Metraipolis › archive › dc_660bdc2f8ab7

SleepEffFormer: Efficient CNN-Transformer with Transition-Aware Smoothing for Single-Channel EEG Sleep Stage Classification — arXiv:2609.22148

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22148
License (as archived)
CC0-1.0
Archived
2026-10-10T00:57:52.496Z
SHA-256 of the archived text
221ee513608998cfb248e11a4b6aaa07f8a4574bfad4b64140ed0ff8b13f7573
Stable URL of this page
https://metraipolis.com/documento/dc_660bdc2f8ab7

How to cite

SleepEffFormer: Efficient CNN-Transformer with Transition-Aware Smoothing for Single-Channel EEG Sleep Stage Classification — arXiv:2609.22148 — arXiv (en), https://arxiv.org/abs/2609.22148 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_660bdc2f8ab7 (Metraipolis archive dc_660bdc2f8ab7, sha256 221ee513608998cfb248e11a4b6aaa07f8a4574bfad4b64140ed0ff8b13f7573)
BibTeX
@misc{dc660bdc2f8ab7,
  title = {SleepEffFormer: Efficient CNN-Transformer with Transition-Aware Smoothing for Single-Channel EEG Sleep Stage Classification — arXiv:2609.22148},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22148},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_660bdc2f8ab7; sha256 221ee513608998cfb248e11a4b6aaa07f8a4574bfad4b64140ed0ff8b13f7573},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22148. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated sleep stage classification based on single-channel EEG is a promising pathway to large-scale sleep monitoring outside the polysomnographic lab. This paper proposes SleepEffFormer TAS, an efficient and interpretable system that consists of a four-stride-block 1D CNN feature extractor, a two-layer pre-normalization Transformer encoder, and a non-parametric Transition-Aware Smoothing (TAS) layer that suppresses physiologically unrealistic transitions between predicted stages. When tested on the Sleep-EDF Expanded dataset using 78 all-night EEG recordings from the Fpz-Cz channel with a subject-wise held-out split, the proposed model achieves 83.9% accuracy, a 78.9% macro F1-score, and a Cohen's kappa of 0.765 with approximately 367K learnable parameters. This performance is comparable to AttnSleep while using 3-5 times fewer parameters. Ablation studies show that the Transformer encoder improves macro F1 by 6.6 percentage points over a CNN-based system, while the TAS layer provides an additional 1.8 percentage point improvement without introducing any trainable parameters. Weighted loss is also critical for improving classification of the minority N1 sleep stage. Attention maps generated by the proposed model reveal physiologically sensible sleep-stage-related EEG features.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in eess.SP).
Categorie arXiv: Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2609.22148 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T23:57:50.891Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).