Fuzzy system with tabu search learning for classification of motor imagery data. (July 2015)

• Record Type: Journal Article
• Authors: Nguyen, Thanh; Khosravi, Abbas; Creighton, Douglas; Nahavandi, Saeid
• Is Part Of: Biomedical signal processing and control. Volume 20(2015)
• Page Start: 61
• Page End: 70
• Publication Date: 2015-07
• Subjects: Wavelet transform -- Wilcoxon test -- EEG signal classification -- Motor imagery data -- BCI competition II; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2015.04.007
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Combine wavelet transform and Wilcoxon statistics for EEG signal feature extraction. Introduce fuzzy standard additive model with tabu search learning for classification. Proposed tabu-FSAM method considerably dominates competitive classifiers. Tabu-FSAM outperforms the best performance reported in the BCI competition II. Proposed method can be implemented into a real-time EEG signal analysis system. Abstract: This paper introduces an approach to classify EEG signals using wavelet transform and a fuzzy standard additive model (FSAM) with tabu search learning mechanism. Wavelet coefficients are ranked based on statistics of the Wilcoxon test. The most informative coefficients are assembled to form a feature set that serves as inputs to the tabu-FSAM. Two benchmark datasets, named Ia and Ib, downloaded from the brain-computer interface (BCI) competition II are employed for the experiments. Classification performance is evaluated using accuracy, mutual information, Gini coefficient and F-measure. Widely-used classifiers, including feedforward neural network, support vector machine, k-nearest neighbours, ensemble learning Adaboost and adaptive neuro-fuzzy inference system, are also implemented for comparisons. The proposed tabu-FSAM method considerably dominates the competitive classifiers, and outperforms the best performance on the Ia and Ib datasets reported in the BCI competition II.