A Transformer‐Based Framework With Data Augmentation for Robust Seizure Detection Across Invasive and Noninvasive Neural Recordings
By eliminating manual feature engineering and enabling robust cross-modal adaptation, this framework bridges invasive experimental research and non-invasive clinical practice. Its efficiency and scalability support potential applications in real-time seizure monitoring and closed-loop neuromodulation systems. Future work will focus on integration with hemodynamic biomarkers, validation in chronic epilepsy models, and optimization for wearable and real-time deployment.
Authors
- Xu Teng (ORCID: https://orcid.org/0000-0003-2206-8308)
- Zheshan Guo (ORCID: https://orcid.org/0000-0001-9707-4185)
- Junyang Zhang (ORCID: https://orcid.org/0000-0002-9268-6278)
- Zhaoxiang Wang (ORCID: https://orcid.org/0000-0002-7601-376X)
- Chen Wang (ORCID: https://orcid.org/0009-0001-9633-8879)
- Yan Hao (ORCID: https://orcid.org/0000-0003-2118-2299)
- Yue Yuan (ORCID: https://orcid.org/0000-0002-5084-6712)
- Xiangyu Ye (ORCID: https://orcid.org/0000-0002-3100-232X)
- Wenjun Ruan
Institutions
- Ministry of Education (NZ)
- Hainan University (CN)
- Zhejiang Lab (CN)
- Hainan Agricultural School (CN)
- Sanya University (CN)
- Center for Life Sciences (CN)
- Hainan Medical University (CN)
Publication Details
- Journal
- CNS Neuroscience & Therapeutics
- Published
- 2025-09-01
- DOI
- https://doi.org/10.1111/cns.70584
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China