Sleep-EDF Dataset Research Articles

Detection of Sleeping Pattern Using EEG Signals with Deep Learning

Background: Recorded brain activity analysis is a major tool used in modern medicine and sleep-based research. However, the volume and complexity of the data make manual investigation difficult. Furthermore, high inter-subject variability presents a challenge to deep learning techniques, especially in the detection of sleep-related EEG patterns and artifacts. Methods: Sleep Pattern Identifier (SPI), a hybrid classifier, was used in this study to address the aforementioned issues. SPI tests the efficacy of artifact detection while examining strategies and tactics used in real-world sleep research. A focus was on inter-subject variability, especially in data gathered from participants suffering from sleep disorders. For comparison and visual inspection of the data, formal statistical measures like accuracy, model loss, precision, recall, and ROC were employed. Results: With an accuracy of 94.85%, the suggested model outperformed current techniques and demonstrated higher accuracy. Further, the Sleep-EDF dataset was used in this investigation. Conclusion: The conclusion highlights the effectiveness of the SPI hybrid classifier in identifying EEG patterns, especially in situations where sleep research is conducted in the real world. Research methodologies based on sleep have made significant progress in handling artifacts and adapting to inter-subject variability.

Sleep stages classification by fusing the time-related synchronization analysis and brain activations

Sleep staging plays an important role in the diagnosis and treatment of clinical sleep disorders. The sleep staging standard defines every 30 seconds as a sleep period, which may mean that there exist similar brain activity patterns during the same sleep period. Thus, in this work, we propose a novel time-related synchronization analysis framework named time-related multimodal sleep scoring model (TRMSC) to explore the potential time-related patterns of sleeping. In the proposed TRMSC, the time-related synchronization analysis is first conducted on the single channel electrophysiological signal, i.e., Electroencephalogram (EEG) and Electrooculogram (EOG), to explore the time-related patterns, and the spectral activation features are also extracted by spectrum analysis to obtain the multimodal features. With the extracted multimodal features, the feature fusion and selection strategy is utilized to obtain the optimal feature set and achieve robust sleep staging. To verify the effectiveness of the proposed TRMSC, sleep staging experiments were conducted on the Sleep-EDF dataset, and the experimental results indicate that the proposed TRMSC has achieved better performance than other existing strategies, which proves that the time-related synchronization features can make up for the shortcomings of traditional spectrum-based strategies and achieve a higher classification accuracy. The proposed TRMSC model may be helpful for portable sleep analyzers and provide a new analytical method for clinical sleeping research.

ZleepAnlystNet: a novel deep learning model for automatic sleep stage scoring based on single-channel raw EEG data using separating training.

Numerous models for sleep stage scoring utilizing single-channel raw EEG signal have typically employed CNN and BiLSTM architectures. While these models, incorporating temporal information for sequence classification, demonstrate superior overall performance, they often exhibit low per-class performance for N1-stage, necessitating an adjustment of loss function. However, the efficacy of such adjustment is constrained by the training process. In this study, a pioneering training approach called separating training is introduced, alongside a novel model, to enhance performance. The developed model comprises 15 CNN models with varying loss function weights for feature extraction and 1 BiLSTM for sequence classification. Due to its architecture, this model cannot be trained using an end-to-end approach, necessitating separate training for each component using the Sleep-EDF dataset. Achieving an overall accuracy of 87.02%, MF1 of 82.09%, Kappa of 0.8221, and per-class F1-socres (W 90.34%, N1 54.23%, N2 89.53%, N3 88.96%, and REM 87.40%), our model demonstrates promising performance. Comparison with sleep technicians reveals a Kappa of 0.7015, indicating alignment with reference sleep stags. Additionally, cross-dataset validation and adaptation through training with the SHHS dataset yield an overall accuracy of 84.40%, MF1 of 74.96% and Kappa of 0.7785 when tested with the Sleep-EDF-13 dataset. These findings underscore the generalization potential in model architecture design facilitated by our novel training approach.

