Feature Engineering for Epileptic Seizure Classification Using SeqBoostNet

Title

Feature Engineering for Epileptic Seizure Classification Using SeqBoostNet

Creator

Najmusseher; Banu, Nizar P.K.

Description

Epileptic seizure, a severe neurological condition, profoundly impacts patients social lives, necessitating precise diagnosis for classification and prediction. This study addresses the need for reliable automated seizure detection in epilepsy by employing Artificial Intelligence (AI) driven analysis of Electroencephalography (EEG) signals. Key innovations include combining spectral and temporal features using Uniform Manifold Approximation and Projection (UMAP) with Fast Fourier Transformation (FFT), and the introduction of the Sequential Boosting Network (SeqBoostNet), a robust stacking model integrating machine learning and deep learning for effective seizure classification. Validated on benchmark datasets such as the BONN dataset from the UCI repository and the BEED from the Bangalore EEG Epilepsy Dataset, this approach achieved high accuracy, distinguishing Focal and Generalized seizure onsets with 95.91% accuracy and overall average accuracies of 96.71% on BEED and 97.11% on BONN. Existing models frequently struggle with the variability of seizure events. However, these findings underscore the models strength in distinguishing between seizure onset types, even with the inherent fluctuations in seizure patterns. This research not only advances automated seizure detection but also underscores the value of integrating AI with EEG analysis to improve neurological diagnostics, offering the potential for significant enhancements in diagnostic accuracy and patient outcomes. 2025 University of Bahrain. All rights reserved.

Source

International Journal of Computing and Digital Systems;Volume;17;Issue;1;

Date

01-01-2025

Publisher

University of Bahrain

Subject

AdaBoost; Deep Learning; Epileptic Seizure; FFT; LSTM; Machine Learning; UMAP

Coverage

Najmusseher, Department, of Computer Science, CHRIST (Deemed to be University), Central Campus, Bangalore, 560029, India; Banu N.P.K., Department, of Computer Science, CHRIST (Deemed to be University), Central Campus, Bangalore, 560029, India

Rights

All Open Access; Gold Open Access

Relation

ISSN: 2210142X;

Format

online

Language

English

Type

Article

Identifier

https://doi.org/10.12785/ijcds/1571020131

https://www.scopus.com/pages/publications/85217538815?origin=resultslist