ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring

2026-02-27

AI Summary

This study addresses the high computational cost of existing deep learning models for automatic sleep staging using polysomnography (PSG), which hinders their deployment on wearable devices. To overcome this limitation, the authors propose ULW-SleepNet, an ultra-lightweight multimodal sleep staging framework that introduces a novel dual-stream separable convolution (DSSC) block. This architecture integrates depthwise separable convolutions, channel-wise parameter sharing, and global average pooling to drastically reduce model complexity while preserving high accuracy. With only 13.3K parameters and 7.89M FLOPs, ULW-SleepNet achieves 86.9% and 81.4% accuracy on the Sleep-EDF-20 and Sleep-EDF-78 datasets, respectively, reducing the number of parameters by up to 98.6% compared to state-of-the-art methods.

Technology Category

• Machine Learning: Hardware-aware ML
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Automatic sleep stage scoring is crucial for the diagnosis and treatment of sleep disorders. Although deep learning models have advanced the field, many existing models are computationally demanding and designed for single-channel electroencephalography (EEG), limiting their practicality for multimodal polysomnography (PSG) data. To overcome this, we propose ULW-SleepNet, an ultra-lightweight multimodal sleep stage scoring framework that efficiently integrates information from multiple physiological signals. ULW-SleepNet incorporates a novel Dual-Stream Separable Convolution (DSSC) Block, depthwise separable convolutions, channel-wise parameter sharing, and global average pooling to reduce computational overhead while maintaining competitive accuracy. Evaluated on the Sleep-EDF-20 and Sleep-EDF-78 datasets, ULW-SleepNet achieves accuracies of 86.9% and 81.4%, respectively, with only 13.3K parameters and 7.89M FLOPs. Compared to state-of-the-art methods, our model reduces parameters by up to 98.6% with only marginal performance loss, demonstrating its strong potential for real-time sleep monitoring on wearable and IoT devices. The source code for this study is publicly available at https://github.com/wzw999/ULW-SLEEPNET.

Problem

• sleep stage scoring
• multimodal polysomnography
• ultra-lightweight model
• computational efficiency
• wearable devices

Innovation

• Ultra-lightweight
• Multimodal sleep staging
• Dual-Stream Separable Convolution
• Depthwise separable convolution
• Parameter sharing