SleepGMUformer: A gated multimodal temporal neural network for sleep staging

TL;DR

SleepGMUformer introduces a gated multimodal neural network that dynamically fuses diverse sleep data modalities, improving sleep staging accuracy and robustness over existing methods.

Contribution

The paper presents a novel gated multimodal neural network with dynamic fusion for sleep staging, effectively handling heterogeneous data and addressing limitations of prior postfusion techniques.

Findings

Achieved 85.03% accuracy on SleepEDF-78 dataset.

Achieved 94.54% accuracy on WristHR-Motion-Sleep dataset.

Outperformed state-of-the-art models by 1-4% in accuracy.

Abstract

Sleep staging is a key method for assessing sleep quality and diagnosing sleep disorders. However, current deep learning methods face challenges: 1) postfusion techniques ignore the varying contributions of different modalities; 2) unprocessed sleep data can interfere with frequency-domain information. To tackle these issues, this paper proposes a gated multimodal temporal neural network for multidomain sleep data, including heart rate, motion, steps, EEG (Fpz-Cz, Pz-Oz), and EOG from WristHR-Motion-Sleep and SleepEDF-78. The model integrates: 1) a pre-processing module for feature alignment, missing value handling, and EEG de-trending; 2) a feature extraction module for complex sleep features in the time dimension; and 3) a dynamic fusion module for real-time modality weighting.Experiments show classification accuracies of 85.03% on SleepEDF-78 and 94.54% on WristHR-Motion-Sleep datasets. The model handles heterogeneous datasets and outperforms state-of-the-art models by 1.00%-4.00%.