Brain wave classification for divergent hand movements

Abstract

Brain-Computer Interface (BCI) is an emerging technology in medical diagnosis and rehabilitation. In this study, by the acquisition of Electroencephalogram (EEG) signals from 30 healthy participants who perform four different hand movements, necessary features are extracted and classified to determine their accuracies. Statistical time domain features are extracted from the mu and beta frequency band. The Event related desynchronization (ERD)/Event related synchronization (ERS) measurements are extracted, from which it was evident that both mu and beta frequency bands are more efficient in the C3 channel. By applying the Paired Samples t-test, the extracted features are analyzed and were determined to have a 95% significant level of difference between the mu and beta band, being statistically efficient in the beta band of the C3 channel. By employing different classifiers such as Support Vector Machine (SVM), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Naïve Bayesian classifier and Binary Decision Tree (BDT) algorithms on both channel’s mu and beta frequency bands, it was observed that the performance of beta frequency band classifiers shows 90% accuracy in binary class classification. In the comparative study of all these classifiers, LDA and Naïve Bayes show above 95% accuracy for binary class classification.