Decoding Human Attentive States from Spatial-temporal EEG Patches Using Transformers
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916741295112192 |
|---|---|
| author | Ding, Yi Lee, Joon Hei Zhang, Shuailei Luo, Tianze Guan, Cuntai |
| author_facet | Ding, Yi Lee, Joon Hei Zhang, Shuailei Luo, Tianze Guan, Cuntai |
| contents | Learning the spatial topology of electroencephalogram (EEG) channels and their temporal dynamics is crucial for decoding attention states. This paper introduces EEG-PatchFormer, a transformer-based deep learning framework designed specifically for EEG attention classification in Brain-Computer Interface (BCI) applications. By integrating a Temporal CNN for frequency-based EEG feature extraction, a pointwise CNN for feature enhancement, and Spatial and Temporal Patching modules for organizing features into spatial-temporal patches, EEG-PatchFormer jointly learns spatial-temporal information from EEG data. Leveraging the global learning capabilities of the self-attention mechanism, it captures essential features across brain regions over time, thereby enhancing EEG data decoding performance. Demonstrating superior performance, EEG-PatchFormer surpasses existing benchmarks in accuracy, area under the ROC curve (AUC), and macro-F1 score on a public cognitive attention dataset. The code can be found via: https://github.com/yi-ding-cs/EEG-PatchFormer . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_03736 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decoding Human Attentive States from Spatial-temporal EEG Patches Using Transformers Ding, Yi Lee, Joon Hei Zhang, Shuailei Luo, Tianze Guan, Cuntai Signal Processing Learning the spatial topology of electroencephalogram (EEG) channels and their temporal dynamics is crucial for decoding attention states. This paper introduces EEG-PatchFormer, a transformer-based deep learning framework designed specifically for EEG attention classification in Brain-Computer Interface (BCI) applications. By integrating a Temporal CNN for frequency-based EEG feature extraction, a pointwise CNN for feature enhancement, and Spatial and Temporal Patching modules for organizing features into spatial-temporal patches, EEG-PatchFormer jointly learns spatial-temporal information from EEG data. Leveraging the global learning capabilities of the self-attention mechanism, it captures essential features across brain regions over time, thereby enhancing EEG data decoding performance. Demonstrating superior performance, EEG-PatchFormer surpasses existing benchmarks in accuracy, area under the ROC curve (AUC), and macro-F1 score on a public cognitive attention dataset. The code can be found via: https://github.com/yi-ding-cs/EEG-PatchFormer . |
| title | Decoding Human Attentive States from Spatial-temporal EEG Patches Using Transformers |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2502.03736 |