A novel approach for classification of mental tasks using multiview ensemble learning (MEL)

• Published in: Neurocomputing (Amsterdam) Vol. 417; pp. 558 - 584
• Main Authors: Gupta, A., Khan, R.U., Singh, V.K., Tanveer, M., Kumar, D., Chakraborti, A., Pachori, R.B.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 05.12.2020
• Subjects: Brain computer interface (BCI); Electroencephalography (EEG); Empirical mode decomposition (EMD); Feature coding; Fuzzy C-means; Mental tasks classification; Multiview learning; Support vector machine (SVM); Wavelet transform (WT); Support vector machine (SVM); Multiview learning; Electroencephalography (EEG); Empirical mode decomposition (EMD); Fuzzy C-means; Wavelet transform (WT); Mental tasks classification; Brain computer interface (BCI); Feature coding
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2020.07.050

Brain-computer interface (BCI) is a domain, in which a person can send information without using any exterior nerve or muscles, just using their brain signal, called electroencephalography (EEG) signal. Multiview learning or data integration or data fusion from a different set of features is an emerging way in machine learning to improve the generalized performance by considering the knowledge with multiple views. Multiview learning has made rapid progress and development in recent years and is also facing many new challenges. This method can be used in the BCI domain, as the meaningful representation of the EEG signal in plenty of ways. This study utilized the multiview ensemble learning (MEL) approach for the binary classification of five mental tasks on the six subjects individually. In this study, we used a well-known EEG database (Keirn and Aunon database). The EEG signal has been decomposed using by methods i.e wavelet transform (WT), empirical mode decomposition (EMD), empirical wavelet transform (EWT), and fuzzy C-means followed by EWT (FEWT). After that, the feature coding technique is applied using parametric feature formation from the decomposed signal. Hence, we had four views to learn four same type of independent base classifiers and predictions are made in an ensemble manner. The study is performed independently with three types of base classifiers, i.e., K-nearest neighbor (KNN), support vector machine (SVM) with linear and non-linear kernels The performance validation of the ten combinations of mental tasks was performed by three MEL based classifiers, i.e., K-nearest neighbor (KNN), support vector machine (SVM) with linear and non-linear kernels. For reliability of the obtained results of the classifiers, 10-fold cross-validation was used. The proposed algorithm shows a promising accuracy of 80% to 100% for binary pair-wise classification of mental tasks.