Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17920 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911168691437568 |
|---|---|
| author | Sukhbaatar, Jamiyan Imamura, Satoshi Inoue, Ibuki Murakami, Shoya Hassan, Kazi Mahmudul Han, Seungwoo Chanpornpakdi, Ingon Tanaka, Toshihisa |
| author_facet | Sukhbaatar, Jamiyan Imamura, Satoshi Inoue, Ibuki Murakami, Shoya Hassan, Kazi Mahmudul Han, Seungwoo Chanpornpakdi, Ingon Tanaka, Toshihisa |
| contents | Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although emerging foundation models aim for broader applicability, their rigid dependence on fixed, high-density multi-channel montages restricts their use across heterogeneous datasets and in missing-channel or practical low-channel settings. To address these limitations, we introduce SingLEM, a self-supervised foundation model that learns robust, general-purpose representations from single-channel EEG, making it inherently hardware agnostic. The model employs a hybrid encoder architecture that combines convolutional layers to extract local features with a hierarchical transformer to model both short- and long-range temporal dependencies. SingLEM is pretrained on 71 public datasets comprising over 9,200 subjects and 357,000 single-channel hours of EEG. When evaluated as a fixed feature extractor across six motor imagery and cognitive tasks, aggregated single-channel representations consistently outperformed leading multi-channel foundation models and handcrafted baselines. These results demonstrate that a single-channel approach can achieve state-of-the-art generalization while enabling fine-grained neurophysiological analysis and enhancing interpretability. The source code and pretrained models are available at https://github.com/ttlabtuat/SingLEM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17920 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SingLEM: Single-Channel Large EEG Model Sukhbaatar, Jamiyan Imamura, Satoshi Inoue, Ibuki Murakami, Shoya Hassan, Kazi Mahmudul Han, Seungwoo Chanpornpakdi, Ingon Tanaka, Toshihisa Machine Learning Current deep learning models for electroencephalography (EEG) are often task-specific and depend on large labeled datasets, limiting their adaptability. Although emerging foundation models aim for broader applicability, their rigid dependence on fixed, high-density multi-channel montages restricts their use across heterogeneous datasets and in missing-channel or practical low-channel settings. To address these limitations, we introduce SingLEM, a self-supervised foundation model that learns robust, general-purpose representations from single-channel EEG, making it inherently hardware agnostic. The model employs a hybrid encoder architecture that combines convolutional layers to extract local features with a hierarchical transformer to model both short- and long-range temporal dependencies. SingLEM is pretrained on 71 public datasets comprising over 9,200 subjects and 357,000 single-channel hours of EEG. When evaluated as a fixed feature extractor across six motor imagery and cognitive tasks, aggregated single-channel representations consistently outperformed leading multi-channel foundation models and handcrafted baselines. These results demonstrate that a single-channel approach can achieve state-of-the-art generalization while enabling fine-grained neurophysiological analysis and enhancing interpretability. The source code and pretrained models are available at https://github.com/ttlabtuat/SingLEM. |
| title | SingLEM: Single-Channel Large EEG Model |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.17920 |