Electroencephalogram (EEG) is a convenient neuroimaging technique due to its non-invasive setup, practical usage, and high temporal resolution. EEG allows to detect brain electrical activity to diagnose neurological disorders. Epilepsy is a crucial neurologic disorder that is reasoned from occurrence of sudden and repeated seizures. The goal of this paper is to classify the focal (epileptogenic area) and non-focal (non-epileptogenic area) EEG records with cepstral coefficients and machine learning algorithms. Analysis is carried out using publicly available Bern-Barcelona EEG dataset. Mel Frequency Cepstral Coefficients (MFCC) are calculated from EEG epochs. Feature sets are normalized with z-score and dimension reduction is realized using Principal Component Analysis. Fine Tree, Quadratic Discriminant Analysis, Logistic Regression, Gaussian Naïve Bayes, Cubic Support Vector Machine, weighted k-nearest neighbors, and Bagged Trees are applied for classification stage. A value of k=10 is used for cross validation. All focal and non-focal EEG pairs are perfectly classified with acc., sen., spe., and F1-score of 100% and AUC with 1 via. Quadratic Discriminant Analysis, Logistic Regression, Cubic SVM and Weighted k-NN. Proposed work recommends MFCCs as a single marker and this provides less computation workload, practicality, and direct processing of focal / non-focal EEG time series. Proposed methodology in this paper serves one of the highest achievements to literature and can assist neurologist and physicians to validate their diagnosis.

Reviewers Suggestions