A Feature Selection and Hyperparameter Optimization Framework for Multiclass EEG-Based Epilepsy Detection

Epilepsy is a neurological disorder characterized by recurrent seizures, and EEG continues to be the gold standard for diagnosis in clinical practice. However, the nonlinear nature of EEG and its sensitivity to noise makes manual interpretations difficult. This study presents a feature selection and hyperparameter optimization approach for automatic multi-class EEG-based epilepsy detection. Five classes representing two healthy states and three epileptic states were analyzed using EEG signals from the Bonn database. Temporal, statistical, fractal, and spectral features were extracted; the importance of the features was ranked according to the ANOVA F-value. Classifications were performed using support vector machines, random forest, nearest neighbor algorithm, decision tree, multilayer perceptron, and linear discriminant analysis methods; hyperparameters were optimized using Grid Search Cross Validation. The robustness of the proposed model was ensured using grouped layered k-fold cross-validation. With this approach, it achieved an F1-score of 0.8126 in 5-class classification and 0.9894 in binary classification, outperforming existing methods on the same dataset. Hjorth complexity, standard deviation, and Hjorth mobility emerged as the most discriminative features for epileptic states. The study demonstrates that combining feature selection with hyperparameter optimization provides a robust and interpretable framework for multi-class EEG classifications. This approach has the potential to support neurologists in their epilepsy assessments by improving diagnostic accuracy and providing clinically meaningful insights.