PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
March 27, 2026Journal of Engineering and Science in Medical Diagnostics and Therapy

Epileptic Seizure Detection Based on Convolutional Self-Attention Adaptive Dimensionality Expansion Network Using EEG Signals

View Full Paper
Ask AI
Bookmark
Share

Authors

XLXingyu Long

Discussion

Loading...

Member takes

Overview

Demonstrates improved seizure detection accuracy in EEG signals, highlighting a new approach for better interpretability.

Key Points

  • The aim is to improve epileptic seizure detection by addressing limitations of traditional methods.
  • Proposed CSADI-Net integrates convolutional self-attention for parameter reduction.
  • Adaptive dimensionality expansion is used for parameter adjustment during training.
  • Class activation heatmaps are generated for enhanced visual interpretability.
  • Validation conducted on CHB-MIT and TUH datasets.
  • Achieved accuracy of 98.87% and F1 score of 98.49% on the CHB-MIT dataset.
  • Obtained accuracy of 98.26% and F1 score of 98.13% on the TUH dataset.
  • Outperformed CNN, CNN-LSTM, and linear self-attention Transformer in terms of accuracy and interpretability.

Cite This Study

Xingyu Long (2026) studied this question.

synapsesocial.com/papers/69c620ab15a0a509bde19334https://doi.org/10.1115/1.4071471
View Full Paper
Ask AI
Bookmark
Share