Título: Exploring the Characterization and Classification of EEG Signals for a Computer-Aided Epilepsy Diagnosis System

Autor(es): UMAQUINGA CRIOLLO ANA CRISTINA, ANDRÉS VARGAS, DIEGO HERNAN PELUFFO ORDOÑEZ, EMIL VEGA GUALÁN, JAIME A. RIASCOS, MIGUEL A. BECERRA

Fecha de publicación: 05-dec-2022

Resumen: Epilepsy occurs when localized electrical activity of neurons suffer from an imbalance. One of the most adequate methods for diagnosing and monitoring is via the analysis of electroencephalographic (EEG) signals. Despite there is a wide range of alternatives to characterize and classify EEG signals for epilepsy analysis purposes, many key aspects related to accuracy and physiological interpretation are still considered as open issues. In this paper, this work performs an exploratory study in order to identify the most adequate frequently-used methods for characterizing and classifying epileptic seizures. In this regard, a comparative study is carried out on several subsets of features using four representative classifiers: Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The framework uses a well-known epilepsy dataset and runs several experiments for two and three classification problems. The results suggest that DWT decomposition with SVM is the most suitable combination.

Palabras clave: lectroencephalogram (EEG), Epilepsy diagnosis, K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machine (SVM)

DOI: https://doi.org/10.1007/978-3-030-37078-7_19

ISSN: 0302-9743

Tipo publicación: Artículo