PulseAugur
EN
LIVE 10:27:15

New ML frameworks tackle sleep staging with Mamba and physiology-aware models · 3 sources tracked

By PulseAugur Editorial · [3 sources] ·

Two new research papers introduce advanced machine learning frameworks for automatic sleep staging using electroencephalogram (EEG) data. GamSleepNet, detailed in one paper, is a lightweight framework that utilizes a constrained Convolutional Neural Network (CNN) and the Mamba architecture, achieving 87.86% accuracy on the Sleepedf dataset with minimal parameters. The second paper presents SleepBand, a framework designed for single-source domain generalization, employing a learnable Morlet filter bank and structured integration to focus on physiologically relevant sleep rhythms and improve robustness across different datasets. AI

IMPACT These frameworks advance automated sleep analysis, potentially improving diagnosis and home monitoring by offering more accurate and efficient models for processing EEG data.

RANK_REASON Two academic papers published on arXiv detailing new machine learning models for sleep staging.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New ML frameworks tackle sleep staging with Mamba and physiology-aware models · 3 sources tracked

COVERAGE [3]

  1. arXiv cs.LG TIER_1 English(EN) · Zihao Wei, Yulin Gong, Yudan Lv ·

    Lightweight ML-Based Automatic Sleep Staging Framework with Constrained CNN and Mamba for Small-Sample EEG Datasets

    arXiv:2607.04934v1 Announce Type: new Abstract: Automatic sleep staging is a key technology for precise diagnosis and treatment of sleep disorders as well as long-term home sleep monitoring. Portable electroencephalogram (EEG) devices have become the focus of research due to thei…

  2. arXiv cs.LG TIER_1 English(EN) · Zhi Lu, Yang Hu, Yan Chen ·

    SleepBand: Single-Source Domain Generalization for Sleep Staging via Physiologically Structured Spectral Modeling

    arXiv:2607.04851v1 Announce Type: cross Abstract: Generalizing sleep staging models to unseen datasets is challenging, and typical domain generalization (DG) methods often rely on multiple source domains or domain labels that are rarely available in practice. We tackle the strict…

  3. arXiv cs.LG TIER_1 English(EN) · Yudan Lv ·

    Lightweight ML-Based Automatic Sleep Staging Framework with Constrained CNN and Mamba for Small-Sample EEG Datasets

    Automatic sleep staging is a key technology for precise diagnosis and treatment of sleep disorders as well as long-term home sleep monitoring. Portable electroencephalogram (EEG) devices have become the focus of research due to their convenience in data collection. However, curre…

RELATED ENTITIES

RELATED TOPICS