Light Sleep Detection based on Surface Electromyography Signals for Nap Monitoring

This paper proposes the development of automatic sleep stage detection by using physiological signals. We aim to develop an application to assist drivers after drowsiness or fatigue detection by a commercial driver vigilance system. The proposed method used a low-cost surface electromyography (EMG) device for sleep stage detection. We investigate skeletal muscle location and EMG features from sleep stage 2 to provide an EMG-based nap monitoring system. The results showed that using only one channel of a bipolar EMG signal from an upper trapezius muscle with median power frequency can achieve 84% accuracy. We implement a MyoWare muscle sensor into the proposed nap monitoring device. The results showed that the proposed system is feasible for detecting sleep stages and waking up the napper. A combination of EMG and electroencephalogram (EEG) signals might be yield a high system performance for nap monitoring and alarm system. We will prototype a portable device to connect the application to a smartphone and test with a target group, such as truck drivers and physicians.

Region-specific complexity of the intracranial EEG in the sleeping human brain

As the brain is a complex system with occurrence of self-similarity at different levels, a dedicated analysis of the complexity of brain signals is of interest to elucidate the functional role of various brain regions across the various stages of vigilance. We exploited intracranial electroencephalogram data from 38 cortical regions using the Higuchi fractal dimension (HFD) as measure to assess brain complexity, on a dataset of 1772 electrode locations. HFD values depended on sleep stage and topography. HFD increased with higher levels of vigilance, being highest during wakefulness in the frontal lobe. HFD did not change from wake to stage N2 in temporo-occipital regions. The transverse temporal gyrus was the only area in which the HFD did not differ between any two vigilance stages. Interestingly, HFD of wakefulness and stage R were different mainly in the precentral gyrus, possibly reflecting motor inhibition in stage R. The fusiform and parahippocampal gyri were the only areas showing no difference between wakefulness and N2. Stages R and N2 were similar only for the postcentral gyrus. Topographical analysis of brain complexity revealed that sleep stages are clearly differentiated in fronto-central brain regions, but that temporo-occipital regions sleep differently.

SCL-SSC: Supervised Contrastive Learning for Sleep Stage Classification

<div>In this study, we have proposed SCL-SSC(Supervised Contrastive Learning for Sleep Stage Classification), a deep learning-based framework for sleep stage classification which performs the task in two stages, 1) feature representation learning, and 2) classification. The feature learner is trained separately to represent the raw EEG signals in the feature space such that the distance between the embedding of EEG signals of the same sleep stage has less than the distance between the embedding of EEG signals of different sleep stages in the euclidean space. On top of feature learners, we have trained the classifier to perform the classification task. The distribution of sleep stages is not uniform in the PSG data, wake(W) and N2 sleep stages appear more frequently than the other sleep stages, which leads to an imbalance dataset problem. This paper addresses this issue by using weighted softmax cross-entropy loss function and also dataset oversampling technique utilized to produce synthetic data points for minority sleep stages for approximately balancing the number of sleep stages in the training dataset. The performance of our proposed model is evaluated on the publicly available Physionet datasets EDF-Sleep 2013 and 2018 versions. We have trained and evaluated our model on two EEG channels (Fpz-Cz and Pz-Oz) on these datasets separately. The evaluation result shows that the performance of SCL-SSC is the best annotation performance compared to the existing state-of art deep learning algorithms to our best of knowledge, with an overall accuracy of 94.1071% with a macro F1 score of 92.6416 and Cohen’s Kappa coefficient(κ) 0.9197. Our ablation studies on SCL-SSC shows that both triplet loss based pre-training of feature learner and oversampling of minority classes are contributing to better performance of the model(SCL-SSC).</div>

SCL-SSC: Supervised Contrastive Learning for Sleep Stage Classification

<div>In this study, we have proposed SCL-SSC(Supervised Contrastive Learning for Sleep Stage Classification), a deep learning-based framework for sleep stage classification which performs the task in two stages, 1) feature representation learning, and 2) classification. The feature learner is trained separately to represent the raw EEG signals in the feature space such that the distance between the embedding of EEG signals of the same sleep stage has less than the distance between the embedding of EEG signals of different sleep stages in the euclidean space. On top of feature learners, we have trained the classifier to perform the classification task. The distribution of sleep stages is not uniform in the PSG data, wake(W) and N2 sleep stages appear more frequently than the other sleep stages, which leads to an imbalance dataset problem. This paper addresses this issue by using weighted softmax cross-entropy loss function and also dataset oversampling technique utilized to produce synthetic data points for minority sleep stages for approximately balancing the number of sleep stages in the training dataset. The performance of our proposed model is evaluated on the publicly available Physionet datasets EDF-Sleep 2013 and 2018 versions. We have trained and evaluated our model on two EEG channels (Fpz-Cz and Pz-Oz) on these datasets separately. The evaluation result shows that the performance of SCL-SSC is the best annotation performance compared to the existing state-of art deep learning algorithms to our best of knowledge, with an overall accuracy of 94.1071% with a macro F1 score of 92.6416 and Cohen’s Kappa coefficient(κ) 0.9197. Our ablation studies on SCL-SSC shows that both triplet loss based pre-training of feature learner and oversampling of minority classes are contributing to better performance of the model(SCL-SSC).</div>

