Sleep experts manually label sleep stages via polysomnography (PSG) to diagnose sleep disorders. However, this process is time-consuming, requires a lot of labor from sleep experts, and makes the participants uncomfortable with the attachment of multiple sensors. Thus, automatic sleep scoring methods are essential for practical sleep monitoring in our daily lives. In this study, we propose an automatic sleep scoring model based on intrinsic oscillations in a single channel electroencephalogram (EEG) signal. We applied noise assisted bivariate empirical mode decomposition (NA-BEMD) to extract the intrinsic mode components and an attention mechanism in deep neural networks to provide weights to the components depending on their significance to sleep scoring. In particular, through the attention mechanism, we found an interpretable model by examining the oscillations that correspond to specific sleep stages. Therefore, we analyzed which frequency components are more weighted to a sleep stage than the others, when the model classifies sleep stages, and, as a result, confirmed that the model assigns convincing weights to the frequency components for each sleep stage. Additionally, the model consists of a one-dimensional convolutional neural network (1D-CNN) to extract features of an epoch and bidirectional long short-term memory (Bi-LSTM) to learn the sequential information of the consecutive epochs. We evaluated proposed model using Fpz-Cz, Pz-Oz, and F3-M2 channel EEG from three different public datasets (Sleep-EDF-2013, Sleep-EDF-2018 and demonstrated that our model yielded the best overall accuracy (Fpz-Cz: 86.22%-82.67%, Pz-Oz: 83.63%-80.15%, F3-M2: 84.20%) and macro F1-score (Fpz-Cz: 80.79%-76.90%, Pz-Oz: 76.89%-72.98%, F3-M2: 74.88%) compared with the state-of-the-art sleep scoring algorithms using single channel EEG. As a benchmark test, FIR bandpass filters were compared, and it was confirmed that NA-BEMD was superior to the traditional filters in all experiments, demonstrating that the proposed model is interpretable and a state-of-the-art sleep scoring algorithm.INDEX TERMS Electroencephalogram (EEG), automatic sleep scoring, deep neural networks, attention mechanism, bivariate empirical mode decomposition.

In this study, we analyze the effect of a recliner chair with rocking motions on sleep quality of naps using automated sleep scoring and spindle detection models. The quality of sleep corresponding to the two rocking motions was measured quantitatively and qualitatively. For the quantitative evaluation, we conducted a sleep parameter analysis based on the results of the estimated sleep stages obtained on the brainwave and spindle estimation, and a sleep survey assessment from the participants was analyzed for the qualitative evaluation. The analysis showed that sleep in the recliner chair with rocking motions positively increased the duration of the spindles and deep sleep stage, resulting in improved sleep quality.

Wearable technologies are known to improve our quality of life. Among the various wearable devices, shoes are non-intrusive, lightweight, and can be used for outdoor activities. In this study, we estimated the energy consumption and heart rate in an environment (i.e., running on a treadmill) using smart shoes equipped with triaxial acceleration, triaxial gyroscope, and four-point pressure sensors. The proposed model uses the latest deep learning architecture which does not require any separate preprocessing. Moreover, it is possible to select the optimal sensor using a channel-wise attention mechanism to weigh the sensors depending on their contributions to the estimation of energy expenditure (EE) and heart rate (HR). The performance of the proposed model was evaluated using the root mean squared error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). Moreover, the RMSE was 1.05 ± 0.15, MAE 0.83 ± 0.12 and R2 0.922 ± 0.005 in EE estimation. On the other hand, and RMSE was 7.87 ± 1.12, MAE 6.21 ± 0.86, and R2 0.897 ± 0.017 in HR estimation. In both estimations, the most effective sensor was the z axis of the accelerometer and gyroscope sensors. Through these results, it is demonstrated that the proposed model could contribute to the improvement of the performance of both EE and HR estimations by effectively selecting the optimal sensors during the active movements of participants.

In this study, the optimal features of electrocardiogram (ECG) signals were investigated for the implementation of a personal authentication system using a reinforcement learning (RL) algorithm. ECG signals were recorded from 11 subjects for 6 days. Consecutive 5-day datasets (from the 1st to the 5th day) were trained, and the 6th dataset was tested. To search for the optimal features of ECG for the authentication problem, RL was utilized as an optimizer, and its internal model was designed based on deep learning structures. In addition, the deep learning architecture in RL was automatically constructed based on an optimization approach called Bayesian optimization hyperband. The experimental results demonstrate that the feature selection process is essential to improve the authentication performance with fewer features to implement an efficient system in terms of computation power and energy consumption for a wearable device intended to be used as an authentication system. Support vector machines in conjunction with the optimized RL algorithm yielded accuracy outcomes using fewer features that were approximately 5%, 3.6%, and 2.6% higher than those associated with information gain (IG), ReliefF, and pure reinforcement learning structures, respectively. Additionally, the optimized RL yielded mostly lower equal error rate (EER) values than the other feature selection algorithms, with fewer selected features.

No abstract