Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN

Gait recognition with wearable sensors is an effective approach to identifying people by recognizing their distinctive walking patterns. Deep learning-based networks have recently emerged as a promising technique in gait recognition, yielding better performance than template matching and traditional...

Full description

Saved in:
Bibliographic Details
Main Authors: Md. Al Mehedi Hasan, Fuad Al Abir, Md. Al Siam, Jungpil Shin
Format: Article
Language:English
Published: IEEE 2022-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/9758696/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846128604336881664
author Md. Al Mehedi Hasan
Fuad Al Abir
Md. Al Siam
Jungpil Shin
author_facet Md. Al Mehedi Hasan
Fuad Al Abir
Md. Al Siam
Jungpil Shin
author_sort Md. Al Mehedi Hasan
collection DOAJ
description Gait recognition with wearable sensors is an effective approach to identifying people by recognizing their distinctive walking patterns. Deep learning-based networks have recently emerged as a promising technique in gait recognition, yielding better performance than template matching and traditional machine learning methods. However, most recent studies have focused on improving gait detection accuracy while neglecting model complexity in the deep learning domain, making them unsuitable for low-power wearable devices. Therefore, inference from these models results in latency due to calculation overhead. This study proposes an efficient network suitable for wearable devices without sacrificing prediction performance. We have modified the residual block and accumulated it in shallow convolutional neural networks with five weighted layers only for gait recognition and proved the efficacy of all the architectural components with extensive experiments over publicly available IMU-based datasets: whuGait and OU-ISIR. Our proposed model outperforms all the state-of-the-art methods regarding recognition accuracy and is more than 85 percent efficient on average in terms of model parameters and memory consumption.
format Article
id doaj-art-575ae9a97a9d492abbb4ae9ee98e7b57
institution Kabale University
issn 2169-3536
language English
publishDate 2022-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-575ae9a97a9d492abbb4ae9ee98e7b572024-12-11T00:02:39ZengIEEEIEEE Access2169-35362022-01-0110425774258810.1109/ACCESS.2022.31680199758696Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNNMd. Al Mehedi Hasan0https://orcid.org/0000-0003-2966-7055Fuad Al Abir1https://orcid.org/0000-0002-9091-3078Md. Al Siam2Jungpil Shin3https://orcid.org/0000-0002-7476-2468School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanDepartment of Computer Science and Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshDepartment of Computer Science and Engineering, Rajshahi University of Engineering and Technology, Rajshahi, BangladeshSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Fukushima, JapanGait recognition with wearable sensors is an effective approach to identifying people by recognizing their distinctive walking patterns. Deep learning-based networks have recently emerged as a promising technique in gait recognition, yielding better performance than template matching and traditional machine learning methods. However, most recent studies have focused on improving gait detection accuracy while neglecting model complexity in the deep learning domain, making them unsuitable for low-power wearable devices. Therefore, inference from these models results in latency due to calculation overhead. This study proposes an efficient network suitable for wearable devices without sacrificing prediction performance. We have modified the residual block and accumulated it in shallow convolutional neural networks with five weighted layers only for gait recognition and proved the efficacy of all the architectural components with extensive experiments over publicly available IMU-based datasets: whuGait and OU-ISIR. Our proposed model outperforms all the state-of-the-art methods regarding recognition accuracy and is more than 85 percent efficient on average in terms of model parameters and memory consumption.https://ieeexplore.ieee.org/document/9758696/Computational efficiencygait recognitionlightweight CNNmemory-usage reductionparameter reductionresidual learning
spellingShingle Md. Al Mehedi Hasan
Fuad Al Abir
Md. Al Siam
Jungpil Shin
Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
IEEE Access
Computational efficiency
gait recognition
lightweight CNN
memory-usage reduction
parameter reduction
residual learning
title Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
title_full Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
title_fullStr Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
title_full_unstemmed Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
title_short Gait Recognition With Wearable Sensors Using Modified Residual Block-Based Lightweight CNN
title_sort gait recognition with wearable sensors using modified residual block based lightweight cnn
topic Computational efficiency
gait recognition
lightweight CNN
memory-usage reduction
parameter reduction
residual learning
url https://ieeexplore.ieee.org/document/9758696/
work_keys_str_mv AT mdalmehedihasan gaitrecognitionwithwearablesensorsusingmodifiedresidualblockbasedlightweightcnn
AT fuadalabir gaitrecognitionwithwearablesensorsusingmodifiedresidualblockbasedlightweightcnn
AT mdalsiam gaitrecognitionwithwearablesensorsusingmodifiedresidualblockbasedlightweightcnn
AT jungpilshin gaitrecognitionwithwearablesensorsusingmodifiedresidualblockbasedlightweightcnn