Motor Imagery Based Eeg Signal Classification Using Self Organizing Maps

MOTOR IMAGERY BASED EEG SIGNAL CLASSIFICATION USING SELF ORGANIZING MAPS *Muhammad Zeeshan Baig, Yasar Ayaz National University of Science and Technology Islamabad, Pakistan *Contact: [email protected] ABSTRACT: Classification of Motor Imagery (MI) tasks based EEG signals effectively is the main hurdle in order to develop online Brain Computer interface (BCI). In this research article, a relatively new approach has been implemented to accurately classify EEG signals that have been extracted from MI. The data-set was obtained from BCI competition-II 2003 named Graz database. Two channels have been selected for preprocessing i.e. C3 and C4. After applying pre processing techniques feature vector have been extracted. The feature vector consists of bi -orthogonal Wavelet Transform (WT) coefficients, Welench Power Spectral Density estimates and the average power. In this study, we have presented a comparison of mostly used classification algorithm with a new unsupervised learning technique for classification i .e. Self-organizing maps (SOM) based neural network. SOM and other algorithms have been used to categorize the feature vector acquired from the EEG data-set; into their corresponding classes. Both orignal and reduced feature set has been used for classification of motor imagery based EEG signals. The reduction is performed by applying Principal Component Analysis (PCA). It has been depicted from measured data that SOM shows a maximum classification accuracy of 84.17% on PCA implemented reduce feature set. Furthermore, an 2% increase in classification accuracy has been attained by using bi-orthogonal wavelet transform instead of Daubechies WT.