Application of SVM Framework for Classification of Single Trial EEG
A brain-computer interface (BCI) system requires effective online processing of electroencephalogram (EEG) signals for real-time classification of continuous brain activity. In this paper, based on support vector machines (SVM), we present a framework for single trial online classification of imaginary left and right hand movements. For classification of motor imagery, the time-frequency information is extracted from two frequency bands (μ and β rhythms) of EEG data with Morlet wavelets, and the SVM framework is used for accumulation of the discrimination evidence over time to infer user’s unknown motor intention. This algorithm improved the single trial online classification accuracy as well as stability, and achieved a low classification error rate of 10%.
KeywordsSupport Vector Machine Mutual Information Motor Imagery Morlet Wavelet Wavelet Power Spectrum
Unable to display preview. Download preview PDF.
- 1.Blankertz, B., Curio, G., Müller, K.-R.: Classifying Single Trial EEG: Toward Brain Computer Interfacing. Advances in Neural Inf. Proc. Systems 14, 157–164 (2002)Google Scholar
- 4.Blankertz, B., Müller, K.-R., Curio, G., Vaughan, T.M., Schalk, G., Wolpaw, J.R., Schloegl, A., Neuper, C., Pfurtscheller, G., Hinterberger, T., Schröder, M., Birbaumer, N.: The BCI Competition 2003: Progress and Perspectives in Detection and Discrimination of EEG Single Trials. IEEE Trans. Biomed. Eng. 51(6), 1044–1051 (2004)CrossRefGoogle Scholar