Algorithm for drowsiness detection based on hybrid brain network parameter optimization

Drowsiness detection is a test designed to detect a person’s reaction ability and speed while in a state of fatigue. This type of drowsiness detection has many practical applications in areas like driver monitoring, transportation industry, and workplace safety. In this paper, a new machine learning drowsiness detection algorithm based on hybrid brain network feature extraction is proposed. First, the raw electroencephalogram signals are segmented into 30 s epochs, which are decomposed with wavelet packet transform into 7 layers to extract 30 s sleep characteristic subbands and the 7-th layer subbands. After that, 30 s subbands are divided into 5 s subbands with 50% overlap. At the same time, 30 s subbands are reconstructed by phase space reconstruction (PSR), whose parameters are optimized through energy valley optimizer. Then, based on mutual information and horizontal visual graph, a hybrid brain network is constructed with the 7-th layer subbands, 5 s subbands and PSR subbands, respectively. Finally, network features and time–frequency features are extracted and input into random forest classifier. The performance of the algorithm is evaluated through two tests: subject-independent test and subject-non-independent test. The results show that in Sleep-EDF dataset, accuracy, κ coefficient, recall, precision and F1-score obtained by the proposed algorithm can reach 94.19%, 88.39%, 95.37%, 92.53% and 93.93%, respectively. In Sleep-EDF Expanded dataset, accuracy, κ coefficient, recall, precision and F1-score can reach 93.65%, 87.65%, 94.53%, 92.11%, and 92.89%, respectively.

Research on the application of the Sleep EEG Net model based on domain adaptation transfer in the detection of driving fatigue

Fatigue detection in driving faces challenges stemming from data scarcity and difficulty in data acquisition, which poses a significant challenge to traditional fatigue detection methods. To address this issue, this study introduces a Sleep EEG Net model based on domain adaptation transfer learning. This model was pre-trained using the publicly available Sleep-EDF dataset, and domain adaptation transfer training techniques were employed to train the feature extractor of the pre-trained model, enabling cross-domain knowledge transfer. As a result, the model has been successfully applied to the task of fatigue detection in driving with only a limited amount of fatigue driving data. Experimental results demonstrate that this approach achieves a recognition accuracy of 91.5% in fatigue detection tasks. Furthermore, the model exhibits strong generalization capabilities and robustness, achieving high recognition accuracy in both simulated and real driving environments, thereby validating its effectiveness in practical applications.

Multivariate phase space reconstruction and Riemannian manifold for sleep stage classification

Background and ObjectiveSleep was highly imperative in human daily life. However, an increasing number of people were undergoing sleep deprivation and sleep disorders. Sleep stage classification became a highly essential process in sleep scoring. Nevertheless, the visual scoring of arousals during sleep routinely performed by sleep specialists was a challenging exercise. MethodsThis paper introduced a novel approach for sleep stage classification using covariance feature matrix architecture with multivariate phase space reconstruction (MPSR). The goal was to capture the geometric properties and the hidden dynamic characteristics of multiple physiological signals. The covariance matrices constructed through the MPSR approach were considered as symmetric and positive definite (SPD) matrices, forming a Riemannian manifold space. These SPD matrices in the Riemannian manifold were mapped to the matrices in the tangent space, allowing them to be vectorized and treated as feature vectors in Euclidean space. Finally, an ensemble learning classifier was applied to perform various sleep stage tasks. ResultsOur proposed method was evaluated on three benchmark datasets to assess its effectiveness and robustness. For the tasks of both Five class and Six class sleep stages, the proposed approach in ten-fold cross validation achieved high accuracy of 93.57% and 92.56% for the Sleep EDF dataset, 86.36% and 84.18% for the DREAMS Subjects dataset, as well as 88.93% and 88.42% for the Sleep EDF Expanded dataset (95 subjects), respectively. In leave-one-subject-out cross validation, our proposed approach for the tasks of both Five class and Six class sleep stages yielded an accuracy of 84.46% and 80.73% for the Sleep EDF dataset, 82.50% and 79.51% for the DREAMS Subjects dataset, as well as 93.25% and 92.06% for the Sleep EDF Expanded-20 dataset (20 subjects), respectively. ConclusionCompared to the traditional sample covariance matrix (SCM), the covariance feature matrix using the MPSR method successfully captured the distinction of spatial information among various sleep stages. Moreover, our proposed method obtained good performance without requiring computationally large artifact suppression or a long signal decomposition process.

Self-Supervised Electroencephalogram Representation Learning for Automatic Sleep Staging: Model Development and Evaluation Study.

