Cargando…

Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network

This paper proposes a human activity recognition (HAR) method for frequency-modulated continuous wave (FMCW) radar sensors. The method utilizes a multi-domain feature attention fusion network (MFAFN) model that addresses the limitation of relying on a single range or velocity feature to describe hum...

Descripción completa

Detalles Bibliográficos
Autores principales: Cao, Lin, Liang, Song, Zhao, Zongmin, Wang, Dongfeng, Fu, Chong, Du, Kangning
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10255355/
https://www.ncbi.nlm.nih.gov/pubmed/37299830
http://dx.doi.org/10.3390/s23115100
_version_ 1785056851373588480
author Cao, Lin
Liang, Song
Zhao, Zongmin
Wang, Dongfeng
Fu, Chong
Du, Kangning
author_facet Cao, Lin
Liang, Song
Zhao, Zongmin
Wang, Dongfeng
Fu, Chong
Du, Kangning
author_sort Cao, Lin
collection PubMed
description This paper proposes a human activity recognition (HAR) method for frequency-modulated continuous wave (FMCW) radar sensors. The method utilizes a multi-domain feature attention fusion network (MFAFN) model that addresses the limitation of relying on a single range or velocity feature to describe human activity. Specifically, the network fuses time-Doppler (TD) and time-range (TR) maps of human activities, resulting in a more comprehensive representation of the activities being performed. In the feature fusion phase, the multi-feature attention fusion module (MAFM) combines features of different depth levels by introducing a channel attention mechanism. Additionally, a multi-classification focus loss (MFL) function is applied to classify confusable samples. The experimental results demonstrate that the proposed method achieves 97.58% recognition accuracy on the dataset provided by the University of Glasgow, UK. Compared to existing HAR methods for the same dataset, the proposed method showed an improvement of about 0.9–5.5%, especially in the classification of confusable activities, showing an improvement of up to 18.33%.
format Online
Article
Text
id pubmed-10255355
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102553552023-06-10 Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network Cao, Lin Liang, Song Zhao, Zongmin Wang, Dongfeng Fu, Chong Du, Kangning Sensors (Basel) Article This paper proposes a human activity recognition (HAR) method for frequency-modulated continuous wave (FMCW) radar sensors. The method utilizes a multi-domain feature attention fusion network (MFAFN) model that addresses the limitation of relying on a single range or velocity feature to describe human activity. Specifically, the network fuses time-Doppler (TD) and time-range (TR) maps of human activities, resulting in a more comprehensive representation of the activities being performed. In the feature fusion phase, the multi-feature attention fusion module (MAFM) combines features of different depth levels by introducing a channel attention mechanism. Additionally, a multi-classification focus loss (MFL) function is applied to classify confusable samples. The experimental results demonstrate that the proposed method achieves 97.58% recognition accuracy on the dataset provided by the University of Glasgow, UK. Compared to existing HAR methods for the same dataset, the proposed method showed an improvement of about 0.9–5.5%, especially in the classification of confusable activities, showing an improvement of up to 18.33%. MDPI 2023-05-26 /pmc/articles/PMC10255355/ /pubmed/37299830 http://dx.doi.org/10.3390/s23115100 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cao, Lin
Liang, Song
Zhao, Zongmin
Wang, Dongfeng
Fu, Chong
Du, Kangning
Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title_full Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title_fullStr Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title_full_unstemmed Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title_short Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network
title_sort human activity recognition method based on fmcw radar sensor with multi-domain feature attention fusion network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10255355/
https://www.ncbi.nlm.nih.gov/pubmed/37299830
http://dx.doi.org/10.3390/s23115100
work_keys_str_mv AT caolin humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork
AT liangsong humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork
AT zhaozongmin humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork
AT wangdongfeng humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork
AT fuchong humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork
AT dukangning humanactivityrecognitionmethodbasedonfmcwradarsensorwithmultidomainfeatureattentionfusionnetwork