A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection

Xin Wen; Xinran Song; Zhi Zheng; Bo Wang; Yongxin Guo

doi:10.1109/IMBioC52515.2022.9790259

A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection

Xin Wen
, Xinran Song
, Zhi Zheng
, Bo Wang
, Yongxin Guo^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

Nowadays, with the wide commercial use of Wi-Fi technology, the use of Wi-Fi channel state information (CSI) for fall detection has gradually become a hot research field. However, many existing fall detection systems based on Wi-Fi lack accurate action classification because of the high acquisition cost of complex action datasets. They cannot accurately identify complex fall actions, and have a high false positive rate. This paper proposes a multi-class dataset expansion method for different fall actions and non-fall actions, which classifies the movements in detail according to fall speed and other limb movements and expands the scale of the data set by dividing and reorganizing the limited data. As a result, the proposed method reaches a recognition accuracy of 91.6%. © 2022 IEEE.

Original language	English
Title of host publication	2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC)
Publisher	IEEE
Pages	195-197
ISBN (Electronic)	978-1-6654-2340-3, 978-1-6654-2339-7
ISBN (Print)	978-1-6654-2341-0
DOIs	https://doi.org/10.1109/IMBioC52515.2022.9790259
Publication status	Published - 2022
Externally published	Yes
Event	2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC 2022) - Virtual, Suzhou, China Duration: 16 May 2022 → 18 May 2022 https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9790154 https://www.nusri.cn/IMBioC2022/index.html

Publication series

Name	IEEE MTT-S International Microwave Biomedical Conference, IMBioC

Conference

Conference	2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC 2022)
Abbreviated title	IEEE IMBioC 2022
Place	China
City	Suzhou
Period	16/05/22 → 18/05/22
Internet address	https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9790154 https://www.nusri.cn/IMBioC2022/index.html

Research Keywords

channel state information
convolution neural network
fall detection
Wi-Fi

Access Output

10.1109/IMBioC52515.2022.9790259

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{bb97e82d10584cbfb3dd637ec2a85137,

title = "A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection",

abstract = "Nowadays, with the wide commercial use of Wi-Fi technology, the use of Wi-Fi channel state information (CSI) for fall detection has gradually become a hot research field. However, many existing fall detection systems based on Wi-Fi lack accurate action classification because of the high acquisition cost of complex action datasets. They cannot accurately identify complex fall actions, and have a high false positive rate. This paper proposes a multi-class dataset expansion method for different fall actions and non-fall actions, which classifies the movements in detail according to fall speed and other limb movements and expands the scale of the data set by dividing and reorganizing the limited data. As a result, the proposed method reaches a recognition accuracy of 91.6\%. {\textcopyright} 2022 IEEE.",

keywords = "channel state information, convolution neural network, fall detection, Wi-Fi",

author = "Xin Wen and Xinran Song and Zhi Zheng and Bo Wang and Yongxin Guo",

year = "2022",

doi = "10.1109/IMBioC52515.2022.9790259",

language = "English",

isbn = "978-1-6654-2341-0",

series = "IEEE MTT-S International Microwave Biomedical Conference, IMBioC",

publisher = "IEEE",

pages = "195--197",

booktitle = "2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC)",

address = "United States",

note = "2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC 2022), IEEE IMBioC 2022 ; Conference date: 16-05-2022 Through 18-05-2022",

url = "https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=\&arnumber=9790154, https://www.nusri.cn/IMBioC2022/index.html",

}

Wen, X, Song, X, Zheng, Z, Wang, B & Guo, Y 2022, A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection. in 2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC). IEEE MTT-S International Microwave Biomedical Conference, IMBioC, IEEE, pp. 195-197, 2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC 2022), Suzhou, China, 16/05/22. https://doi.org/10.1109/IMBioC52515.2022.9790259

A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection. / Wen, Xin; Song, Xinran; Zheng, Zhi et al.
2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC). IEEE, 2022. p. 195-197 (IEEE MTT-S International Microwave Biomedical Conference, IMBioC).

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection

AU - Wen, Xin

AU - Song, Xinran

AU - Zheng, Zhi

AU - Wang, Bo

AU - Guo, Yongxin

PY - 2022

Y1 - 2022

N2 - Nowadays, with the wide commercial use of Wi-Fi technology, the use of Wi-Fi channel state information (CSI) for fall detection has gradually become a hot research field. However, many existing fall detection systems based on Wi-Fi lack accurate action classification because of the high acquisition cost of complex action datasets. They cannot accurately identify complex fall actions, and have a high false positive rate. This paper proposes a multi-class dataset expansion method for different fall actions and non-fall actions, which classifies the movements in detail according to fall speed and other limb movements and expands the scale of the data set by dividing and reorganizing the limited data. As a result, the proposed method reaches a recognition accuracy of 91.6%. © 2022 IEEE.

AB - Nowadays, with the wide commercial use of Wi-Fi technology, the use of Wi-Fi channel state information (CSI) for fall detection has gradually become a hot research field. However, many existing fall detection systems based on Wi-Fi lack accurate action classification because of the high acquisition cost of complex action datasets. They cannot accurately identify complex fall actions, and have a high false positive rate. This paper proposes a multi-class dataset expansion method for different fall actions and non-fall actions, which classifies the movements in detail according to fall speed and other limb movements and expands the scale of the data set by dividing and reorganizing the limited data. As a result, the proposed method reaches a recognition accuracy of 91.6%. © 2022 IEEE.

KW - channel state information

KW - convolution neural network

KW - fall detection

KW - Wi-Fi

UR - https://www.scopus.com/pages/publications/85133127037

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85133127037&origin=recordpage

U2 - 10.1109/IMBioC52515.2022.9790259

DO - 10.1109/IMBioC52515.2022.9790259

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 978-1-6654-2341-0

T3 - IEEE MTT-S International Microwave Biomedical Conference, IMBioC

SP - 195

EP - 197

BT - 2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC)

PB - IEEE

T2 - 2022 IEEE MTT-S International Microwave Biomedical Conference (IMBioC 2022)

Y2 - 16 May 2022 through 18 May 2022

ER -

A Multi-class Dataset Expansion Method for Wi-Fi-Based Fall Detection

Abstract

Publication series

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this