Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review

Human Activity Recognition (HAR) is a field that infers human activities from raw time-series signals acquired through embedded sensors of smartphones and wearable devices. It has gained much attraction in various smart home environments, especially to continuously monitor human behaviors in ambient...

Full description

Bibliographic Details
Main Authors: Ramanujam, E., Perumal, Thinagaran, Padmavathi, S.
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers 2021
Online Access:http://psasir.upm.edu.my/id/eprint/97564/
http://psasir.upm.edu.my/id/eprint/97564/1/ABSTRACT.pdf
_version_ 1848862633696952320
author Ramanujam, E.
Perumal, Thinagaran
Padmavathi, S.
author_facet Ramanujam, E.
Perumal, Thinagaran
Padmavathi, S.
author_sort Ramanujam, E.
building UPM Institutional Repository
collection Online Access
description Human Activity Recognition (HAR) is a field that infers human activities from raw time-series signals acquired through embedded sensors of smartphones and wearable devices. It has gained much attraction in various smart home environments, especially to continuously monitor human behaviors in ambient assisted living to provide elderly care and rehabilitation. The system follows various operation modules such as data acquisition, pre-processing to eliminate noise and distortions, feature extraction, feature selection, and classification. Recently, various state-of-the-art techniques have proposed feature extraction and selection techniques classified using traditional Machine learning classifiers. However, most of the techniques use rustic feature extraction processes that are incapable of recognizing complex activities. With the emergence and advancement of high computational resources, Deep Learning techniques are widely used in various HAR systems to retrieve features and classification efficiently. Thus, this review paper focuses on providing profound concise of deep learning techniques used in smartphone and wearable sensor-based recognition systems. The proposed techniques are categorized into conventional and hybrid deep learning models described with its uniqueness, merits, and limitations. The paper also discusses various benchmark datasets used in existing techniques. Finally, the paper lists certain challenges and issues that require future research and improvements.
first_indexed 2025-11-15T13:20:08Z
format Article
id upm-97564
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T13:20:08Z
publishDate 2021
publisher Institute of Electrical and Electronics Engineers
recordtype eprints
repository_type Digital Repository
spelling upm-975642022-07-27T01:45:34Z http://psasir.upm.edu.my/id/eprint/97564/ Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review Ramanujam, E. Perumal, Thinagaran Padmavathi, S. Human Activity Recognition (HAR) is a field that infers human activities from raw time-series signals acquired through embedded sensors of smartphones and wearable devices. It has gained much attraction in various smart home environments, especially to continuously monitor human behaviors in ambient assisted living to provide elderly care and rehabilitation. The system follows various operation modules such as data acquisition, pre-processing to eliminate noise and distortions, feature extraction, feature selection, and classification. Recently, various state-of-the-art techniques have proposed feature extraction and selection techniques classified using traditional Machine learning classifiers. However, most of the techniques use rustic feature extraction processes that are incapable of recognizing complex activities. With the emergence and advancement of high computational resources, Deep Learning techniques are widely used in various HAR systems to retrieve features and classification efficiently. Thus, this review paper focuses on providing profound concise of deep learning techniques used in smartphone and wearable sensor-based recognition systems. The proposed techniques are categorized into conventional and hybrid deep learning models described with its uniqueness, merits, and limitations. The paper also discusses various benchmark datasets used in existing techniques. Finally, the paper lists certain challenges and issues that require future research and improvements. Institute of Electrical and Electronics Engineers 2021 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/97564/1/ABSTRACT.pdf Ramanujam, E. and Perumal, Thinagaran and Padmavathi, S. (2021) Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review. IEEE Sensors Journal, 21 (12). 13029 - 13040. ISSN 1530-437X https://ieeexplore.ieee.org/document/9389739 10.1109/JSEN.2021.3069927
spellingShingle Ramanujam, E.
Perumal, Thinagaran
Padmavathi, S.
Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title_full Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title_fullStr Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title_full_unstemmed Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title_short Human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
title_sort human activity recognition with smartphone and wearable sensors using deep learning techniques: a review
url http://psasir.upm.edu.my/id/eprint/97564/
http://psasir.upm.edu.my/id/eprint/97564/
http://psasir.upm.edu.my/id/eprint/97564/
http://psasir.upm.edu.my/id/eprint/97564/1/ABSTRACT.pdf