A lightweight automatic sleep staging method for children using single-channel EEG based on edge artificial intelligence

World Wide Web https://doi.org/10.1007/s11280-021-00983-3 A lightweight automatic sleep staging method for children using single‑channel EEG based on edge artificial intelligence Liqiang Zhu1 · Changming Wang2,3 · Zhihui He4 · Yuan Zhang1 Received: 27 July 2021 / Revised: 8 November 2021 / Accepted: 26 November 2021 © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2021 Abstract With the development of telemedicine and edge computing, edge artificial intelligence (AI) will become a new development trend for smart medicine. On the other hand, nearly onethird of children suffer from sleep disorders. However, all existing sleep staging methods are for adults. Therefore, we adapted edge AI to develop a lightweight automatic sleep staging method for children using single-channel EEG. The trained sleep staging model will be deployed to edge smart devices so that the sleep staging can be implemented on edge devices which will greatly save network resources and improving the performance and privacy of sleep staging application. Then the results and hypnogram will be uploaded to the cloud server for further analysis by the physicians to get sleep disease diagnosis reports and treatment opinions. We utilized 1D convolutional neural networks (1D-CNN) and long short term memory (LSTM) to build our sleep staging model, named CSleepNet. We tested the model on our childrens sleep (CS) dataset and sleep-EDFX dataset. For the CS dataset, we experimented with F4-M1 channel EEG using four different loss functions, and the logcosh performed best with overall accuracy of 83.06% and F1-score of 76.50%. We used Fpz-Cz and Pz-Oz channel EEG to train our model in Sleep-EDFX dataset, and achieved an accuracy of 86.41% without manual feature extraction. The experimental results show that our method has great potential. It not only plays an important role in sleep-related research, but also can be widely used in the classification of other time sequences physiological signals. Keywords Sleep staging · Edge AI · Deep learning · LSTM · EEG Liqiang Zhu and Changming Wang contributed equally to this work. This article belongs to the Topical Collection: Special Issue on Resource Management at the Edge for Future Web, Mobile and IoT Applications Guest Editors: Qiang He, Fang Dong, Chenshu Wu, and Yun Yang * Yuan Zhang Extended author information available on the last page of the article 13 Vol.:(0123456789) World Wide Web 1 Introduction At present, most of the computing tasks of the remote sleep monitoring (such as sleep staging) are deployed on platforms with large-scale computing resources such as computing centers, which largely limit the convenience to people. With the advancement of Internet of Things (IoT), the number of networking devices has increased dramatically, and the total amount of data generated has increased accordingly. Data transmission from the end to the cloud will bring huge bandwidth pressure and energy consumption, which makes the traditional centralized processing unbearable, thus giving birth to the edge computing and gradually developing to the edge AI [15, 25]. Sleep staging is a basic work of sleep research, which requires the use of sleep records throughout the night. Automatic sleep staging based on edge artificial intelligence can solve the problem of traditional remote sleep monitoring that sleep staging on a cloud server consumes a lot of network resources. Sleep-induced diseases such as insomnia, drowsiness, obstructive sleep apnea (OSA) and other sleep disorders are becoming more and more common and have become a major medical challenge. For children, high-quality sleep helps children’s intellectual development and is closely related to children’s cognitive function, learning and attention. If school-age children are not able to get enough and good sleep, it will affect their mental development and cause emotional, behavioral, and attention problems. However, nearly one-third of children suffer from sleep disorders [11]. Polysomnography (PSG) recordings is used to diagnose sleep-related diseases, which include electroencephalogram (EEG), electrooculogram (EOG), electrocardiogram (ECG), electromyogram (EMG), breathing exercises (chest and abdominal), oral and nasal airflow, body movement, blood oxygen saturation (SaO2) and other physiological parameters. Sleep stage scoring is to divide the physiological parameters in the polysomnography chart into 30 s continuous epochs according to the time axis, and divide these epochs into different sleep stages according to the American Academy of Sleep Medicine (AASM) rules [4]. Sleep stage scoring can be performed using single-channel EEG or multiple physiological parameters. The hypnogram obtained from the results of sleep staging can intuitively reflect the sleep of subjects throughout the night, and is used to evaluate sleep quality and sleep-related problems [6]. The AASM manual was first published in 2007 [4]. In the AASM rules, all sleep recordings are divided into 5 stages. They include Wake (W), Rapid Eye Movement (REM) and Non-Rapid Eye Movement (NREM) , where the NREM includes N1 (transition stage), N2 (light sleep) and N3 (deep sleep). Age may be the most critical factor in differentiating the sleep pattern between children and adults, due to the EEG variation reflected by PSG mornitoring [10]. The AASM rules also include sleep stage scoring methods for children. Technicians need to spend a lot of time and efforts to monitor the changes of different physiological signals in the PSG for sleep stage scoring. In addition, the quality of sleep stage scoring depends on the experience and fatigue of technicians, and the agreement between the technicians is usually less than 90% [28]. In addition, the existing automatic sleep stage classification methods are for adults by default. Therefore, it is necessary to develop an automatic sleep staging method for children. To perform automatic sleep staging on a cloud server, it is necessary to upload the collected sleep recordings of the whole night(usually hundreds of MB or even more than 1GB size) to the cloud, which takes a long time to respond, puts a lot of pressure on network bandwidth and may leak user privacy. Edge AI trains and deploys deep learning models at the edge of the network closer to users and data sources, thereby improving the 13 World Wide Web performance and privacy of AI applications [25]. Therefore, we develop a lightweight automatic sleep staging method for children using single-channel EEG based on edge AI. The sleep staging performed on edge devices, and the results and hypnogram will be uploaded to the cloud server for physicians to further analyze. Users will get analysis reports and some useful suggestions. COVID-19 has made a huge impact on people’s work, study and life [2]. The rapid development of wearable computing technologies has led to an increased involvement of wearable de (...truncated)