Effective Early Detection of Epileptic Seizures through EEG Signals Using Classification Algorithms Based on t-Distributed Stochastic Neighbor Embedding and K-Means

Aug 5, 2026

Epilepsy is a neurological disorder characterized by seizures, and electroencephalogram (EEG) recordings offer physiological information for seizure detection. Manual EEG interpretation by experts is time-consuming and diagnoses may vary, motivating automated computer-aided diagnosis for early detection. This work extracts discriminative features using discrete wavelet transform (DWT), then applies PCA and t-SNE for dimensionality reduction. K-means clustering combined with PCA or t-SNE forms representative subgroups, and the resulting features train XGBoost, K-NN, decision tree, random forest, and MLP models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

Abstract

Introduction

Background on epilepsy and seizure risks

Methodology

Feature extraction with DWT

Dimensionality reduction with PCA and t-SNE

Clustering with K-means

Classifier training and evaluation

diagnostics Article Effective Early Detection of Epileptic Seizures through EEG Signals Using Classiﬁcation Algorithms Based on t-Distributed Stochastic Neighbor Embedding and K-Means Khaled M. Alalayah 1,*, Ebrahim Mohammed Senan 2, *, Hany F. Atlam 3, Ibrahim Abdulrab Ahmed 4 and Hamzeh Salameh Ahmad Shatnawi 4 Citation: Alalayah, K.M.; Senan, E.M.; Atlam, H.F.; Ahmed, I.A.; Shatnawi, H.S.A. Effective Early Detection of Epileptic Seizures through EEG Signals Using Classiﬁcation Algorithms Based ont-Distributed Stochastic Neighbor Embedding and K-Means. Diagnostics 2023, 13, 1957 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics13111957 Academic Editors: Ayman El-Baz and Sang Kun Lee Received: 1 April 2023 Revised: 22 May 2023 Accepted: 2 June 2023 Published: 3 June 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Department of Computer Science, College of Science and Arts, Najran University, Sharurah 68341, Saudi Arabia 2 Department of Artiﬁcial Intelligence, Faculty of Computer Science and Information Technology, Alrazi University, Sana'a P.O. Box 1152, Yemen 3 Cyber Security Centre, WMG, University of Warwick, Coventry CV4 7AL, UK; [hany.atlam@warwick.ac.uk](hany.atlam@warwick.ac.uk) 4 Computer Department, Applied College, Najran University, Najran 66462, Saudi Arabia; [iaalqubati@nu.edu.sa](iaalqubati@nu.edu.sa) (I.A.A.) * Correspondence: [kmalalayah@nu.edu.sa](kmalalayah@nu.edu.sa) (K.M.A.); [senan1710@gmail.com](senan1710@gmail.com) (E.M.S.) Abstract: Epilepsy is a neurological disorder in the activity of brain cells that leads to seizures. An electroencephalogram (EEG) can detect seizures as it contains physiological information of the neural activity of the brain. However, visual examination of EEG by experts is time consuming, and their diagnoses may even contradict each other. Thus, an automated computer-aided diagnosis for EEG diagnostics is necessary. Therefore, this paper proposes an effective approach for the early detection of epilepsy. The proposed approach involves the extraction of important features and classiﬁcation. First, signal components are decomposed to extract the features via the discrete wavelet transform (DWT) method. Principal component analysis (PCA) and the t-distributed stochastic neighbor embedding (t-SNE) algorithm were applied to reduce the dimensions and focus on the most important features. Subsequently, K-means clustering + PCA and K-means clustering + t-SNE were used to divide the dataset into subgroups to reduce the dimensions and focus on the most important representative features of epilepsy. The features extracted from these steps were fed to extreme gradient boosting, K-nearest neighbors (K-NN), decision tree (DT), random forest (RF) and multilayer perceptron (MLP) classiﬁers. The experimental results demonstrated that the proposed approach provides superior results to those of existing studies. During the testing phase, the RFclassiﬁer with DWT and PCA achieved an accuracy of 97.96%, precision of 99.1%, recall of 94.41% and F1 score of 97.41% . Moreover, the RF classiﬁer with DWT and t-SNE attained an accuracy of 98.09%, precision of 99.1%, recall of 93.9% and F1 score of 96.21% . In comparison, the MLP classiﬁer with PCA + K-means reached an accuracy of 98.98%, precision of 99.16%, recall of 95.69% and F1 score of 97 .4% . Keywords: EEG; epileptic seizure; DWT; K-means; PCA; t-SNE; machine learning 1. Introduction Epilepsy is one of the most common neurological disorders worldwide. According to the World Health Organization, approximately 50 million people worldwide suffer from this

FAQs

Why is automated early detection of epileptic seizures needed?

Expert visual EEG assessment is time-consuming and diagnoses can contradict, so automated computer-aided diagnosis is needed for earlier and more consistent detection.

How does the proposed method extract and select EEG features?

It decomposes signal components using discrete wavelet transform (DWT), then applies PCA and t-SNE to reduce dimensions and highlight important features.

Which classifiers are used and how are they evaluated?

The extracted features are fed into multiple classifiers including extreme gradient boosting, K-nearest neighbors, decision tree, random forest, and multilayer perceptron, and results are reported using accuracy, precision, recall, and F1 score.

Aug 5, 2026

Upload by Olivia Brown