Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities

The advancement of sensor technology has provided valuable information for evaluating functional abilities in various application domains. Human activity recognition (HAR) has gained high demand from the researchers to undergo their exploration in activity recognition system by utilizing Micro-machi...

Full description

Bibliographic Details
Main Authors: Zainudin, M. N. Shah, Sulaiman, Md. Nasir, Mustapha, Norwati, Perumal, Thinagaran
Format: Article
Language:English
Published: Universiti Teknikal Malaysia Melaka 2018
Online Access:http://psasir.upm.edu.my/id/eprint/75188/
http://psasir.upm.edu.my/id/eprint/75188/1/Pairwise%20classification%20using%20combination%20of%20statistical%20descriptors%20with%20spectral%20analysis%20features%20for%20recognizing%20walking%20activities.pdf
_version_ 1848857625407520768
author Zainudin, M. N. Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
author_facet Zainudin, M. N. Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
author_sort Zainudin, M. N. Shah
building UPM Institutional Repository
collection Online Access
description The advancement of sensor technology has provided valuable information for evaluating functional abilities in various application domains. Human activity recognition (HAR) has gained high demand from the researchers to undergo their exploration in activity recognition system by utilizing Micro-machine Electromechanical (MEMs) sensor technology. Tri-axial accelerometer sensor is utilized to record various kinds of activities signal placed at selected areas of the human bodies. The presence of high inter-class similarities between two or more different activities is considered as a recent challenge in HAR. The nt of incorrectly classified instances involving various types of walking activities could degrade the average accuracy performance. Hence, pairwise classification learning methods are proposed to tackle the problem of differentiating between very similar activities. Several machine learning classifier models are applied using hold out validation approach to evaluate the proposed method.
first_indexed 2025-11-15T12:00:31Z
format Article
id upm-75188
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T12:00:31Z
publishDate 2018
publisher Universiti Teknikal Malaysia Melaka
recordtype eprints
repository_type Digital Repository
spelling upm-751882020-04-20T14:30:05Z http://psasir.upm.edu.my/id/eprint/75188/ Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities Zainudin, M. N. Shah Sulaiman, Md. Nasir Mustapha, Norwati Perumal, Thinagaran The advancement of sensor technology has provided valuable information for evaluating functional abilities in various application domains. Human activity recognition (HAR) has gained high demand from the researchers to undergo their exploration in activity recognition system by utilizing Micro-machine Electromechanical (MEMs) sensor technology. Tri-axial accelerometer sensor is utilized to record various kinds of activities signal placed at selected areas of the human bodies. The presence of high inter-class similarities between two or more different activities is considered as a recent challenge in HAR. The nt of incorrectly classified instances involving various types of walking activities could degrade the average accuracy performance. Hence, pairwise classification learning methods are proposed to tackle the problem of differentiating between very similar activities. Several machine learning classifier models are applied using hold out validation approach to evaluate the proposed method. Universiti Teknikal Malaysia Melaka 2018 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/75188/1/Pairwise%20classification%20using%20combination%20of%20statistical%20descriptors%20with%20spectral%20analysis%20features%20for%20recognizing%20walking%20activities.pdf Zainudin, M. N. Shah and Sulaiman, Md. Nasir and Mustapha, Norwati and Perumal, Thinagaran (2018) Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities. Journal of Telecommunication, Electronic and Computer Engineering, 9 (2-11). 55 - 60. ISSN 2180-1843; ESSN: 2289-8131 https://journal.utem.edu.my/index.php/jtec/article/view/2738
spellingShingle Zainudin, M. N. Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title_full Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title_fullStr Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title_full_unstemmed Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title_short Pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
title_sort pairwise classification using combination of statistical descriptors with spectral analysis features for recognizing walking activities
url http://psasir.upm.edu.my/id/eprint/75188/
http://psasir.upm.edu.my/id/eprint/75188/
http://psasir.upm.edu.my/id/eprint/75188/1/Pairwise%20classification%20using%20combination%20of%20statistical%20descriptors%20with%20spectral%20analysis%20features%20for%20recognizing%20walking%20activities.pdf