EEG Waveform Classification Using Transform Domain Features and SVM

Abstract

Electroencephalogram (EEG) waveforms are fluctuations in brain-recorded utilizing anodes set on the scalp. Albeit a few strategies for the evaluation of working of brain, for example, MEG, PET, CT scan, and MRI have been presented, the EEG waveform is as yet an important biological signal for checking the brain signal variations because of its moderately ease and being helpful for the patient. We have presented an approach to classify the EEG waveforms into two classes, viz. epileptic and normal. The algorithm fuses the features extracted using discrete wavelet transform, discrete cosine transform, and stationary wavelet transform. The fused features are subjected to support vector machine (SVM) classifier.