EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Method for Explainable Epileptic Seizure Detection Through Wavelet Transforms Obtained by Electroencephalogram-Based Audio Recordings

Paul Tavolato, Hubert Schölnast iD, Oliver Eigner, Antonella Santone, Mario Cesarelli, Fabio Martinelli, Francesco Mercaldo iD

Sensors · 30.12.2025 · 26 (1) · 237

DOI: 10.3390/s26010237 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.12.2025. Verfasst von Paul Tavolato und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Computer Science, University of Vienna, 1090 Vienna, Austria. Hauptthemen laut MEDLINE: Electroencephalography, Wavelet Analysis, Epilepsy, Seizures. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EU DUCA, EU CyberSecPro, SYNAPSE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate classification of brain activity from electroencephalogram signals is essential for diagnosing neurological disorders such as epilepsy. In this paper, we propose an explainable deep learning method for epileptic seizure detection. The proposed approach converts electroencephalogram signals into audio waveforms, which are then transformed into time–frequency representations using two distinct continuous wavelet transforms, i.e., the Morlet and the Mexican Hat. These wavelet-based spectrograms effectively capture both temporal and spectral characteristics of the electroencephalogram signal data and serve as inputs to a set of convolutional neural network models with the aim to detect seizure activity. To improve model transparency, the proposed method integrates three class activation mapping techniques aimed to visualize the salient regions in the wavelet images that influence each prediction. Experimental evaluation on a real-world dataset emphasizes the efficacy of wavelet-based preprocessing in electroencephalogram signal analysis in prompt epileptic seizure detection, showing an accuracy equal to 0.922.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectroencephalographyWavelet AnalysisEpilepsySeizuresHumansConvolutional Neural NetworksSignal Processing, Computer-AssistedAlgorithmsDeep Learning

Stichwörter der Autor:innen

convolutional neural networkdeep learningepilepsyexplainabilitywavelet

Autor:innen und Institutionen

  • Faculty of Computer Science, University of Vienna, 1090 Vienna, Austria.
  • Department of Computer Science and Security, St. Pölten University of Applied Sciences, 3100 Sankt Pölten, Austria.
  • Department of Medicine and Health Sciences "V. Tiberio", University of Molise, 86100 Campobasso, Italy.
  • Department of Engineering, University of Sannio, 82100 Benevento, Italy.
  • Institute of High Performance Computing and Networking, National Research Council of Italy (CNR), 87036 Rende, Italy.

ORCID-Profile: Hubert Schölnast, Francesco Mercaldo

Förderung

  • EU DUCA
  • EU CyberSecPro
  • SYNAPSE
  • Cybersecurity
  • SERICS
  • EU—NextGenerationEU projects
  • Health Operational Plan
  • PRIN-MUR-Ministry of Health

Zitieren

APA

Tavolato, P., Schölnast, H., Eigner, O., Santone, A., Cesarelli, M., Martinelli, F., & Mercaldo, F. (2025). A Method for Explainable Epileptic Seizure Detection Through Wavelet Transforms Obtained by Electroencephalogram-Based Audio Recordings. Sensors, 26(1), 237. https://doi.org/10.3390/s26010237

Vancouver

Tavolato P, Schölnast H, Eigner O, Santone A, Cesarelli M, Martinelli F, et al. A Method for Explainable Epileptic Seizure Detection Through Wavelet Transforms Obtained by Electroencephalogram-Based Audio Recordings. Sensors. 2025;26(1):237. doi:10.3390/s26010237

BibTeX
@article{Tavolato2025,
  author = {Tavolato, Paul and Schölnast, Hubert and Eigner, Oliver and Santone, Antonella and Cesarelli, Mario and Martinelli, Fabio and Mercaldo, Francesco},
  title = {A Method for Explainable Epileptic Seizure Detection Through Wavelet Transforms Obtained by Electroencephalogram-Based Audio Recordings},
  journal = {Sensors},
  year = {2025},
  volume = {26},
  number = {1},
  pages = {237},
  doi = {10.3390/s26010237}
}
Kostenlos starten →