Abstract:
Epileptic seizures occur due to disorder in brain functionality which can affect patient’s
health. Prediction of epileptic seizures before the beginning of the onset is quite useful for pre-
venting the seizure by medication. Machine learning techniques and computational methods
are used for predicting epileptic seizures from Electroencephalograms (EEG) signals. The
proposed methodology involves multiple stages of data pre-processing, feature extraction,
and classification using various machine learning models. Initially, pre-ictal (before seizure
onset) and inter-ictal (non-seizure) EEG data are extracted and subjected to pre-processing
steps. The pre-processed data then undergoes feature extraction using Common Spatial Pat-
terns (CSP) and Empirical Mode Decomposition (EMD) techniques, enabling the extraction
of both time and frequency domain features. Subsequently, the extracted features are utilized
as input to different machine learning models including), K-Nearest Neighbors (KNN), and
Support Vector Machine (SVM). These models are trained and evaluated for their ability to
predict seizure events based on the extracted features. The performance of each model is
assessed using metrics such as accuracy, sensitivity, anticipation time. Experimental results
demonstrate the effectiveness of the proposed methodology in accurately predicting seizure
events from EEG signals.
