MC2SleepNet: Multi-modal Cross-masking with Contrastive Learning for Sleep Stage Classification

TL;DR

MC2SleepNet is a novel deep learning model that combines CNNs and Transformers with contrastive learning and cross-masking to improve sleep stage classification accuracy across multiple datasets.

Contribution

The paper introduces MC2SleepNet, a new multi-modal deep learning framework that effectively integrates CNNs and Transformers for sleep stage classification using contrastive learning.

Findings

Achieved 84.6% accuracy on SleepEDF-78

Achieved 88.6% accuracy on SHHS dataset

Demonstrated strong generalization across datasets

Abstract

Sleep profoundly affects our health, and sleep deficiency or disorders can cause physical and mental problems. Despite significant findings from previous studies, challenges persist in optimizing deep learning models, especially in multi-modal learning for high-accuracy sleep stage classification. Our research introduces MC2SleepNet (Multi-modal Cross-masking with Contrastive learning for Sleep stage classification Network). It aims to facilitate the effective collaboration between Convolutional Neural Networks (CNNs) and Transformer architectures for multi-modal training with the help of contrastive learning and cross-masking. Raw single channel EEG signals and corresponding spectrogram data provide differently characterized modalities for multi-modal learning. Our MC2SleepNet has achieved state-of-the-art performance with an accuracy of both 84.6% on the SleepEDF-78 and 88.6% accuracy on the Sleep Heart Health Study (SHHS). These results demonstrate the effective generalization of our proposed network across both small and large datasets.