scholarly journals Hybrid Binary Particle Swarm Optimization Differential Evolution-Based Feature Selection for EMG Signals Classification

Axioms ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 79 ◽  
Author(s):  
Jingwei Too ◽  
Abdul Rahim Abdullah ◽  
Norhashimah Mohd Saad

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.

Computation ◽  
2019 ◽  
Vol 7 (1) ◽  
pp. 12 ◽  
Author(s):  
Jingwei Too ◽  
Abdul Abdullah ◽  
Norhashimah Mohd Saad ◽  
Weihown Tee

Due to the increment in hand motion types, electromyography (EMG) features are increasingly required for accurate EMG signals classification. However, increasing in the number of EMG features not only degrades classification performance, but also increases the complexity of the classifier. Feature selection is an effective process for eliminating redundant and irrelevant features. In this paper, we propose a new personal best (Pbest) guide binary particle swarm optimization (PBPSO) to solve the feature selection problem for EMG signal classification. First, the discrete wavelet transform (DWT) decomposes the signal into multiresolution coefficients. The features are then extracted from each coefficient to form the feature vector. After which pbest-guide binary particle swarm optimization (PBPSO) is used to evaluate the most informative features from the original feature set. In order to measure the effectiveness of PBPSO, binary particle swarm optimization (BPSO), genetic algorithm (GA), modified binary tree growth algorithm (MBTGA), and binary differential evolution (BDE) were used for performance comparison. Our experimental results show the superiority of PBPSO over other methods, especially in feature reduction; where it can reduce more than 90% of features while keeping a very high classification accuracy. Hence, PBPSO is more appropriate for application in clinical and rehabilitation applications.


IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 85989-86002 ◽  
Author(s):  
Bai Ji ◽  
Xiaozheng Lu ◽  
Geng Sun ◽  
Wei Zhang ◽  
Jiahui Li ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document