← Back to all news
arXiv Computer Vision By Chongjian Wang, Chen Liu, Junjie Gao, Xiaofang Zhong, Shiyuan Han, Tong Zhang

DualStabSleepNet: A Dual-Domain Diffusion Stabilization Network for Robust Sleep Staging

Read the original on arXiv Computer Vision →

DualStabSleepNet (DSSNet) is a dual-domain diffusion stabilization network designed to improve the robustness of automatic sleep staging across heterogeneous recording conditions. It employs a continuous-scale diffusion-based module to suppress noise while preserving physiological signals, then transforms stabilized signals into time-frequency representations for a Vision Transformer backbone. A teacher‑student guided diffusion feature stabilization further reduces feature drift, achieving state‑of‑the‑art accuracy on four public PSG datasets and demonstrating strong performance under cross‑dataset distribution shifts.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Machine Learning
Jul 28

StageGuard: Physiologically Constrained Sleep Staging

arXiv:2607. 23284v1 Announce Type: new Abstract: Automated sleep staging is increasingly used in large-scale studies to derive sleep-architecture endpoints: total sleep time, REM latency, sleep efficiency, and bout-duration statistics.

By Juntang Wang, Yihan Wang, Hao Wu, Jiayu Gao, Shixin Xu, Dongmian Zou
safety
More like this →
arXiv Machine Learning
Sep 17

LightSleepX: A Lightweight, Inception-Based Dual-Modal Network for Sleep Staging

LightSleepX is a lightweight, inception‑based dual‑modal network designed for sleep staging in resource‑constrained environments. It uses depthwise separable convolutions, multi‑scale enhanced attention for efficient EEG/EOG feature extraction, and a Mamba encoder for long‑range temporal modeling. On public benchmarks, it achieves 85.9% accuracy on Sleep‑EDF‑20 and 81.8% on ISRUC‑S3 with only 0.049M parameters and 195.9 MFLOPs.

By Yi Wang
multimodalbenchmarkssafety
More like this →
arXiv Machine Learning
Aug 20

NanoSleep: A Parameter-Efficient Hybrid Temporal Convolutional Network for Single-Channel Sleep Stage Classification

NanoSleep is a compact hybrid temporal convolutional network designed for single‑channel EEG sleep stage classification. It integrates a learnable Sinc‑convolutional front end, dual‑branch feature extraction for multi‑scale temporal and spectral representations, a gated dilated temporal convolutional backbone with channel recalibration, and a conditional random field for sequence‑level decoding. Evaluated on Sleep‑EDF and Sleep‑EDF‑Expanded datasets, NanoSleep consistently outperforms six baseline methods and demonstrates that each major component contributes to its performance.

By S M Asif Hossain, Shruti Kshirsagar
benchmarks
More like this →