Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.10004 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918189855670272 |
|---|---|
| author | Hong, Jiahui Li, Siqing Jian, Muqing Yang, Luming |
| author_facet | Hong, Jiahui Li, Siqing Jian, Muqing Yang, Luming |
| contents | Existing EEG recognition models suffer from poor cross-paradigm generalization due to dataset-specific constraints and individual variability. To overcome these limitations, we propose BITE (Bidirectional Time-Freq Pyramid Network), an end-to-end unified architecture featuring robust multistream synergy, pyramid time-frequency attention (PTFA), and bidirectional adaptive convolutions. The framework uniquely integrates: 1) Aligned time-frequency streams maintaining temporal synchronization with STFT for bidirectional modeling, 2) PTFA-based multi-scale feature enhancement amplifying critical neural patterns, 3) BiTCN with learnable fusion capturing forward/backward neural dynamics. Demonstrating enhanced robustness, BITE achieves state-of-the-art performance across four divergent paradigms (BCICIV-2A/2B, HGD, SD-SSVEP), excelling in both within-subject accuracy and cross-subject generalization. As a unified architecture, it combines robust performance across both MI and SSVEP tasks with exceptional computational efficiency. Our work validates that paradigm-aligned spectral-temporal processing is essential for reliable BCI systems. Just as its name suggests, BITE "takes a bite out of EEG." The source code is available at https://github.com/cindy-hong/BiteEEG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_10004 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification Hong, Jiahui Li, Siqing Jian, Muqing Yang, Luming Machine Learning Existing EEG recognition models suffer from poor cross-paradigm generalization due to dataset-specific constraints and individual variability. To overcome these limitations, we propose BITE (Bidirectional Time-Freq Pyramid Network), an end-to-end unified architecture featuring robust multistream synergy, pyramid time-frequency attention (PTFA), and bidirectional adaptive convolutions. The framework uniquely integrates: 1) Aligned time-frequency streams maintaining temporal synchronization with STFT for bidirectional modeling, 2) PTFA-based multi-scale feature enhancement amplifying critical neural patterns, 3) BiTCN with learnable fusion capturing forward/backward neural dynamics. Demonstrating enhanced robustness, BITE achieves state-of-the-art performance across four divergent paradigms (BCICIV-2A/2B, HGD, SD-SSVEP), excelling in both within-subject accuracy and cross-subject generalization. As a unified architecture, it combines robust performance across both MI and SSVEP tasks with exceptional computational efficiency. Our work validates that paradigm-aligned spectral-temporal processing is essential for reliable BCI systems. Just as its name suggests, BITE "takes a bite out of EEG." The source code is available at https://github.com/cindy-hong/BiteEEG. |
| title | Bidirectional Time-Frequency Pyramid Network for Enhanced Robust EEG Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.10004 |