3DSleepNet: A Multi-Channel Bio-Signal Based Sleep Stages Classification Method Using Deep Learning

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 31; p. 1
• Main Authors: Ji, Xiaopeng, Li, Yan, Wen, Peng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.01.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3D convolutional networks; Accuracy; Algorithms; Artificial neural networks; Brain modeling; Channels; Classification; Convolution; Convolutional neural networks; Datasets; Deep learning; EEG; Electroencephalography; Electromyography; Feature extraction; Frequencies; Frequency domain analysis; Long short-term memory; Machine learning; Neural networks; Signal classification; Sleep; Sleep disorders; sleep stages classification; Three dimensional models; Three-dimensional displays; Time-frequency analysis; Training
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2023.3309542

A novel multi-channel-based 3D convolutional neural network (3D-CNN) is proposed in this paper to classify sleep stages. Time domain features, frequency domain features, and time-frequency domain features are extracted from electroencephalography (EEG), electromyogram (EMG), and electrooculogram (EOG) channels and fed into the 3D-CNN model to classify sleep stages. Intrinsic connections among different bio-signals and different frequency bands in time series and time-frequency are learned by 3D convolutional layers, while the frequency relations are learned by 2D convolutional layers. Partial dot-product attention layers help this model find the most important channels and frequency bands in different sleep stages. A long short-term memory unit is added to learn the transition rules among neighboring epochs. Classification experiments were conducted using both ISRUC-S3 datasets and ISRUC-S1, sleep-disorder datasets. The experimental results showed that the overall accuracy achieved 0.832 and the F1-score and Cohen's kappa reached 0.814 and 0.783, respectively, on ISRUC-S3, which are a competitive classification performance with the state-of-the-art baselines. The overall accuracy, F1-score, and Cohen's kappa on ISRUC-S1 achieved 0.820, 0.797, and 0.768, respectively, which also demonstrate its generality on unhealthy subjects. Further experiments were conducted on ISRUC-S3 subset to evaluate its training time. The training time on 10 subjects from ISRUC-S3 with 8549 epochs is 4493s, which indicates its highest calculation speed compared with the existing high-performance graph convolutional networks and U2-Net architecture algorithms.