Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention

Jaekwon Lee; Lu Zhang; Donghyun Kim; Kar Ann Toh

doi:10.1109/ISCAS58744.2024.10558208

Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention

Jaekwon Lee, Lu Zhang, Donghyun Kim, Kar Ann Toh

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we construct a network for human activity recognition based on the tokenized Wi-Fi signals on an attention mechanism. After standardizing the signals, the WiFi channel state information is utilized as a set of time-series data, acknowledging its inherent temporal structure. Motivated by the Transformer's ability to model temporal dependencies, the construction is enriched with a frequency-based tokenization scheme. This unique construction is adept at managing noise and sensitivity intrinsic to Wi-Fi signals, effectively mitigating the challenges in Wi-Fi-based human activity recognition. Our experimental evaluations validated the effectiveness of the proposed structure.

Original language	English
Title of host publication	ISCAS 2024 - IEEE International Symposium on Circuits and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350330991
DOIs	https://doi.org/10.1109/ISCAS58744.2024.10558208
Publication status	Published - 2024
Event	2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024 - Singapore, Singapore Duration: 2024 May 19 → 2024 May 22

Publication series

Name	Proceedings - IEEE International Symposium on Circuits and Systems
ISSN (Print)	0271-4310

Conference

Conference	2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024
Country/Territory	Singapore
City	Singapore
Period	24/5/19 → 24/5/22

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

All Science Journal Classification (ASJC) codes

Electrical and Electronic Engineering

Access to Document

10.1109/ISCAS58744.2024.10558208

Cite this

Lee, J., Zhang, L., Kim, D., & Toh, K. A. (2024). Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention. In ISCAS 2024 - IEEE International Symposium on Circuits and Systems (Proceedings - IEEE International Symposium on Circuits and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCAS58744.2024.10558208

@inproceedings{6cdfb34b0e584384aaaedd316e837ca2,

title = "Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention",

abstract = "In this paper, we construct a network for human activity recognition based on the tokenized Wi-Fi signals on an attention mechanism. After standardizing the signals, the WiFi channel state information is utilized as a set of time-series data, acknowledging its inherent temporal structure. Motivated by the Transformer's ability to model temporal dependencies, the construction is enriched with a frequency-based tokenization scheme. This unique construction is adept at managing noise and sensitivity intrinsic to Wi-Fi signals, effectively mitigating the challenges in Wi-Fi-based human activity recognition. Our experimental evaluations validated the effectiveness of the proposed structure.",

keywords = "Human activity recognition, Time-series classification, Transformer encoder, Wi-Fi channel state information signal",

author = "Jaekwon Lee and Lu Zhang and Donghyun Kim and Toh, {Kar Ann}",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024 ; Conference date: 19-05-2024 Through 22-05-2024",

year = "2024",

doi = "10.1109/ISCAS58744.2024.10558208",

language = "English",

series = "Proceedings - IEEE International Symposium on Circuits and Systems",

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

booktitle = "ISCAS 2024 - IEEE International Symposium on Circuits and Systems",

address = "United States",

}

Lee, J, Zhang, L, Kim, D & Toh, KA 2024, Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention. in ISCAS 2024 - IEEE International Symposium on Circuits and Systems. Proceedings - IEEE International Symposium on Circuits and Systems, Institute of Electrical and Electronics Engineers Inc., 2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024, Singapore, Singapore, 24/5/19. https://doi.org/10.1109/ISCAS58744.2024.10558208

Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention. / Lee, Jaekwon; Zhang, Lu; Kim, Donghyun et al.
ISCAS 2024 - IEEE International Symposium on Circuits and Systems. Institute of Electrical and Electronics Engineers Inc., 2024. (Proceedings - IEEE International Symposium on Circuits and Systems).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention

AU - Lee, Jaekwon

AU - Zhang, Lu

AU - Kim, Donghyun

AU - Toh, Kar Ann

PY - 2024

Y1 - 2024

N2 - In this paper, we construct a network for human activity recognition based on the tokenized Wi-Fi signals on an attention mechanism. After standardizing the signals, the WiFi channel state information is utilized as a set of time-series data, acknowledging its inherent temporal structure. Motivated by the Transformer's ability to model temporal dependencies, the construction is enriched with a frequency-based tokenization scheme. This unique construction is adept at managing noise and sensitivity intrinsic to Wi-Fi signals, effectively mitigating the challenges in Wi-Fi-based human activity recognition. Our experimental evaluations validated the effectiveness of the proposed structure.

AB - In this paper, we construct a network for human activity recognition based on the tokenized Wi-Fi signals on an attention mechanism. After standardizing the signals, the WiFi channel state information is utilized as a set of time-series data, acknowledging its inherent temporal structure. Motivated by the Transformer's ability to model temporal dependencies, the construction is enriched with a frequency-based tokenization scheme. This unique construction is adept at managing noise and sensitivity intrinsic to Wi-Fi signals, effectively mitigating the challenges in Wi-Fi-based human activity recognition. Our experimental evaluations validated the effectiveness of the proposed structure.

KW - Human activity recognition

KW - Time-series classification

KW - Transformer encoder

KW - Wi-Fi channel state information signal

UR - http://www.scopus.com/inward/record.url?scp=85198511125&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85198511125&partnerID=8YFLogxK

U2 - 10.1109/ISCAS58744.2024.10558208

DO - 10.1109/ISCAS58744.2024.10558208

M3 - Conference contribution

AN - SCOPUS:85198511125

T3 - Proceedings - IEEE International Symposium on Circuits and Systems

BT - ISCAS 2024 - IEEE International Symposium on Circuits and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2024 IEEE International Symposium on Circuits and Systems, ISCAS 2024

Y2 - 19 May 2024 through 22 May 2024

ER -

Human Activity Recognition Using Wi-Fi Signals based on Tokenized Signals with Attention

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this