Epileptic Seizure Detection using SVM Classifier based on Temporal and Spectral Features Dr. Murali L.*, Dr. Chitra D.**, Dr. Manigandan T.***, Priyanga P.**** *Associate Professor, Department of Electronics and Communication Engineering, P. A. College of Engineering and Technology, Pollachi, Coimbatore, India **Professor, Department of Computer Science and Engineering, P. A. College of Engineering and Technology, Pollachi, Coimbatore, India ***Professor, Department of Computer Science and Engineering, P. A. College of Engineering and Technology, Pollachi, Coimbatore, India ****PG Scholar, Department of Electronics and Communication Engineering, Hindusthan College of Engineering and Technology, Coimbatore, India Online published on 2 August, 2016. Abstract In this paper, the proposed systems detect the recorded epileptic seizure activity in EEG segments. Seizure evolution is typically a dynamic and non-stationary process. The dataset is collected from epilepsy centre, university of Bonn, Germany for seizure event detection. Based on the dataset, the analysis is performed in the following stages like Pre-processing Temporal and Spectral features are used in the process of Feature extraction and Support Vector Machine classifier used in Classification process. This leads to better classification of the database into three groups are Healthy subjects, epileptic subjects during a seizure-free interval that means Interictal and epileptic subjects during a seizure course that means Ictal. The proposed system presents the seizure detection and related prediction methods using support vector machine with recurrence quantification algorithm which provides the higher accuracy. Top Keywords Classification (Support Vector Machine), Epileptic Seizure detection, EEG segments, Feature extraction (temporal and spectral), Phase space Reconstruction, Pre-Processing, Wavelet Decomposition. Top |