OFFLINE LINEAR DISCRIMINANT ANALYSIS CLASSIFICATION OF TWO CLASS EEG SIGNALS

Abstract

This paper investigates the use of LDA algorithm In the EEG classification. EEG feature extraction isImplemented to reduce the dimensionality of data. The Sliding Window Technique is used to calculate the meanwithin each window samples. Then, classification is done based on hyperplane technique. The LDA algorithm isdescribed in details with all the implementation Issues. The LDA regularization is also discussed and its effects onthe classification accuracy is given. In addition, both window size and channel selection effect on the accuracy isIllustrated. Results show that a window size of 150 samples, channel 3 and regularization parameter of 0.9 givesan accuracy of 90%.