A Lightweight Segmented Attention Network for Sleep Staging by Fusing Local Characteristics and Adjacent Information

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 31; pp. 238 - 247
• Main Authors: Zhou, Wei, Zhu, Hangyu, Shen, Ning, Chen, Hongyu, Fu, Cong, Yu, Huan, Shu, Feng, Chen, Chen, Chen, Wei
• Format: Journal Article
• Language: English
• Published: United States IEEE 2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Brain modeling; China; Coders; Computational modeling; Convolutional neural networks; Data mining; Datasets; Deep learning; EEG; Electroencephalography; Feature extraction; Humans; Information processing; Machine learning; Model accuracy; Modules; multi-head attention; multiple multiscale convolutional neural network; Neural networks; Neural Networks, Computer; Quality assessment; Quality control; Recurrent neural networks; residual squeeze and excitation block; Sleep; Sleep disorders; Sleep stage; Sleep Stages; State-of-the-art reviews; time sequence encoder; China

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole...