Abstract

The next generation of mobile communication aims to extend the capabilities of traditional communication by reshaping the environment with wireless signals. The channel state information can describe the propagation characteristics in wireless communications, which is beneficial in developing wireless communication networks towards intelligent communication and wireless sensing networks. Raspberry PI with Nexmon firmware patched can extract the channel state information from WiFi signals and realize human activity recognition. However, the phase values on some carriers are susceptible to noise, resulting in phase errors after singular value decomposition. To solve this problem, a method is proposed in this paper to find the optimal phase value by dynamic time warping algorithm utilizing the property of orthogonality between amplitude and phase. In contrast to the conventional recognition strategies, the proposed optimal phase extraction method with commercial WiFi signals can further improve the accuracy of the recognition strategy
under different complicated scenarios.

Original language	English
Pages (from-to)	121580-121589
Number of pages	10
Journal	IEEE Access
Volume	10
DOIs	https://doi.org/10.1109/access.2022.3223437
Publication status	Published - 18 Nov 2022

Keywords

Wireless sensing
channel state information
WIFI
dynamic time warping

Access to Document

10.1109/access.2022.3223437Licence: CC BY-NC-ND

Final Published VersionFinal published version, 2 MBLicence: CC BY-NC-ND

Cite this

@article{618b278e13f948a88235ab24aaec4ba7,

title = "Human activity recognition with commercial WiFi signals",

abstract = "The next generation of mobile communication aims to extend the capabilities of traditional communication by reshaping the environment with wireless signals. The channel state information can describe the propagation characteristics in wireless communications, which is beneficial in developing wireless communication networks towards intelligent communication and wireless sensing networks. Raspberry PI with Nexmon firmware patched can extract the channel state information from WiFi signals and realize human activity recognition. However, the phase values on some carriers are susceptible to noise, resulting in phase errors after singular value decomposition. To solve this problem, a method is proposed in this paper to find the optimal phase value by dynamic time warping algorithm utilizing the property of orthogonality between amplitude and phase. In contrast to the conventional recognition strategies, the proposed optimal phase extraction method with commercial WiFi signals can further improve the accuracy of the recognition strategy under different complicated scenarios.",

keywords = "Wireless sensing, channel state information, WIFI, dynamic time warping",

author = "Chen Tian and Yue Tian and Xianling Wang and Kho, \{Yau Hee\} and Zhenzhe Zhong and Wenda Li and Baiyun Xiao",

year = "2022",

month = nov,

day = "18",

doi = "10.1109/access.2022.3223437",

language = "English",

volume = "10",

pages = "121580--121589",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Human activity recognition with commercial WiFi signals

AU - Tian, Chen

AU - Tian, Yue

AU - Wang, Xianling

AU - Kho, Yau Hee

AU - Zhong, Zhenzhe

AU - Li, Wenda

AU - Xiao, Baiyun

PY - 2022/11/18

Y1 - 2022/11/18

N2 - The next generation of mobile communication aims to extend the capabilities of traditional communication by reshaping the environment with wireless signals. The channel state information can describe the propagation characteristics in wireless communications, which is beneficial in developing wireless communication networks towards intelligent communication and wireless sensing networks. Raspberry PI with Nexmon firmware patched can extract the channel state information from WiFi signals and realize human activity recognition. However, the phase values on some carriers are susceptible to noise, resulting in phase errors after singular value decomposition. To solve this problem, a method is proposed in this paper to find the optimal phase value by dynamic time warping algorithm utilizing the property of orthogonality between amplitude and phase. In contrast to the conventional recognition strategies, the proposed optimal phase extraction method with commercial WiFi signals can further improve the accuracy of the recognition strategy under different complicated scenarios.

AB - The next generation of mobile communication aims to extend the capabilities of traditional communication by reshaping the environment with wireless signals. The channel state information can describe the propagation characteristics in wireless communications, which is beneficial in developing wireless communication networks towards intelligent communication and wireless sensing networks. Raspberry PI with Nexmon firmware patched can extract the channel state information from WiFi signals and realize human activity recognition. However, the phase values on some carriers are susceptible to noise, resulting in phase errors after singular value decomposition. To solve this problem, a method is proposed in this paper to find the optimal phase value by dynamic time warping algorithm utilizing the property of orthogonality between amplitude and phase. In contrast to the conventional recognition strategies, the proposed optimal phase extraction method with commercial WiFi signals can further improve the accuracy of the recognition strategy under different complicated scenarios.

KW - Wireless sensing

KW - channel state information

KW - WIFI

KW - dynamic time warping

U2 - 10.1109/access.2022.3223437

DO - 10.1109/access.2022.3223437

M3 - Article

SN - 2169-3536

VL - 10

SP - 121580

EP - 121589

JO - IEEE Access

JF - IEEE Access

ER -

Human activity recognition with commercial WiFi signals

Abstract

Keywords

Access to Document

Fingerprint

Cite this