{"ID":2867789,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.17920","arxiv_id":"2509.17920","title":"SingLEM: Single-Channel Large EEG Model","abstract":"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.","short_abstract":"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 hete...","url_abs":"https://arxiv.org/abs/2509.17920","url_pdf":"https://arxiv.org/pdf/2509.17920v1","authors":"[\"Jamiyan Sukhbaatar\",\"Satoshi Imamura\",\"Ibuki Inoue\",\"Shoya Murakami\",\"Kazi Mahmudul Hassan\",\"Seungwoo Han\",\"Ingon Chanpornpakdi\",\"Toshihisa Tanaka\"]","published":"2025-09-22T15:46:58Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Transformer\"]","has_code":false,"code_links":[{"ID":609512,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2867789,"paper_url":"https://arxiv.org/abs/2509.17920","paper_title":"SingLEM: Single-Channel Large EEG Model","repo_url":"https://github.com/ttlabtuat/SingLEM","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}