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

被引:42
作者
Too, Jingwei [1 ]
Abdullah, Abdul Rahim [1 ]
Saad, Norhashimah Mohd [2 ]
机构
[1] Univ Tekn Malaysia Melaka, Fak Kejuruteraan Elekt, Durian Tunggal 76100, Melaka, Malaysia
[2] Univ Tekn Malaysia Melaka, Fak Kejuruteraan Elekt & Kejuruteraan Komputer, Durian Tunggal 76100, Melaka, Malaysia
关键词
electromyography; discrete wavelet transform; binary particle swarm optimization; binary differential evolution; feature selection; hybrid optimization; classification; ADAPTIVE INERTIA WEIGHT; FEATURE-EXTRACTION; PSO;
D O I
10.3390/axioms8030079
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
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.
引用
收藏
页数:17
相关论文
共 37 条
[1]   Image steganalysis using improved particle swarm optimization based feature selection [J].
Adeli, Ali ;
Broumandnia, Ali .
APPLIED INTELLIGENCE, 2018, 48 (06) :1609-1622
[2]   An integrated PSO for parameter determination and feature selection of ELM and its application in classification of power system disturbances [J].
Ahila, R. ;
Sadasivam, V. ;
Manimala, K. .
APPLIED SOFT COMPUTING, 2015, 32 :23-37
[3]   Pattern Recognition of Eight Hand Motions Using Feature Extraction of Forearm EMG Signal [J].
Al Omari, Firas ;
Hui, Jiang ;
Mei, Congli ;
Liu, Guohai .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES INDIA SECTION A-PHYSICAL SCIENCES, 2014, 84 (03) :473-480
[4]   Feature subset selection using differential evolution and a wheel based search strategy [J].
Al-Ani, Ahmed ;
Alsukker, Akram ;
Khushaba, Rami N. .
SWARM AND EVOLUTIONARY COMPUTATION, 2013, 9 :15-26
[5]  
[Anonymous], 2018, APPL COMPUT INFORM, DOI [DOI 10.1016/J.ACI.2018.04.001, 10.1016/j.aci.2018.04.001]
[6]   A Hamming distance based binary particle swarm optimization (HDBPSO) algorithm for high dimensional feature selection, classification and validation [J].
Banka, Haider ;
Dara, Suresh .
PATTERN RECOGNITION LETTERS, 2015, 52 :94-100
[7]   Power quality time series data mining using S-transform and fuzzy expert system [J].
Behera, H. S. ;
Dash, P. K. ;
Biswal, B. .
APPLIED SOFT COMPUTING, 2010, 10 (03) :945-955
[8]   Opposition chaotic fitness mutation based adaptive inertia weight BPSO for feature selection in text clustering [J].
Bharti, Kusum Kumari ;
Singh, Pramod Kumar .
APPLIED SOFT COMPUTING, 2016, 43 :20-34
[9]   Surface Electromyography Signal Processing and Classification Techniques [J].
Chowdhury, Rubana H. ;
Reaz, Mamun B. I. ;
Ali, Mohd Alauddin Bin Mohd ;
Bakar, Ashrif A. A. ;
Chellappan, Kalaivani ;
Chang, Tae. G. .
SENSORS, 2013, 13 (09) :12431-12466
[10]   Improved binary PSO for feature selection using gene expression data [J].
Chuang, Li-Yeh ;
Chang, Hsueh-Wei ;
Tu, Chung-Jui ;
Yang, Cheng-Hong .
COMPUTATIONAL BIOLOGY AND CHEMISTRY, 2008, 32 (01) :29-38