Sleep Stage Classification For Medical Purposes: Machine Learning Evaluation For Imbalanced Data

Background: Sleep is commonly associated with physical and mental health status. Sleep quality can be determined from the dynamic of sleep stages during the night. Data from the wearable device can potentially be used as predictors to classify the sleep stage. Robust Machine Learning (ML) model is needed to learn the pattern within wearable data to be associated with the sleep-wake classification, especially to handle the imbalanced proportion between wake and sleep stages. In this study, we incorporated a publicy available dataset consists of three features captured from a consumer wearable device and the labelled sleep stages from a polysomnogram. We implemented Random Forest, Support Vector Machine , Extreme Gradiet Boosting Tree, Densed Neural Network (DNN), and Long Short-Term Memory (LSTM), complemented by three strategies to handle the imbalanced data problem. Results: In total, we included more than 24,815 rows of preprocessed data from 31 samples. The proportion of minority-majority data is 1:10. In classifying this extreme imbalanced data, the DNN model was found to have the best performance compared to the previous best model, which is based on basic Multi-Layer Perceptron. Our best model successfully achieved a 12% higher specificity score (prediction score for minority class) and 1% improvement on the sensitivity score (prediction score for majority class) by including all features in the model. This achievement was affected by the implementation of custom class weight and oversampling strategy. In contrast, when we only used two features, XGB achieved a specificity improvement only by 1%, while keeping the sensitivity at the same level.Conclusions: The non-linear operation within the DNN model could successfully learn the hidden pattern from the combination of three features. Additionally, the class weight parameter avoided the model ignoring the minority class by giving more weight for this class in the loss function. The feature engineering process seemed to obscure the time-series characteristics within the data. This is why LSTM, as one of the best methods for time-series data, failed to perform well in this classification task.

Novel Methods for Elucidating Modality Importance in Multimodal Electrophysiology Classifiers

Multimodal classification is increasingly common in biomedical informatics studies. Many such studies use deep learning classifiers with raw data, which makes explainability difficult. As such, only a few studies have applied explainability methods, and new methods are needed. In this study, we propose sleep stage classification as a testbed for method development and train a convolutional neural network with electroencephalogram (EEG), electrooculogram, and electromyogram data. We then present a global approach that is uniquely adapted for electrophysiology analysis. We further present two local approaches that can identify subject-level differences in explanations that would be obscured by global methods and that can provide insight into the effects of clinical and demographic variables upon the patterns learned by the classifier. We find that EEG is globally the most important modality for all sleep stages, except non-rapid eye movement stage 1 and that local subject-level differences in importance arise. We further show that sex, followed by medication and age had significant effects upon the patterns learned by the classifier. Our novel methods enhance explainability for the growing field of multimodal classification, provide avenues for the advancement of personalized medicine, and yield novel insights into the effects of demographic and clinical variables upon classifiers.

Extreme sleep fragmentation for 11 consecutive days and nights does not significantly alter total sleep time, and sleep stage distribution, during the continuous alpine downhill skiing world record

Introduction: Extreme levels of sleep deprivation, fragmentation and management, are major problems in many sportive disciplines, ultramarathons, polar or extreme altitude expeditions, and in space operations. Material and methods: Polysomnographic (PSG) data was continuously recorded (total sleep time and sleep stage distribution) in a 34-year-old male whilst performing the new world record in long-term downhill skiing. He napped only during the short ski lift rides for 11 days and nights. Results: After an initial period of complete sleep deprivation for 24 hours, total sleep time and the total times of non-REM and REM achieved during the lift rides returned to standard values on the second day. PSG data revealed an average sleep time per 24 hours of 6 hours and 6 minutes. During daylight sleep was rarely registered. The subject experienced only two minor falls without injury and immediately resumed skiing. Conclusion: In a healthy, trained, elite male athlete, sleep fragmentation over 11 consecutive days did not significantly impair the sleep, motor or cognitive skills required to perform a continuous downhill skiing world record after an initial adaptation phase.