Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity

Widespread research on activity recognition is becoming an imperative topic for improving the quality of human health. The fast development of sensing technology has become a fundamental platform for researchers to implement a system that could fulfill human needs. Due to privacy interests and low c...

Full description

Bibliographic Details
Main Authors: Zainudin, Muhammad Noorazlan Shah, Sulaiman, Md. Nasir, Mustapha, Norwati, Perumal, Thinagaran, Mohamed, Raihani
Format: Article
Language:English
Published: Scientific and Technical research Council of Turkey - TUBITAK/Turkiye Bilimsel ve Teknik Arastirma Kurumu 2018
Online Access:http://psasir.upm.edu.my/id/eprint/74353/
http://psasir.upm.edu.my/id/eprint/74353/1/Two-stage%20feature%20selection%20using%20ranking%20self-adaptive%20differential%20evolution%20algorithm%20for%20recognition%20of%20acceleration%20activity.pdf
_version_ 1848857483978735616
author Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
Mohamed, Raihani
author_facet Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
Mohamed, Raihani
author_sort Zainudin, Muhammad Noorazlan Shah
building UPM Institutional Repository
collection Online Access
description Widespread research on activity recognition is becoming an imperative topic for improving the quality of human health. The fast development of sensing technology has become a fundamental platform for researchers to implement a system that could fulfill human needs. Due to privacy interests and low cost, wearable sensing technology is used in numerous physical activity monitoring and recognition systems. While these systems have proved to be successful, it is crucial to pay attention to the less relevant features to be classified. In such circumstances, it might happen that some features are less meaningful for describing the activity. Less complex and easy to understand, feature ranking is gaining a lot of attention in most feature dimension problems such as in bioinformatics and hyperspectral images. However, the improvement of ranking features in activity recognition has not yet been achieved. On the other hand, an evolutionary algorithm has proven its effectiveness in searching the best feature subsets. An exhaustive searching process of finding an optimal parameter value is another challenge. Consequently, this paper proposes a ranking self-adaptive differential evolution (rsaDE) feature selection algorithm. The proposed algorithm is capable of selecting the optimal feature subsets while improving the recognition of acceleration activity using a minimum number of features. The experiments employed real-world physical acceleration data sets: WISDM and PAMAP2. As a result, rsaDE performed better than the current methods in terms of model performance and its efficiency in the context of random forest ensemble classifiers.
first_indexed 2025-11-15T11:58:17Z
format Article
id upm-74353
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T11:58:17Z
publishDate 2018
publisher Scientific and Technical research Council of Turkey - TUBITAK/Turkiye Bilimsel ve Teknik Arastirma Kurumu
recordtype eprints
repository_type Digital Repository
spelling upm-743532020-03-27T06:40:41Z http://psasir.upm.edu.my/id/eprint/74353/ Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity Zainudin, Muhammad Noorazlan Shah Sulaiman, Md. Nasir Mustapha, Norwati Perumal, Thinagaran Mohamed, Raihani Widespread research on activity recognition is becoming an imperative topic for improving the quality of human health. The fast development of sensing technology has become a fundamental platform for researchers to implement a system that could fulfill human needs. Due to privacy interests and low cost, wearable sensing technology is used in numerous physical activity monitoring and recognition systems. While these systems have proved to be successful, it is crucial to pay attention to the less relevant features to be classified. In such circumstances, it might happen that some features are less meaningful for describing the activity. Less complex and easy to understand, feature ranking is gaining a lot of attention in most feature dimension problems such as in bioinformatics and hyperspectral images. However, the improvement of ranking features in activity recognition has not yet been achieved. On the other hand, an evolutionary algorithm has proven its effectiveness in searching the best feature subsets. An exhaustive searching process of finding an optimal parameter value is another challenge. Consequently, this paper proposes a ranking self-adaptive differential evolution (rsaDE) feature selection algorithm. The proposed algorithm is capable of selecting the optimal feature subsets while improving the recognition of acceleration activity using a minimum number of features. The experiments employed real-world physical acceleration data sets: WISDM and PAMAP2. As a result, rsaDE performed better than the current methods in terms of model performance and its efficiency in the context of random forest ensemble classifiers. Scientific and Technical research Council of Turkey - TUBITAK/Turkiye Bilimsel ve Teknik Arastirma Kurumu 2018 Article PeerReviewed text en http://psasir.upm.edu.my/id/eprint/74353/1/Two-stage%20feature%20selection%20using%20ranking%20self-adaptive%20differential%20evolution%20algorithm%20for%20recognition%20of%20acceleration%20activity.pdf Zainudin, Muhammad Noorazlan Shah and Sulaiman, Md. Nasir and Mustapha, Norwati and Perumal, Thinagaran and Mohamed, Raihani (2018) Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity. Turkish Journal of Electrical Engineering and Computer Sciences, 26. 1378 - 1389. ISSN 1378–1389 http://journals.tubitak.gov.tr/elektrik/ 10.3906/elk-1709-138
spellingShingle Zainudin, Muhammad Noorazlan Shah
Sulaiman, Md. Nasir
Mustapha, Norwati
Perumal, Thinagaran
Mohamed, Raihani
Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title_full Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title_fullStr Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title_full_unstemmed Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title_short Two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
title_sort two-stage feature selection using ranking self-adaptive differential evolution algorithm for recognition of acceleration activity
url http://psasir.upm.edu.my/id/eprint/74353/
http://psasir.upm.edu.my/id/eprint/74353/
http://psasir.upm.edu.my/id/eprint/74353/
http://psasir.upm.edu.my/id/eprint/74353/1/Two-stage%20feature%20selection%20using%20ranking%20self-adaptive%20differential%20evolution%20algorithm%20for%20recognition%20of%20acceleration%20activity.pdf