Classification of epileptic seizures in EEG data based on iterative gated graph convolution network
Ablation experiments verified the efficacy of iterative graph optimization and gated graph convolution. The optimized graph structure significantly differs from the predefined EEG topology. Gated graph convolutions demonstrate superior performance in capturing the long-term dependencies in EEG series. Additionally, Focal Loss outperforms other commonly used loss functions in the TUSZ classification task.
Authors
- Rencheng Sun (ORCID: https://orcid.org/0000-0003-2921-2659)
- Jian Liu (ORCID: https://orcid.org/0000-0003-3258-0380)
- Yongqiang Yu
- Yi Sui (ORCID: https://orcid.org/0000-0002-3174-0015)
- Yue Hu
Institutions
- Qingdao University of Science and Technology (CN)
- Jinan Stomatological Hospital (CN)
Publication Details
- Journal
- Frontiers in Computational Neuroscience
- Published
- 2024-08-29
- DOI
- https://doi.org/10.3389/fncom.2024.1454529
- Citations
- 10
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 3.43
Funders
- National Natural Science Foundation of China
- Natural Science Foundation for Young Scientists of Shanxi Province
- Young Scientists Fund