Research map / Time series / Causal and generative time series
U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging
Mathias Perslev, Michael Jensen, Sune Darkner, Poul Jørgen Jennum, Christian Igel
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use fully convolutional U-Time instead of CNN-LSTM | Sleep staging · Sleep-EDF-39 | mean F1: 0.77 -> 0.79 | Improved |
| Use fully convolutional U-Time instead of CNN-LSTM | Sleep staging · Sleep-EDF-153 | mean F1: 0.73 -> 0.76 | Improved |
| Use fully convolutional U-Time instead of CNN-LSTM | Sleep staging · Physionet-2018 | mean F1: 0.77 -> 0.77 | No clear effect |
| Use fully convolutional U-Time instead of CNN-LSTM | Sleep staging · DCSM | mean F1: 0.76 -> 0.79 | Improved |
| Use fully convolutional U-Time instead of CNN-LSTM | Sleep staging · ISRUC | mean F1: 0.71 -> 0.77 | Improved |
| Replace CNN-LSTM with U-Time | Sleep staging · CAP | mean F1: 0.68 -> 0.68 | No clear effect |
| Use smaller CNN filters (ablation) | DeepSleepNet · DCSM (100-record subset, 5-CV) | mean F1: 0.73 -> 0.74 | Improved |
| Change DeepSleepNet architecture or hyperparameters (ablation) | DeepSleepNet · Sleep-EDF-39 (25 records, 5-CV) | mean F1: 0.76 -> 0.71 | Hurt |
| Add EMG and EOG channels (ablation) | U-Time · Sleep-EDF-153 | mean F1: 0.76 -> 0.76 | No clear effect |
| Add EOG channel (ablation) | U-Time · DCSM | mean F1: 0.79 -> 0.80 | Improved |
| Add EOG channel (ablation) | U-Time · ISRUC | mean F1: 0.77 -> 0.78 | Improved |
Closest papers by meaning
- PSDNorm: Temporal Normalization for Deep Learning in Sleep Staging (ICLR 2026 · similarity 0.87)
- SleepFM: Multi-modal Representation Learning for Sleep Across Brain Activity, ECG and Respiratory Signals (ICML 2024 · similarity 0.87)
- XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (TPAMI 2021 · similarity 0.87)
- Generalizable Sleep Staging via Multi-Level Domain Alignment (AAAI 2024 · similarity 0.84)
- Personalized Sleep Staging Leveraging Source-free Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.84)
- Subject-Relative Micro-Motion and Sleep Dynamics for Near-Infrared Video Sleep Staging (NeurIPS 2026 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