Deep learning models have shown great success in automating tasks in sleep medicine by learning from carefully annotated electroencephalogram (EEG) data. However, effectively using a large amount of raw EEG data remains a challenge. In this study, we aim to learn robust vector representations from massive unlabeled EEG signals, such that the learned vectorized features (1) are expressive enough to replace the raw signals in the sleep staging task, and (2) provide better predictive performance than supervised models in scenarios involving fewer labels and noisy samples. We propose a self-supervised model, Contrast with the World Representation (ContraWR), for EEG signal representation learning. Unlike previous models that use a set of negative samples, our model uses global statistics (ie, the average representation) from the data set to distinguish signals associated with different sleep stages. The ContraWR model is evaluated on 3 real-world EEG data sets that include both settings: at-home and in-laboratory EEG recording. ContraWR outperforms 4 recently reported self-supervised learning methods on the sleep staging task across 3 large EEG data sets. ContraWR also supersedes supervised learning when fewer training labels are available (eg, 4% accuracy improvement when less than 2% of data are labeled on the Sleep EDF data set). Moreover, the model provides informative, representative feature structures in 2D projection. We show that ContraWR is robust to noise and can provide high-quality EEG representations for downstream prediction tasks. The proposed model can be generalized to other unsupervised physiological signal learning tasks. Future directions include exploring task-specific data augmentations and combining self-supervised methods with supervised methods, building upon the initial success of self-supervised learning reported in this study.

Sleep Track: Automated Detection and Classification of Sleep Stages

Sleep is vital for our body’s physical restoration, but sleep disorders can cause various problems. Determining sleep stages is essential for diagnosing and curing such disorders. Polysomnography (PSG) signals are recordings of brain activity, eye movements, muscle activity and other physiological signals that are collected during a sleep study. Insomnia, Sleep Apnea, and Restless Legs Syndrome are some of the sleep problems that can be identified using these signals. However, analysing PSG signals manually can be time-consuming and prone to errors. Deep Learning Models such as Convolutional Neural Networks (CNN), can be used to automate the analysis of PSG signals. CNN is followed by Long-Short Term Memory (LSTM) and CNN are used as a stack ensemble method to recognize patterns in the signals that correspond to different sleep stages and events. By training these models on large datasets of PSG signals, they can detect the disorders. The dataset is collected from PhysioNet Sleep-EDF dataset that consists of PSG signals. The accuracies obtained using different training and testing data using CNN and CNN-LSTM are 95.15% and 83.9% respectively, and using metadata classifier the overall accuracy is increased by 1%. The future enhancement of the paper can be done by considering Heart rate, EEG Pz-oz signals and EEG Pz-oz along with EEG Fpz-cz.

SleepXAI: An explainable deep learning approach for multi-class sleep stage identification

Extensive research has been conducted on the automatic classification of sleep stages utilizing deep neural networks and other neurophysiological markers. However, for sleep specialists to employ models as an assistive solution, it is necessary to comprehend how the models arrive at a particular outcome, necessitating the explainability of these models. This work proposes an explainable unified CNN-CRF approach (SleepXAI) for multi-class sleep stage classification designed explicitly for univariate time-series signals using modified gradient-weighted class activation mapping (Grad-CAM). The proposed approach significantly increases the overall accuracy of sleep stage classification while demonstrating the explainability of the multi-class labeling of univariate EEG signals, highlighting the parts of the signals emphasized most in predicting sleep stages. We extensively evaluated our approach to the sleep-EDF dataset, and it demonstrates the highest overall accuracy of 86.8% in identifying five sleep stage classes. More importantly, we achieved the highest accuracy when classifying the crucial sleep stage N1 with the lowest number of instances, outperforming the state-of-the-art machine learning approaches by 16.3%. These results motivate us to adopt the proposed approach in clinical practice as an aid to sleep experts.

Local Pattern Transformation-Based convolutional neural network for sleep stage scoring

