On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition

Yeqin Li; David Chieng; Boon Giin Lee; Chiew Foong Kwong; Chenyu Yang

doi:10.1109/CSCN60443.2023.10453177

On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition

Yeqin Li, David Chieng, Boon Giin Lee, Chiew Foong Kwong, Chenyu Yang

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

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.

Original language	English
Title of host publication	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	417-422
Number of pages	6
ISBN (Electronic)	9798350395389
DOIs	https://doi.org/10.1109/CSCN60443.2023.10453177
Publication status	Published - 2023
Event	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023 - Munich, Germany Duration: 6 Nov 2023 → 8 Nov 2023

Publication series

Name	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023

Conference

Conference	2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023
Country/Territory	Germany
City	Munich
Period	6/11/23 → 8/11/23

Keywords

auto-correlation function
human activity recognition
IEEE 802.11 WLAN/Wi-Fi sensing
lightweight FCNN

ASJC Scopus subject areas

Computer Networks and Communications
Hardware and Architecture
Safety, Risk, Reliability and Quality

Access to Document

10.1109/CSCN60443.2023.10453177

Cite this

Li, Y., Chieng, D., Lee, B. G., Kwong, C. F., & Yang, C. (2023). On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition. In 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023 (pp. 417-422). (2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCN60443.2023.10453177

@inproceedings{ea1278596a51445796e0cd453a758e02,

title = "On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition",

abstract = "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.",

keywords = "auto-correlation function, human activity recognition, IEEE 802.11 WLAN/Wi-Fi sensing, lightweight FCNN",

author = "Yeqin Li and David Chieng and Lee, {Boon Giin} and Kwong, {Chiew Foong} and Chenyu Yang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023 ; Conference date: 06-11-2023 Through 08-11-2023",

year = "2023",

doi = "10.1109/CSCN60443.2023.10453177",

language = "English",

series = "2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023",

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

pages = "417--422",

booktitle = "2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023",

address = "United States",

}

Li, Y , Chieng, D , Lee, BG , Kwong, CF & Yang, C 2023, On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition. in 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023. 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023, Institute of Electrical and Electronics Engineers Inc., pp. 417-422, 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023, Munich, Germany, 6/11/23. https://doi.org/10.1109/CSCN60443.2023.10453177

On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition. / Li, Yeqin ; Chieng, David ; Lee, Boon Giin et al.
2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 417-422 (2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023).

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

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

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 -

Li Y , Chieng D , Lee BG , Kwong CF , Yang C. On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition. In 2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 417-422. (2023 IEEE Conference on Standards for Communications and Networking, CSCN 2023). doi: 10.1109/CSCN60443.2023.10453177

On Robustness of IEEE 802.11 WLAN-based Human Activity Recognition

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this