Epileptic Seizure Classification and Prediction Model Using Fuzzy Logic-Based Augmented Learning

Abstract

Epileptic Seizure (ES) is an abnormality associated with discharging of continues electric impulses from the instance of normal activity. The period and time interval of occurrence is a challenging task to record and validate. In this article, a focus is made to classify and predict the occurrence ratio of seizer based on augmented learning and fuzzy rules. The Epileptic Seizure datasets are acquired from pre-trained and validated approaches further re-trained using interdependent attributes based on augmented learning and training approach. The outcome of training is further used by fuzzy rules to classify and categorize the Epileptic Seizure based on occurrences series of patterns and time. The proposed technique is a hybrid approach and novel as segmented based learning is used to predict the seizer. The technique has recorded 92.23% accuracy in seizure classification and 89.91% in reliable prediction.