Multi-label classification for physical activity recognition from various accelerometer sensor positions

In recent years, the use of accelerometers embedded in smartphones for Human Activity Recognition (HAR) has been well considered. Nevertheless, the role of the sensor placement is yet to be explored and needs to be further investigated. In this study, we investigated the role of sensor place...

Full description

Bibliographic Details
Main Authors: Mohamed, Raihani, Zainudin, Muhammad Noorazlan Shah, Sulaiman, Md. Nasir, Perumal, Thinagaran, Mustapha, Norwati
Format: Article
Language:English
Published: Universiti Utara Malaysia Press 2018
Online Access:http://psasir.upm.edu.my/id/eprint/59715/
http://psasir.upm.edu.my/id/eprint/59715/1/Multi-label%20classification%20for%20physical%20activity%20recognition%20from%20various%20accelerometer%20sensor%20positions.pdf
_version_ 1848853998513160192
author Mohamed, Raihani
Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Perumal, Thinagaran
Mustapha, Norwati
author_facet Mohamed, Raihani
Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Perumal, Thinagaran
Mustapha, Norwati
author_sort Mohamed, Raihani
building UPM Institutional Repository
collection Online Access
description In recent years, the use of accelerometers embedded in smartphones for Human Activity Recognition (HAR) has been well considered. Nevertheless, the role of the sensor placement is yet to be explored and needs to be further investigated. In this study, we investigated the role of sensor placements for recognizing various types of physical activities using the accelerometer sensor embedded in the smartphone. In fact, most of the reported work in HAR utilized traditional multi-class classification approaches to determine the types of activities. Hence, this study was to recognize the activity based on the best sensor placements that are appropriate to the activity performed. The traditional multi-class classification approach required more manual work and was time consuming to run the experiment separately. Thus, this study proposed the multi- label classification technique with the Label Combination (LC) approach in order to tackle this issue. The result was compared with several state-of-the-art traditional multi-class classification approaches. The multi-label classification result significantly outperformed the traditional multi-class classification methods as well as minimized the model build time.
first_indexed 2025-11-15T11:02:53Z
format Article
id upm-59715
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T11:02:53Z
publishDate 2018
publisher Universiti Utara Malaysia Press
recordtype eprints
repository_type Digital Repository
spelling upm-597152018-03-20T03:38:58Z http://psasir.upm.edu.my/id/eprint/59715/ Multi-label classification for physical activity recognition from various accelerometer sensor positions Mohamed, Raihani Zainudin, Muhammad Noorazlan Shah Sulaiman, Md. Nasir Perumal, Thinagaran Mustapha, Norwati In recent years, the use of accelerometers embedded in smartphones for Human Activity Recognition (HAR) has been well considered. Nevertheless, the role of the sensor placement is yet to be explored and needs to be further investigated. In this study, we investigated the role of sensor placements for recognizing various types of physical activities using the accelerometer sensor embedded in the smartphone. In fact, most of the reported work in HAR utilized traditional multi-class classification approaches to determine the types of activities. Hence, this study was to recognize the activity based on the best sensor placements that are appropriate to the activity performed. The traditional multi-class classification approach required more manual work and was time consuming to run the experiment separately. Thus, this study proposed the multi- label classification technique with the Label Combination (LC) approach in order to tackle this issue. The result was compared with several state-of-the-art traditional multi-class classification approaches. The multi-label classification result significantly outperformed the traditional multi-class classification methods as well as minimized the model build time. Universiti Utara Malaysia Press 2018 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/59715/1/Multi-label%20classification%20for%20physical%20activity%20recognition%20from%20various%20accelerometer%20sensor%20positions.pdf Mohamed, Raihani and Zainudin, Muhammad Noorazlan Shah and Sulaiman, Md. Nasir and Perumal, Thinagaran and Mustapha, Norwati (2018) Multi-label classification for physical activity recognition from various accelerometer sensor positions. Journal of Information and Communication Technology, 18 (2). pp. 209-231. ISSN 1675-414X; ESSN: 2180-3862 http://jict.uum.edu.my/index.php/current-issues
spellingShingle Mohamed, Raihani
Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Perumal, Thinagaran
Mustapha, Norwati
Multi-label classification for physical activity recognition from various accelerometer sensor positions
title Multi-label classification for physical activity recognition from various accelerometer sensor positions
title_full Multi-label classification for physical activity recognition from various accelerometer sensor positions
title_fullStr Multi-label classification for physical activity recognition from various accelerometer sensor positions
title_full_unstemmed Multi-label classification for physical activity recognition from various accelerometer sensor positions
title_short Multi-label classification for physical activity recognition from various accelerometer sensor positions
title_sort multi-label classification for physical activity recognition from various accelerometer sensor positions
url http://psasir.upm.edu.my/id/eprint/59715/
http://psasir.upm.edu.my/id/eprint/59715/
http://psasir.upm.edu.my/id/eprint/59715/1/Multi-label%20classification%20for%20physical%20activity%20recognition%20from%20various%20accelerometer%20sensor%20positions.pdf