Early Epileptic Seizure Prediction Using EEG Signals with Machine Learning
| dc.contributor.author | Oran, Samet | |
| dc.contributor.author | Yıldırım, Esen | |
| dc.date.accessioned | 2025-01-06T17:29:56Z | |
| dc.date.available | 2025-01-06T17:29:56Z | |
| dc.date.issued | 2023 | |
| dc.description | 9th World Congress on Electrical Engineering and Computer Systems and Sciences, EECSS 2023 -- 3 August 2023 through 5 August 2023 -- London -- 305029 | |
| dc.description.abstract | Epilepsy is a chronic disease that dates back to ancient times and affects people only during seizures. Since the onset of seizures is unknown, it heavily poor affects the living standards of patients. If seizure onset can be predicted in sufficient advance, seizures can be prevented with drugs to be used or an opportunity can be provided for patients who cannot be stopped with drugs to move to a safe zone. For this purpose, to predict an epileptic seizure, before a certain period of time happens, frequency-based feature extraction is applied with the use of recorded EEG data. Bases of the study rely on creating time for patients to reach necessary medications approximately ahead 30-60 minutes before having an epileptic seizure. In this respect, an open-access dataset with 24 pediatric patients’ EEG recordings was used and frequency-based feature extraction was performed using wavelet transformation. Afterward, classification performances of the features are compared for a k-nearest neighbor (k-NN), random forest algorithm (RF), support vector machine (SVM), and J48 which are extensively used machine learning techniques. In accordance with the classification results, the average highest accuracy was acquired as 99.87% with the SVM classifier. © 2023, Avestia Publishing. All rights reserved. | |
| dc.description.sponsorship | Adana Alparslan Türkeş Bilim ve Teknoloji Üniversitesi, ATÜ, (22303005) | |
| dc.identifier.doi | 10.11159/icbes23.145 | |
| dc.identifier.isbn | 978-199080026-9 | |
| dc.identifier.issn | 2369-811X | |
| dc.identifier.scopus | 2-s2.0-85180626906 | |
| dc.identifier.scopusquality | Q4 | |
| dc.identifier.uri | https://doi.org/10.11159/icbes23.145 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.14669/1399 | |
| dc.indekslendigikaynak | Scopus | |
| dc.language.iso | en | |
| dc.publisher | Avestia Publishing | |
| dc.relation.ispartof | Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science | |
| dc.relation.publicationcategory | Konferans Öğesi - Uluslararası - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.snmz | KA_20241211 | |
| dc.subject | Classification | |
| dc.subject | Epileptic Seizure | |
| dc.subject | Feature Extraction | |
| dc.subject | Machine Learning | |
| dc.subject | Wavelet Spectrum | |
| dc.title | Early Epileptic Seizure Prediction Using EEG Signals with Machine Learning | |
| dc.type | Conference Object |
