TY - GEN
T1 - On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition
AU - Li, Yeqin
AU - Chieng, David
AU - Lee, Boon Giin
AU - Kwong, Chiew Foong
AU - Yang, Chenyu
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Contact-less or Device-less Human Activity Recognition (HAR) using IEEE 802.11 Wireless Local Area Network (WLAN) has garnered significant interest due to its ubiquitous coverage, convenience, and privacy compared to wearable and vision-based approaches. However, maintaining the accuracy of HAR in varying environments, ranges, and time periods remains a challenge. This work proposes a robust scheme using threshold segmentation, auto-correlation function (ACF), and a lightweight fully connected neural network (FCNN), which can maintain the HAR accuracy across different environments without the need to retrain the model. The proposed scheme is also evaluated across different transceivers' ranges to understand its deployment constraints. The results demonstrate that the proposed scheme delivers consistent performance across different environments, ranges, and days, achieving an average HAR accuracy of over 97.25% without retraining. This greatly reduces the deployment complexity and enhances its practicality.
AB - Contact-less or Device-less Human Activity Recognition (HAR) using IEEE 802.11 Wireless Local Area Network (WLAN) has garnered significant interest due to its ubiquitous coverage, convenience, and privacy compared to wearable and vision-based approaches. However, maintaining the accuracy of HAR in varying environments, ranges, and time periods remains a challenge. This work proposes a robust scheme using threshold segmentation, auto-correlation function (ACF), and a lightweight fully connected neural network (FCNN), which can maintain the HAR accuracy across different environments without the need to retrain the model. The proposed scheme is also evaluated across different transceivers' ranges to understand its deployment constraints. The results demonstrate that the proposed scheme delivers consistent performance across different environments, ranges, and days, achieving an average HAR accuracy of over 97.25% without retraining. This greatly reduces the deployment complexity and enhances its practicality.
KW - auto-correlation function
KW - human activity recognition
KW - IEEE 802.11 WLAN/Wi-Fi sensing
KW - lightweight FCNN
UR - http://www.scopus.com/inward/record.url?scp=85187791991&partnerID=8YFLogxK
U2 - 10.1109/CSCN60443.2023.10453177
DO - 10.1109/CSCN60443.2023.10453177
M3 - Conference contribution
AN - SCOPUS:85187791991
T3 - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
SP - 417
EP - 422
BT - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
Y2 - 6 November 2023 through 8 November 2023
ER -