Sleep stage scoring is essential for the diagnosis and treatment of sleep disorders. However, manual sleep scoring is a tedious, time-consuming, and subjective task. Therefore, this paper proposes a novel framework based on local pattern transformation (LPT) methods and convolutional neural networks for automatic sleep stage scoring. Unlike in previous works in other fields, these methods were not employed for manual feature extraction, which requires expert knowledge and the pipeline behind it might bias results. The transformed signals were directly fed into a CNN model (called EpochNet) that can accept multiple successive epochs. The model learns features from multiple input epochs and considers inter-epoch context during classification. To evaluate and validate the effectiveness of the proposed approach, we conducted several experiments on the Sleep-EDF dataset. Four LPT methods, including One-dimensional Local Binary Pattern (1D-LBP), Local Neighbor Descriptive Pattern (LNDP), Local Gradient Pattern (LGP), and Local Neighbor Gradient Pattern (LNGP), and different polysomnography (PSG) signals were analyzed as sequence length (number of input epochs) increased from one to five. 1D-LBP and LNDP achieved similar performances, outperforming other LPT methods that are less sensitive to local variations. The best performance was achieved when an input sequence containing five epochs of PSG signals transformed by 1D-LBP was employed. The best accuracy, F1 score, and Kohen's kappa coefficient were 0.848, 0.782, and 0.790, respectively. The results showed that our approach can achieve comparable performance to other state-of-the-art methods while occupying fewer computing resources because of the compact size of EpochNet.

Deep Learning Model of Sleep EEG Signal by Using Bidirectional Recurrent Neural Network Encoding and Decoding

Electroencephalogram (EEG) is a signal commonly used for detecting brain activity and diagnosing sleep disorders. Manual sleep stage scoring is a time-consuming task, and extracting information from the EEG signal is difficult because of the non-linear dependencies of time series. To solve the aforementioned problems, in this study, a deep learning model of sleep EEG signal was developed using bidirectional recurrent neural network (BiRNN) encoding and decoding. First, the input signal was denoised using the wavelet threshold method. Next, feature extraction in the time and frequency domains was realized using a convolutional neural network to expand the scope of feature extraction and preserve the original EEG feature information to the maximum extent possible. Finally, the time-series information was mined using the encoding–decoding module of the BiRNN, and the automatic discrimination of the sleep staging of the EEG signal was realized using the SoftMax function. The model was cross-validated using Fpz-Cz single-channel EEG signals from the Sleep-EDF dataset for 19 nights, and the results demonstrated that the proposed model can achieve a high recognition rate and stability.

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

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.

A novel sleep staging network based on multi-scale dual attention

Sleep is extremely important for protecting people’s mental and physical health. Once the sleep disorder occurs, people’s lives will be greatly affected. Sleep staging plays an important role in the diagnosis of sleep disorders. In general, experts classify sleep stages manually based on polysomnography (PSG), which is quite time-consuming. Meanwhile, the acquisition process of multiple signals is much complex, which can affect the subject’s sleep. Therefore, the use of single-channel electroencephalogram (EEG) for automatic sleep staging has become a popular research topic. For EEG signals, several in-siding salient waveforms used to distinguish sleep stages generally have different scales, and a single-scale convolutional neural network(CNN) cannot fully capture the salient waveforms features. To address this issue, we proposed a multiscale dual attention network (MSDAN) based on raw EEG, which utilizes a 1d CNN to automatically extract features from raw EEG. Experiments were conducted using two datasets with 20-fold cross-validation and hold-out validation method. The final average accuracy, overall accuracy, macro F1 score and Cohen’s Kappa coefficient of the model reach 96.70%, 91.74%, 0.8231 and 0.8723 on the Sleep-EDF dataset, 96.14%, 90.35%, 0.7945 and 0.8284 on the Sleep-EDFx dataset. The results show the superiority of our network over the existing methods, reaching state-of-the-arts.

Learned Factor Graphs for Inference From Stationary Time Sequences

The design of methods for inference from time sequences has traditionally relied on statistical models that describe the relation between a latent desired sequence and the observed one. A broad family of model-based algorithms have been derived to carry out inference at controllable complexity using recursive computations over the factor graph representing the underlying distribution. An alternative model-agnostic approach utilizes machine learning (ML) methods. Here we propose a framework that combines model-based algorithms and data-driven ML tools for stationary time sequences. In the proposed approach, neural networks are developed to separately learn specific components of a factor graph describing the distribution of the time sequence, rather than the complete inference task. By exploiting stationary properties of this distribution, the resulting approach can be applied to sequences of varying temporal duration. Learned factor graphs can be realized using compact neural networks that are trainable using small training sets, or alternatively, be used to improve upon existing deep inference systems. We present an inference algorithm based on learned stationary factor graphs, which learns to implement the sum-product scheme from labeled data, and can be applied to sequences of different lengths. Our experimental results demonstrate the ability of the proposed learned factor graphs to learn from small training sets to carry out accurate inference for sleep stage detection using the Sleep-EDF dataset, as well as for symbol detection in digital communications with unknown channels.

