Detection of epileptic spikes in egg signal using wavelet transform and adaptive neuro – fuzzy inference system(ANFIS) techniques

Diagnostic and warning methods can prove useful for epilepsy infinite recognition, controlling seizure (to prepare for seizure e.g., pull over if driving) and organizing medicine schedule to reduce unwanted side effects of untimely medication. Such methods employ brain electrical activity signals called electro encephalography (EEG). Epileptiform from EEG can be detected either visually (by specialist inspection) or automatically (by using signal processing knowledge). The first method requires plenty of time and precision. Automatic systems, growingly popular in recent decades, have been proposed to reduce time. In this study, an automated system is developed to detect spikes from EEG and classify them into healthy and epileptic categories in order to increase accuracy and precision. Discrete wavelet (DWT) is applied as a feature extraction method and adaptive neuro-fuzzy inference system (ANFIS) is used for classification. A sensitivity of 99% has been obtained