Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar

Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this p...

Full description

Saved in:
Bibliographic Details
Main Authors: Yukun Gao, Lin Cao, Zongmin Zhao, Dongfeng Wang, Chong Fu, Yanan Guo
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/1/197
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1841548957162930176
author Yukun Gao
Lin Cao
Zongmin Zhao
Dongfeng Wang
Chong Fu
Yanan Guo
author_facet Yukun Gao
Lin Cao
Zongmin Zhao
Dongfeng Wang
Chong Fu
Yanan Guo
author_sort Yukun Gao
collection DOAJ
description Human activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks. Firstly, an MRW image encoder is used to extract salient feature representations from all time-Doppler images through contrastive learning. This can extract the representative vector of each image and also obtain the pre-training parameters of the MRW image encoder. During the pre-training process, large-scale residual networks, medium-scale residual networks, and small-scale residual networks are used to extract global information, texture information, and semantic information, respectively. Moreover, the time–channel weighting mechanism can allocate weights to important time and channel dimensions to achieve more effective extraction of feature information. The model parameters obtained from pre-training are frozen, and the classifier is added to the backend. Finally, the classifier is fine-tuned using a small amount of labeled data. In addition, we constructed a new dataset with eight dangerous activities. The proposed MRW-CN model was trained on this dataset and achieved a classification accuracy of 96.9%. We demonstrated that our method achieves state-of-the-art performance. The ablation analysis also demonstrated the role of multi-scale convolutional kernels and time–channel weighting mechanisms in classification.
format Article
id doaj-art-ed9dd4a820bc415e99c5cd72a4b9f6c8
institution Kabale University
issn 1424-8220
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-ed9dd4a820bc415e99c5cd72a4b9f6c82025-01-10T13:21:13ZengMDPI AGSensors1424-82202025-01-0125119710.3390/s25010197Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave RadarYukun Gao0Lin Cao1Zongmin Zhao2Dongfeng Wang3Chong Fu4Yanan Guo5School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, ChinaSchool of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, ChinaSchool of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, ChinaBeijing TransMicrowave Technology Company, Beijing 100080, ChinaSchool of Computer Science and Engineering, Northeastern University, Shenyang 110169, ChinaSchool of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, ChinaHuman activity recognition by radar sensors plays an important role in healthcare and smart homes. However, labeling a large number of radar datasets is difficult and time-consuming, and it is difficult for models trained on insufficient labeled data to obtain exact classification results. In this paper, we propose a multiscale residual weighted classification network with large-scale, medium-scale, and small-scale residual networks. Firstly, an MRW image encoder is used to extract salient feature representations from all time-Doppler images through contrastive learning. This can extract the representative vector of each image and also obtain the pre-training parameters of the MRW image encoder. During the pre-training process, large-scale residual networks, medium-scale residual networks, and small-scale residual networks are used to extract global information, texture information, and semantic information, respectively. Moreover, the time–channel weighting mechanism can allocate weights to important time and channel dimensions to achieve more effective extraction of feature information. The model parameters obtained from pre-training are frozen, and the classifier is added to the backend. Finally, the classifier is fine-tuned using a small amount of labeled data. In addition, we constructed a new dataset with eight dangerous activities. The proposed MRW-CN model was trained on this dataset and achieved a classification accuracy of 96.9%. We demonstrated that our method achieves state-of-the-art performance. The ablation analysis also demonstrated the role of multi-scale convolutional kernels and time–channel weighting mechanisms in classification.https://www.mdpi.com/1424-8220/25/1/197deep learning (DL)human activity recognition (HAR)contrastive learningradar micro-Doppler signaturestime-Doppler images
spellingShingle Yukun Gao
Lin Cao
Zongmin Zhao
Dongfeng Wang
Chong Fu
Yanan Guo
Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
Sensors
deep learning (DL)
human activity recognition (HAR)
contrastive learning
radar micro-Doppler signatures
time-Doppler images
title Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
title_full Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
title_fullStr Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
title_full_unstemmed Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
title_short Multiscale Residual Weighted Classification Network for Human Activity Recognition in Microwave Radar
title_sort multiscale residual weighted classification network for human activity recognition in microwave radar
topic deep learning (DL)
human activity recognition (HAR)
contrastive learning
radar micro-Doppler signatures
time-Doppler images
url https://www.mdpi.com/1424-8220/25/1/197
work_keys_str_mv AT yukungao multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar
AT lincao multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar
AT zongminzhao multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar
AT dongfengwang multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar
AT chongfu multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar
AT yananguo multiscaleresidualweightedclassificationnetworkforhumanactivityrecognitioninmicrowaveradar