A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification
Features extracted from the electromyography (EMG) signal normally consist of irrelevant and redundant features. Conventionally, feature selection is an effective way to evaluate the most informative features, which contributes to performance enhancement and feature reduction. Therefore, this articl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/7/4/58 |
| _version_ | 1828118985270362112 |
|---|---|
| author | Jingwei Too Abdul Rahim Abdullah Norhashimah Mohd Saad Nursabillilah Mohd Ali Weihown Tee |
| author_facet | Jingwei Too Abdul Rahim Abdullah Norhashimah Mohd Saad Nursabillilah Mohd Ali Weihown Tee |
| author_sort | Jingwei Too |
| collection | DOAJ |
| description | Features extracted from the electromyography (EMG) signal normally consist of irrelevant and redundant features. Conventionally, feature selection is an effective way to evaluate the most informative features, which contributes to performance enhancement and feature reduction. Therefore, this article proposes a new competitive binary grey wolf optimizer (CBGWO) to solve the feature selection problem in EMG signals classification. Initially, short-time Fourier transform (STFT) transforms the EMG signal into time-frequency representation. Ten time-frequency features are extracted from the STFT coefficient. Then, the proposed method is used to evaluate the optimal feature subset from the original feature set. To evaluate the effectiveness of proposed method, CBGWO is compared with binary grey wolf optimization (BGWO1 and BGWO2), binary particle swarm optimization (BPSO), and genetic algorithm (GA). The experimental results show the superiority of CBGWO not only in classification performance, but also feature reduction. In addition, CBGWO has a very low computational cost, which is more suitable for real world application. |
| first_indexed | 2024-04-11T13:40:58Z |
| format | Article |
| id | doaj.art-a05a9a059a5c46738e4945526d4c8dcf |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-04-11T13:40:58Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-a05a9a059a5c46738e4945526d4c8dcf2022-12-22T04:21:14ZengMDPI AGComputers2073-431X2018-11-01745810.3390/computers7040058computers7040058A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals ClassificationJingwei Too0Abdul Rahim Abdullah1Norhashimah Mohd Saad2Nursabillilah Mohd Ali3Weihown Tee4Fakulti Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya 76100, Durian Tunggal, Melaka, MalaysiaFakulti Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya 76100, Durian Tunggal, Melaka, MalaysiaFakulti Kejuruteraan Elektronik dan Kejuruteraan Komputer, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya 76100, Durian Tunggal, Melaka, MalaysiaFakulti Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya 76100, Durian Tunggal, Melaka, MalaysiaFakulti Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya 76100, Durian Tunggal, Melaka, MalaysiaFeatures extracted from the electromyography (EMG) signal normally consist of irrelevant and redundant features. Conventionally, feature selection is an effective way to evaluate the most informative features, which contributes to performance enhancement and feature reduction. Therefore, this article proposes a new competitive binary grey wolf optimizer (CBGWO) to solve the feature selection problem in EMG signals classification. Initially, short-time Fourier transform (STFT) transforms the EMG signal into time-frequency representation. Ten time-frequency features are extracted from the STFT coefficient. Then, the proposed method is used to evaluate the optimal feature subset from the original feature set. To evaluate the effectiveness of proposed method, CBGWO is compared with binary grey wolf optimization (BGWO1 and BGWO2), binary particle swarm optimization (BPSO), and genetic algorithm (GA). The experimental results show the superiority of CBGWO not only in classification performance, but also feature reduction. In addition, CBGWO has a very low computational cost, which is more suitable for real world application.https://www.mdpi.com/2073-431X/7/4/58feature selectionelectromyographygrey wolf optimizerbinary grey wolf optimizationclassificationtime-frequency feature |
| spellingShingle | Jingwei Too Abdul Rahim Abdullah Norhashimah Mohd Saad Nursabillilah Mohd Ali Weihown Tee A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification Computers feature selection electromyography grey wolf optimizer binary grey wolf optimization classification time-frequency feature |
| title | A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification |
| title_full | A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification |
| title_fullStr | A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification |
| title_full_unstemmed | A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification |
| title_short | A New Competitive Binary Grey Wolf Optimizer to Solve the Feature Selection Problem in EMG Signals Classification |
| title_sort | new competitive binary grey wolf optimizer to solve the feature selection problem in emg signals classification |
| topic | feature selection electromyography grey wolf optimizer binary grey wolf optimization classification time-frequency feature |
| url | https://www.mdpi.com/2073-431X/7/4/58 |
| work_keys_str_mv | AT jingweitoo anewcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT abdulrahimabdullah anewcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT norhashimahmohdsaad anewcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT nursabillilahmohdali anewcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT weihowntee anewcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT jingweitoo newcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT abdulrahimabdullah newcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT norhashimahmohdsaad newcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT nursabillilahmohdali newcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification AT weihowntee newcompetitivebinarygreywolfoptimizertosolvethefeatureselectionprobleminemgsignalsclassification |