DSSNet: A Deep Sequential Sleep Network for Self-Supervised Representation Learning Based on Single-Channel EEG

Sleep staging by highly trained specialists is laborious. Although automatic sleep staging with supervised learning methods has been implemented for almost a decade, it requires lots of manually annotated data. Self-supervised learning methods have recently been gaining attention. They can learn representations with unlabeled data, which alleviates the cost of labeling work. However, the problem is that these self-supervised sleep staging methods either require prior knowledge, as with frequency information, or they produce unsatisfactory results. Thus, we propose a deep sequential sleep network (DSSNet), a self-supervised framework that aims to perform multi-view representations based on contrastive learning. It utilizes a single-channel electroencephalogram but achieves competitive performance. We also explore the impact of different contrastive mechanisms on DSSNet performance. The results of the Sleep-EDF dataset prove that the consistency of negative samples is crucial for improving performance. We evaluate DSSNet on Sleep-EDF and ISRUC-Sleep and achieve accuracies of 80.0% and 71.4%.

Reliable sleep staging of unseen subjects with fusion of multiple EEG features and RUSBoost

Extensive experiments have been carried out in this study to classify sleep EEG from three different standard databases – Sleep EDF, DREAMS and Expanded sleep EDF databases. Both two-class (sleep-awake) and multiclass classifications have been performed using a fusion of various EEG features and an ensemble classifier called random undersampling with boosting technique (RUSBoost). The results achieved using a single channel EEG are comparable or better than the state-of-the-art methods in the literature for both types of classification, on all the databases. Two-class classification is useful to determine the preferred timings for sensory stimulation of patients with disorders of consciousness. 10-fold cross-validation accuracies of 92.6% and 97.9% have been obtained on Sleep EDF database for 6-class and 2-class problems, respectively. Using Expanded Sleep-EDF dataset, the accuracies improved to 96.3% for 6-state and 99.8% for 2-state classification. For DREAMS dataset, we achieved an accuracy of 96.6% for 2-state classification. Unlike most research in the literature where performance on unseen subjects is not considered, we report classification results on the data from unseen test subjects using both 50%-holdout and leave-one-out cross-validation approaches. Similar results were achieved using both validation techniques for different datasets emphasizing the reliability of our method. These results are very crucial for the method to be applicable for clinical use.

Automatic Sleep Staging Algorithm Based on Time Attention Mechanism.

The most important part of sleep quality assessment is the automatic classification of sleep stages. Sleep staging is helpful in the diagnosis of sleep-related diseases. This study proposes an automatic sleep staging algorithm based on the time attention mechanism. Time-frequency and non-linear features are extracted from the physiological signals of six channels and then normalized. The time attention mechanism combined with the two-way bi-directional gated recurrent unit (GRU) was used to reduce computing resources and time costs, and the conditional random field (CRF) was used to obtain information between tags. After five-fold cross-validation on the Sleep-EDF dataset, the values of accuracy, WF1, and Kappa were 0.9218, 0.9177, and 0.8751, respectively. After five-fold cross-validation on the our own dataset, the values of accuracy, WF1, and Kappa were 0.9006, 0.8991, and 0.8664, respectively, which is better than the result of the latest algorithm. In the study of sleep staging, the recognition rate of the N1 stage was low, and the imbalance has always been a problem. Therefore, this study introduces a type of balancing strategy. By adopting the proposed strategy, SEN-N1 and ACC of 0.7 and 0.86, respectively, can be achieved. The experimental results show that compared to the latest method, the proposed model can achieve significantly better performance and significantly improve the recognition rate of the N1 period. The performance comparison of different channels shows that even when the EEG channel was not used, considerable accuracy can be obtained.

Unsupervised sleep staging system based on domain adaptation

Currently, most deep-learning-based sleep staging system relies heavily on a large number of labeled physiological signals. However, sleep-related data, such as polysommography (PSG), are often manually labeled by one or more than one professional experts with much effort. Meanwhile, due to physiological differences that existed among different subjects, how to boost the performance of trained models on an unseen dataset is still an open issue. One potential solution to this issue is to borrow knowledge from a labeled dataset to train an unlabeled or few labeled dataset by way of unsupervised or semi-unsupervised domain adaptation. To overcome the problem of insufficient labeled data for training robust sleep staging systems, this study aims to investigate the training of an unlabeled target sleep dataset from a labeled source sleep dataset in a deep learning framework, which integrates a conditional and collaborative adversarial domain adaptation module. To facilitate the network to learn domain-invariant features, a domain classifier is deployed for each feature extraction block at different scale. The input to the domain classifier at different level is the multilinear mapping of the sleep stage prediction vector and the corresponding feature vector at this level. It is assumed that the feedback of the class information provided by the network into the domain classifier can be beneficial to help the network to reduce the feature distribution distance between different domains. Experiments on public Sleep-EDF dataset demonstrate the effectiveness of the proposed approach. Compared to other domain adaptation approaches, the proposed approaches can provide better sleep staging performance in different model transferring tasks.

