Stockwell-common spatial pattern technique for motor imagery-based Brain Computer Interface design. (October 2018)

• Record Type: Journal Article
• Authors: Sethi, S.; Upadhyay, R.; Singh, H.S.
• Is Part Of: Computers & electrical engineering. Volume 71(2018)
• Page Start: 492
• Page End: 504
• Publication Date: 2018-10
• Subjects: Brain Computer Interface (BCI) -- Electroencephalogram (EEG) -- S-transform -- Common Spatial Pattern (CSP) -- Machine learning technique; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2018.07.056
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: In this paper, an attempt is made to obtain optimal S-Transform based Common Spatial features for automated recognition of motor imagery signals. The combined approach of S-Transform and Common Spatial Pattern is established as an efficient technique for binary class Brain Computer Interface implementation. The method is carried out in four methodological steps. In the first step, Electroencephalogram signals are decomposed into time-frequency sub-bands using S-Transform based decomposition technique. The S-Transform coefficients are grouped to represent distinct frequency sub-bands of Electroencephalogram activity in the second step. In the third step, the Common Spatial Pattern method is applied on fundamental sub-bands to prepare discriminative feature vector. The classification of motor imagery signals is performed using three soft computing techniques viz. Least Square-Support Vector Machine, Random Forest and Artificial Neural Network in the fourth step. Classification results illustrate the efficacy of proposed technique in motor imagery signal classification task.