DynamicSleepNet: a multi-exit neural network with adaptive inference time for sleep stage classification

Frontiers in Physiology

Physiology

Xiao Qian¹  Hu Zhikun¹  Xue Jun¹  Wang Wenjian² 

[1] School of Information Science, Yunnan University, Kunming, China;null;

关键词: multimodal;    sleep stage;    depth-adaptive;    feature fusion;    attention network;    electrophysiological signals;   

DOI  :  10.3389/fphys.2023.1171467

 received in 2023-02-22, accepted in 2023-04-26,  发布年份 2023

来源: Frontiers

【 摘 要 】

Sleep is an essential human physiological behavior, and the quality of sleep directly affects a person’s physical and mental state. In clinical medicine, sleep stage is an important basis for doctors to diagnose and treat sleep disorders. The traditional method of classifying sleep stages requires sleep experts to classify them manually, and the whole process is time-consuming and laborious. In recent years, with the help of deep learning, automatic sleep stage classification has made great progress, especially networks using multi-modal electrophysiological signals, which have greatly improved in terms of accuracy. However, we found that the existing multimodal networks have a large number of redundant calculations in the process of using multiple electrophysiological signals, and the networks become heavier due to the use of multiple signals, and difficult to be used in small devices. To solve these two problems, this paper proposes DynamicSleepNet, a network that can maximize the use of multiple electrophysiological signals and can dynamically adjust between accuracy and efficiency. DynamicSleepNet consists of three effective feature extraction modules (EFEMs) and three classifier modules, each EFEM is connected to a classifier. Each EFEM is able to extract signal features while making the effective features more prominent and the invalid features are suppressed. The samples processed by the EFEM are given to the corresponding classifier for classification, and if the classifier considers the uncertainty of the sample to be below the threshold we set, the sample can be output early without going through the whole network. We validated our model on four datasets. The results show that the highest accuracy of our model outperforms all baselines. With accuracy close to baselines, our model is faster than the baselines by a factor of several to several tens, and the number of parameters of the model is lower or close. The implementation code is available at: https://github.com/Quinella7291/A-Multi-exit-Neural-Network-with-Adaptive-Inference-Time-for-Sleep-Stage-Classification/.

【 授权许可】

Unknown   
Copyright © 2023 Wenjian, Qian, Jun and Zhikun.