Machine learning with ensemble stacking model for automated sleep staging using dual-channel EEG signal

Sleep staging is an important part of diagnosing the different types of sleep-related disorders because any discrepancies in the sleep scoring process may cause serious health problems such as misinterpretations of sleep patterns, medication errors, and improper diagnosis. The best way of analyzing sleep staging is visual interpretations of the polysomnography (PSG) signals recordings from the patients, which is a quite tedious task, requires more domain experts, and time-consuming process. This proposed study aims to develop a new automated sleep staging system using the brain EEG signals. Based on a new automated sleep staging system based on an ensemble learning stacking model that integrates Random Forest (RF) and eXtreme Gradient Boosting (XGBoosting). Additionally, this proposed methodology considers the subjects’ age, which helps analyze the S1 sleep stage properly. In this study, both linear (time and frequency) and non-linear features are extracted from the pre-processed signals. The most relevant features are selected using the ReliefF weight algorithm. Finally, the selected features are classified through the proposed two-layer stacking model. The proposed methodology performance is evaluated using the two most popular datasets, such as the Sleep-EDF dataset (S-EDF) and Sleep Expanded-EDF database (SE-EDF) under the Rechtschaffen & Kales (R&K) sleep scoring rules. The performance of the proposed method is also compared with the existing published sleep staging methods. The comparison results signify that the proposed sleep staging system has an excellent improvement in classification accuracy for the six-two sleep states classification. In the S-EDF dataset, the overall accuracy and Cohen’s kappa coefficient score obtained by the proposed model is (91.10%, 0.87) and (90.68%, 0.86) with inclusion and exclusion of age feature using the Fpz-Cz channel, respectively. Similarly, the Pz-Oz channel’s performance is (90.56%, 0.86) with age feature and (90.11%, 0.86) without age feature. The performed results with the SE-EDF dataset using Fpz-Cz channel is (81.32%, 0.77) and (81.06%, 0.76), using Pz-Oz channel with the inclusion and exclusion of the age feature, respectively. Similarly the model achieved an overall accuracy of 96.67% (CT-6), 96.60% (CT-5), 96.28% (CT-4),96.30% (CT-3) and 97.30% (CT-2) for with 16 selected features using S-EDF database. Similarly the model reported an overall accuracy of 85.85%, 84.98%, 85.51%, 85.37% and 87.40% for CT-6 to CT-2 with 18 selected features using SE-EDF database.

CCRRSleepNet: A Hybrid Relational Inductive Biases Network for Automatic Sleep Stage Classification on Raw Single-Channel EEG

In the inference process of existing deep learning models, it is usually necessary to process the input data level-wise, and impose a corresponding relational inductive bias on each level. This kind of relational inductive bias determines the theoretical performance upper limit of the deep learning method. In the field of sleep stage classification, only a single relational inductive bias is adopted at the same level in the mainstream methods based on deep learning. This will make the feature extraction method of deep learning incomplete and limit the performance of the method. In view of the above problems, a novel deep learning model based on hybrid relational inductive biases is proposed in this paper. It is called CCRRSleepNet. The model divides the single channel Electroencephalogram (EEG) data into three levels: frame, epoch, and sequence. It applies hybrid relational inductive biases from many aspects based on three levels. Meanwhile, multiscale atrous convolution block (MSACB) is adopted in CCRRSleepNet to learn the features of different attributes. However, in practice, the actual performance of the deep learning model depends on the nonrelational inductive biases, so a variety of matching nonrelational inductive biases are adopted in this paper to optimize CCRRSleepNet. The CCRRSleepNet is tested on the Fpz-Cz and Pz-Oz channel data of the Sleep-EDF dataset. The experimental results show that the method proposed in this paper is superior to many existing methods.