← Back to all news
arXiv Computation and Language By Elmira Salari, Shruti Kshirsagar

LLM-Assisted Label Noise Correction for EEG-Based Sleep Stage Classification

Read the original on arXiv Computation and Language →

The paper introduces an LLM-assisted label-noise filtering pipeline for EEG-based sleep stage classification. TinySleepNet is first trained to generate confidence scores, after which low-confidence epochs are evaluated by LLaMA 3.1 using EEG spectral features and context to label them as RELIABLE or SUSPICIOUS. Suspicious epochs are removed, and TinySleepNet is retrained, yielding higher accuracy and Macro F1-score on the Sleep-EDF Expanded dataset while keeping the lightweight model unchanged for inference.

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 Computation and Language.

Related stories

arXiv AI
Aug 14

Personalized Scorer Modeling: A Learning-Based Framework for Deriving Robust Sleep Stage Labels from Multiple Experts

arXiv:2608. 12446v1 Announce Type: cross Abstract: Sleep stage classification is important for the diagnosis and management of sleep disorders, yet most automatic staging studies evaluate models against a single reference hypnogram despite known inter-scorer variability.

By Seyyed Ali Hoseini, Javad Baseri, Hamid Saadatfar, Edris Hoseini Gol, AmirHossein Eshghi
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
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 →