Multi-scale ResNet and BiGRU automatic sleep staging based on attention mechanism

Abstract

Sleep staging is the basis of sleep evaluation and a key step in the diagnosis of sleep-related diseases. Despite being useful, the existing sleep staging methods have several disadvantages, such as relying on artificial feature extraction, failing to recognize temporal sequence patterns in the long-term associated data, and reaching the accuracy upper limit of sleep staging. Hence, this paper proposes an automatic Electroencephalogram (EEG) sleep signal staging model, which based on Multi-scale Attention Residual Nets (MAResnet) and Bidirectional Gated Recurrent Unit (BiGRU). The proposed model is based on the residual neural network in deep learning. Compared with the traditional residual learning module, the proposed model additionally uses the improved channel and spatial feature attention units and convolution kernels of different sizes in parallel at the same position. Thus, multiscale feature extraction of the EEG sleep signals and residual learning of the neural networks is performed to avoid network degradation. Finally, BiGRU is used to determine the dependence between the sleep stages and to realize the automatic learning of sleep data staging features and sleep cycle extraction. According to the experiment, the classification accuracy and kappa coefficient of the proposed method on sleep-EDF data set are 84.24% and 0.78, which are respectively 0.24% and 0.21 higher than the traditional residual net. At the same time, this paper also verified the proposed method on UCD and SHHS data sets, and the figure of classification accuracy is 79.34% and 81.6%, respectively. Compared to related existing studies, the recognition accuracy is significantly improved, which validates the effectiveness and generalization performance of the proposed method.

Power fingerprint identification based on the improved V-I trajectory with color encoding and transferred CBAM-ResNet

“…The ResNet model effectively mitigates degradation and gradient disappearance during model training by stacking the residual structures [ 33 ]. Networks with fewer layers lack certain feature representation capabilities.…”

Speaker identification under noisy conditions using hybrid convolutional neural network and gated recurrent unit

“…Enhanced variants of the RNN model include gated recurrent unit (GRU) [29], long short-term memory (LSTM), and bidirectional LSTM (BiLSTM) [30]. The GRU model is an enhanced version of the LSTM and it has the advantages of extracting and learning long-term correlation between features sequentially in only one direction [31]. GRU models have fewer parameters than LSTM to minimize the computation cost.…”

Automatic sleep staging by a hybrid model based on deep 1D-ResNet-SE and LSTM with single-channel raw EEG signals

“…AttnSleep [17], developed by Eldele et al, is an attention-based deep learning architecture that leverages multi-resolution CNNs to extract low-and high-frequency features of EEG signals, while employs an adaptive feature recalibration technique to improve the quality of the extracted features by modeling the inter-dependencies between them, and uses a multi-head attention mechanism to capture the temporal relationships among sleep stages. In another study, Liu et al [18] employed parallel residual neural networks with improved channel and spatial feature attention units for multi-scale feature extraction of EEG sleep signals, while a bi-directional gated recurrent unit (Bi-GRU) was utilized to determine the dependence between sleep stages. Among the above-mentioned deep learning models, multi-layer architectures of onedimensional convolutional neural networks (1D-CNNs) have been shown to be effective in extracting informative features from EEG signals for sleep staging.…”