EUVIMEDEUVIMED entdecken
Crossref

Multi-Class EEG-Based Epileptic Seizure Classification using Hybrid Deep Learning Architectures

Arya Manve, Akshat Patil, Abhijeet Kolhe, Aditya Jain, Sanjivani Adusl

International Journal of Science, Strategic Management and Technology · 17.05.2026 · 02 (05) · 1-9

DOI: 10.55041/ijsmt.v2i5.192 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Science, Strategic Management and Technology, online erschienen am 17.05.2026. Verfasst von Arya Manve und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Epilepsy affects roughly 50 million people worldwide, yet reliable automated seizure detection remains an open problem. Manual EEG interpretation is slow, subjective, and requires specialist expertise that is scarce in many clinical settings. We built an automated five-class seizure classification system and evaluated three deep learning architectures—a 1D Convolutional Neural Network (1D-CNN), a Bidirectional LSTM (BiLSTM), and a CNN-LSTM hybrid—against traditional baselines (Random Forest, SVM, Decision Tree) on the Bonn University EEG dataset. The 1D-CNN achieved the highest accuracy at 95.5% (precision 95.6%, recall 95.5%, F1 95.5%), outperforming all other models. A Streamlit web application was developed alongside the models to support real-time EEG upload and seizure prediction. Our results suggest that convolutional feature extraction is particularly effective for this task, even when compared to architectures designed to model temporal sequences.

Zitieren

APA

Manve, A., Patil, A., Kolhe, A., Jain, A., & Adusl, S. (2026). Multi-Class EEG-Based Epileptic Seizure Classification using Hybrid Deep Learning Architectures. International Journal of Science, Strategic Management and Technology, 02(05), 1-9. https://doi.org/10.55041/ijsmt.v2i5.192

Vancouver

Manve A, Patil A, Kolhe A, Jain A, Adusl S. Multi-Class EEG-Based Epileptic Seizure Classification using Hybrid Deep Learning Architectures. International Journal of Science, Strategic Management and Technology. 2026;02(05):1-9. doi:10.55041/ijsmt.v2i5.192

BibTeX
@article{Manve2026,
  author = {Manve, Arya and Patil, Akshat and Kolhe, Abhijeet and Jain, Aditya and Adusl, Sanjivani},
  title = {Multi-Class EEG-Based Epileptic Seizure Classification using Hybrid Deep Learning Architectures},
  journal = {International Journal of Science, Strategic Management and Technology},
  year = {2026},
  volume = {02},
  number = {05},
  pages = {1--9},
  doi = {10.55041/ijsmt.v2i5.192}
}
Kostenlos starten →