Open AccessROC Analysis of EEG Subbands for Epileptic Seizure Detection using Naïve Bayes Classifier
Author(s) -
Mustafa Sameer,
Bharat Gupta
Publication year - 2021
Publication title -
journal of mobile multimedia
Language(s) - English
Resource type - Journals
eISSN - 1550-4654
pISSN - 1550-4646
DOI - 10.13052/jmm1550-4646.171315
Subject(s) - ictal , pattern recognition (psychology) , electroencephalography , artificial intelligence , naive bayes classifier , receiver operating characteristic , epileptic seizure , short time fourier transform , classifier (uml) , speech recognition , computer science , fourier transform , mathematics , fourier analysis , psychology , machine learning , neuroscience , support vector machine , mathematical analysis
This paper presents analysis of Electroencephalograms (EEGs) and subbands (delta, theta, alpha, beta, gamma) using image descriptors for epileptic seizure detection. Short-time Fourier transform (STFT) has been utilized to convert 1-D EEG data into image. All subbands are separated from the time-frequency (t-f) matrix and Haralick features of each subband is fed in the Naïve Bayes (NB) classifier. Receiver operating characteristic (ROC) analysis has been used for performance evaluation of classifier. Among all subbands, gamma band alone shows a maximum AUC of 0.98 to classify between ictal and healthy class, while beta band shows a maximum AUC of 0.96 to differentiate between ictal and interictal class. Significance of this work is it shows the medical advantage of different subbands for the detection process.