Fuzzy-Based Automatic Epileptic Seizure Detection Framework

Detection of epileptic seizures on the basis Electroencephalogram (EEG) recordings is a challenging task due to complex, non-stationary and non-linear nature these biomedical signals. In existing literature, number automatic seizure detection methods have been proposed that extract useful features from EEG segments classify them using machine learning algorithms. Some characterizing non-epileptic signals overlap; therefore, it requires analysis must be performed diverse perspectives. Few studies analyzed in domains identify distinguishing characteristics To pose challenge mentioned above, this paper, fuzzy-based model incorporates novel feature extraction selection method along with fuzzy classifiers. The work extracts pattern time-domain, frequency-domain, It applies strategy extracted get more discriminating build classifiers for seizures. empirical evaluation was conducted benchmark Bonn dataset. shows significant accuracy 98% 100% normal vs. ictal classification cases while three class inter-ictal reaches above 97.5%. obtained results ten (including normal, or ictal, seizure-free classes) prove superior performance as compared other state-of-the-art counterparts.