SSVEP Extraction Applying Wavelet Transform and Decision Tree with Bays Classification

Background: SSVEP signals are usable in BCI systems (Brain-Computer interface) in order to make the paralysis movement more comfortable via his Wheelchair. Methods: In this study, we extracted The SSVEP from EEG signals, next we attained the features from it then we ranked them to obtain the best features among all feature and at the end we applied the selected features to classify them. We want to show the degree of accuracy we applied in this work. Results: In this study Bayes (applied for classifying of selected features) got the highest level of accuracy (83.32%) with t-test method, until the SVM took the next place of having the highest accuracy to itself with t-test method (79.62%). In the next place according to the feature selection method, decision tree took the next place with Bayes classification (79.13%) and then with SVM classification (78.70%). Conclusion: Bays obtained the better results to itself rather than SVM with t-test.