Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification
To date, the usage of electromyography (EMG) signals in myoelectric prosthetics allows patients to recover functional rehabilitation of their upper limbs. However, the increment in the number of EMG features has been shown to have a great impact on performance degradation. Therefore, feature select...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019
|
Online Access: | http://eprints.utem.edu.my/id/eprint/24581/2/2019%20AXIOMS-08-00079%20%281%29.PDF http://eprints.utem.edu.my/id/eprint/24581/ https://www.mdpi.com/2075-1680/8/3/79/htm https://doi.org/10.3390/axioms8030079 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utem.eprints.24581 |
---|---|
record_format |
eprints |
spelling |
my.utem.eprints.245812020-12-09T10:28:21Z http://eprints.utem.edu.my/id/eprint/24581/ Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification Too, Jing Wei Abdullah, Abdul Rahim Mohd Saad, Norhashimah To date, the usage of electromyography (EMG) signals in myoelectric prosthetics allows patients to recover functional rehabilitation of their upper limbs. However, the increment in the number of EMG features has been shown to have a great impact on performance degradation. Therefore, feature selection is an essential step to enhance classification performance and reduce the complexity of the classifier. In this paper, a hybrid method, namely, binary particle swarm optimization differential evolution (BPSODE) was proposed to tackle feature selection problems in EMG signals classification. The performance of BPSODE was validated using the EMG signals of 10 healthy subjects acquired from a publicly accessible EMG database. First, discrete wavelet transform was applied to decompose the signals into wavelet coefficients. The features were then extracted from each coefficient and formed into the feature vector. Afterward, BPSODE was used to evaluate the most informative feature subset. To examine the effectiveness of the proposed method, four state-of-the-art feature selection methods were used for comparison. The parameters, including accuracy, feature selection ratio, precision, F-measure, and computation time were used for performance measurement. Our results showed that BPSODE was superior, in not only offering a high classification performance, but also in having the smallest feature size. From the empirical results, it can be inferred that BPSODE-based feature selection is useful for EMG signals classification MDPI AG 2019 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/24581/2/2019%20AXIOMS-08-00079%20%281%29.PDF Too, Jing Wei and Abdullah, Abdul Rahim and Mohd Saad, Norhashimah (2019) Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification. Axioms, 8 (3). pp. 1-17. ISSN 2075-1680 https://www.mdpi.com/2075-1680/8/3/79/htm https://doi.org/10.3390/axioms8030079 |
institution |
Universiti Teknikal Malaysia Melaka |
building |
UTEM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknikal Malaysia Melaka |
content_source |
UTEM Institutional Repository |
url_provider |
http://eprints.utem.edu.my/ |
language |
English |
description |
To date, the usage of electromyography (EMG) signals in myoelectric prosthetics allows patients to recover functional rehabilitation of their upper limbs. However, the increment in the
number of EMG features has been shown to have a great impact on performance degradation. Therefore, feature selection is an essential step to enhance classification performance and reduce
the complexity of the classifier. In this paper, a hybrid method, namely, binary particle swarm optimization differential evolution (BPSODE) was proposed to tackle feature selection problems
in EMG signals classification. The performance of BPSODE was validated using the EMG signals of 10 healthy subjects acquired from a publicly accessible EMG database. First, discrete wavelet
transform was applied to decompose the signals into wavelet coefficients. The features were then extracted from each coefficient and formed into the feature vector. Afterward, BPSODE was used
to evaluate the most informative feature subset. To examine the effectiveness of the proposed method, four state-of-the-art feature selection methods were used for comparison. The parameters,
including accuracy, feature selection ratio, precision, F-measure, and computation time were used for performance measurement. Our results showed that BPSODE was superior, in not only offering
a high classification performance, but also in having the smallest feature size. From the empirical results, it can be inferred that BPSODE-based feature selection is useful for EMG signals classification |
format |
Article |
author |
Too, Jing Wei Abdullah, Abdul Rahim Mohd Saad, Norhashimah |
spellingShingle |
Too, Jing Wei Abdullah, Abdul Rahim Mohd Saad, Norhashimah Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
author_facet |
Too, Jing Wei Abdullah, Abdul Rahim Mohd Saad, Norhashimah |
author_sort |
Too, Jing Wei |
title |
Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
title_short |
Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
title_full |
Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
title_fullStr |
Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
title_full_unstemmed |
Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection For EMG Signals Classification |
title_sort |
hybrid binary particle swarm optimization differential evolution-based feature selection for emg signals classification |
publisher |
MDPI AG |
publishDate |
2019 |
url |
http://eprints.utem.edu.my/id/eprint/24581/2/2019%20AXIOMS-08-00079%20%281%29.PDF http://eprints.utem.edu.my/id/eprint/24581/ https://www.mdpi.com/2075-1680/8/3/79/htm https://doi.org/10.3390/axioms8030079 |
_version_ |
1687397248579665920 |
score |
13.159267 |