Detection of Epileptic Seizures using a Five-level Db4 Wavelet, Scalogram and CNN
International Journal of Advanced Technology and Social Sciences · 08.06.2026 · 4 (5) · 515-530
DOI: 10.59890/ijatss.v4i5.237 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Technology and Social Sciences, online erschienen am 08.06.2026. Verfasst von Rieke Syochrani Zaef und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This Epilepsy is a serious neurological disorder after stroke that affects 50 million individuals. People with epilepsy face various challenges, with around 20-30% unable to fully control seizures. Due to this issue, automated detection based on EEG signals is necessary to support epilepsy studies with appropriate methodological approaches. This paper's epilepsy detection is conducted based on EEG raw signals categorized into normal and epileptic seizures, the programming language used is Python. The signals are decomposed into five-level by Daubechies4 Discrete Wavelet Transform (DWT) to extract both approximation and detail signals. This system utilizes Python programming. A scalogram is used to visualize how transient signal activity changes with changes in time scale. DWT processthe with original sampling frequency is 128 Hz, and the number of levels is 5. The frequency range of the output data after DWT at level 5 is 4-7 Hz. Finally, an Convolutional Neural Network (CNN) classifies all the extracted features. With an accuracy of 97%
Zitieren
APA
Zaef, R. S., Dwizarah, A., Islami, L., Susanti, R., Fitra, A., & Hafiza, Z. (2026). Detection of Epileptic Seizures using a Five-level Db4 Wavelet, Scalogram and CNN. International Journal of Advanced Technology and Social Sciences, 4(5), 515-530. https://doi.org/10.59890/ijatss.v4i5.237
Vancouver
Zaef RS, Dwizarah A, Islami L, Susanti R, Fitra A, Hafiza Z. Detection of Epileptic Seizures using a Five-level Db4 Wavelet, Scalogram and CNN. International Journal of Advanced Technology and Social Sciences. 2026;4(5):515-530. doi:10.59890/ijatss.v4i5.237
BibTeX
@article{Zaef2026,
author = {Zaef, Rieke Syochrani and Dwizarah, Anisa and Islami, Lysa and Susanti, Roza and Fitra, Andika and Hafiza, Zikra},
title = {Detection of Epileptic Seizures using a Five-level Db4 Wavelet, Scalogram and CNN},
journal = {International Journal of Advanced Technology and Social Sciences},
year = {2026},
volume = {4},
number = {5},
pages = {515--530},
doi = {10.59890/ijatss.v4i5.237}
}
EUVIMED