VBCNet: A Hybird Network for Human Activity Recognition

In recent years, the research on human activity recognition based on channel state information (CSI) of Wi-Fi has gradually attracted much attention in order to avoid the deployment of additional devices and reduce the risk of personal privacy leakage. In this paper, we propose a hybrid network arch...

Full description

Saved in:
Bibliographic Details
Main Authors: Fei Ge, Zhenyang Dai, Zhimin Yang, Fei Wu, Liansheng Tan
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/23/7793
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850060300985827328
author Fei Ge
Zhenyang Dai
Zhimin Yang
Fei Wu
Liansheng Tan
author_facet Fei Ge
Zhenyang Dai
Zhimin Yang
Fei Wu
Liansheng Tan
author_sort Fei Ge
collection DOAJ
description In recent years, the research on human activity recognition based on channel state information (CSI) of Wi-Fi has gradually attracted much attention in order to avoid the deployment of additional devices and reduce the risk of personal privacy leakage. In this paper, we propose a hybrid network architecture, named VBCNet, that can effectively identify human activity postures. Firstly, we extract CSI sequences from each antenna of Wi-Fi signals, and the data are preprocessed and tokenised. Then, in the encoder part of the model, we introduce a layer of long short-term memory network to further extract the temporal features in the sequences and enhance the ability of the model to capture the temporal information. Meanwhile, VBCNet employs a convolutional feed-forward network instead of the traditional feed-forward network to enhance the model’s ability to process local and multi-scale features. Finally, the model classifies the extracted features into human behaviours through a classification layer. To validate the effectiveness of VBCNet, we conducted experimental evaluations on the classical human activity recognition datasets UT-HAR and Widar3.0 and achieved an accuracy of 98.65% and 77.92%. These results show that VBCNet exhibits extremely high effectiveness and robustness in human activity recognition tasks in complex scenarios.
format Article
id doaj-art-708c82db24dc4df2a6ada1356b30cf84
institution DOAJ
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-708c82db24dc4df2a6ada1356b30cf842025-08-20T02:50:37ZengMDPI AGSensors1424-82202024-12-012423779310.3390/s24237793VBCNet: A Hybird Network for Human Activity RecognitionFei Ge0Zhenyang Dai1Zhimin Yang2Fei Wu3Liansheng Tan4School of Computer Science, Central China Normal University, Wuhan 430070, ChinaSchool of Computer Science, Central China Normal University, Wuhan 430070, ChinaSchool of Computer Science, Central China Normal University, Wuhan 430070, ChinaSchool of Computer Science, Central China Normal University, Wuhan 430070, ChinaSchool of Computer Science, Central China Normal University, Wuhan 430070, ChinaIn recent years, the research on human activity recognition based on channel state information (CSI) of Wi-Fi has gradually attracted much attention in order to avoid the deployment of additional devices and reduce the risk of personal privacy leakage. In this paper, we propose a hybrid network architecture, named VBCNet, that can effectively identify human activity postures. Firstly, we extract CSI sequences from each antenna of Wi-Fi signals, and the data are preprocessed and tokenised. Then, in the encoder part of the model, we introduce a layer of long short-term memory network to further extract the temporal features in the sequences and enhance the ability of the model to capture the temporal information. Meanwhile, VBCNet employs a convolutional feed-forward network instead of the traditional feed-forward network to enhance the model’s ability to process local and multi-scale features. Finally, the model classifies the extracted features into human behaviours through a classification layer. To validate the effectiveness of VBCNet, we conducted experimental evaluations on the classical human activity recognition datasets UT-HAR and Widar3.0 and achieved an accuracy of 98.65% and 77.92%. These results show that VBCNet exhibits extremely high effectiveness and robustness in human activity recognition tasks in complex scenarios.https://www.mdpi.com/1424-8220/24/23/7793Wi-Fi channel state informationbody-coordinate velocity profileViTBiLSTMconvolutional feed-forward
spellingShingle Fei Ge
Zhenyang Dai
Zhimin Yang
Fei Wu
Liansheng Tan
VBCNet: A Hybird Network for Human Activity Recognition
Sensors
Wi-Fi channel state information
body-coordinate velocity profile
ViT
BiLSTM
convolutional feed-forward
title VBCNet: A Hybird Network for Human Activity Recognition
title_full VBCNet: A Hybird Network for Human Activity Recognition
title_fullStr VBCNet: A Hybird Network for Human Activity Recognition
title_full_unstemmed VBCNet: A Hybird Network for Human Activity Recognition
title_short VBCNet: A Hybird Network for Human Activity Recognition
title_sort vbcnet a hybird network for human activity recognition
topic Wi-Fi channel state information
body-coordinate velocity profile
ViT
BiLSTM
convolutional feed-forward
url https://www.mdpi.com/1424-8220/24/23/7793
work_keys_str_mv AT feige vbcnetahybirdnetworkforhumanactivityrecognition
AT zhenyangdai vbcnetahybirdnetworkforhumanactivityrecognition
AT zhiminyang vbcnetahybirdnetworkforhumanactivityrecognition
AT feiwu vbcnetahybirdnetworkforhumanactivityrecognition
AT lianshengtan vbcnetahybirdnetworkforhumanactivityrecognition