Multichannel Detection of Epilepsy using SVM classifier on EEG signal

Epilepsy is a chronic neurological disorder which occurs due to the recurring evoking of seizure which results due to the abnormal rhythmic discharge of electrical activities of the brain. This fluctuation in the electrical activities of the brain can be analyzed using EEG signal which provides valuable information about the physiological states of the brain. In this paper we propose an efficient mechanism algorithm based on statistical analysis using features i.e. average value, standard deviation, variance and kurtosis along with the electrical features such as least significant value, most significant value and band power. These features were used on multichannel EEG signals which provide promising results with less complexity, simplicity along with accuracy. Thus, automatic seizure detection mechanism based on multichannel EEG signal analysis using advanced signal processing techniques with the statistical and electrical features helps to reduce the physician workload.