Deep learning approaches for diagnosing seizure based on EEG signal analysis
A comparative evaluation is performed using standard evaluation metrics on two datasets, the CHB-MIT Scalp EEG Database and Turkish Epilepsy EEG Dataset. The proposed EDTL models are evaluated against the individual models on standard performance metrics, with the EDTL achieving the highest performance of 99.23% on the AUC.
Authors
- Mosleh Hmoud Al-Adhaileh (ORCID: https://orcid.org/0000-0002-3519-1121)
- Muhammad Ali Zeb (ORCID: https://orcid.org/0009-0009-3746-9308)
- Ayoub K. Al-Hamadi (ORCID: https://orcid.org/0000-0002-3632-2402)
- Nadhem Ebrahim (ORCID: https://orcid.org/0000-0001-9975-589X)
- Mohammed Alarfaj (ORCID: https://orcid.org/0000-0001-6089-9319)
Institutions
- University of Akron (US)
- Saudi Electronic University (SA)
- Kohat University of Science and Technology (PK)
- King Salman Center for Disability Research (SA)
- King Faisal University (SA)
Publication Details
- Journal
- Frontiers in Human Neuroscience
- Published
- 2025-11-10
- DOI
- https://doi.org/10.3389/fnhum.2025.1669919
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- King Salman Center for Disability Research