A new approach to eliminating EOG artifacts from the sleep EEG signals for the automatic sleep stage classification

Spintronic Eyeblink Gesture Sensor With Wearable Interface System

This work presents an eyeblink system that detects magnets placed on the eyelid via integrated magnetic sensors and an analogue circuit on an eyewear frame (without a glass lens). The eyelid magnets were detected using tunnelling magnetoresistance (TMR) bridge sensors with a sensitivity of 14 mV/V/Oe and were positioned centre-right and centre-left of the eyewear frame. Each eye side has a single TMR sensor wired to a single circuit, where the signal was filtered (<0.5 Hz and >30 Hz) and amplified to detect the weak magnetic field produced by the 3-millimetre (mm) diameter and 0.5 mm thickness N42 Neodymium magnets attached to a medical tape strip, for the adult-age demographic. Each eyeblink was repeated by a trigger command (right eyeblink) followed by the appropriate command, right, left or both eyeblinks. The eyeblink gesture system has shown repeatability, resulting in blinking classification based on the analogue signal amplitude threshold. As a result, the signal can be scaled and classified as well as, integrated with a Bluetooth module in real-time. This will enable end-users to connect to various other Bluetooth enabled devices for wireless assistive technologies. The eyeblink system was tested by 14 participants via a stimuli-based game. Within an average time of 185-seconds, the system demonstrated a group mean accuracy of 72% for 40 commands. Moreover, the maximum information transfer rate (ITR) of the participants was 35.95 Bits per minute.

Sleep staging classification based on a new parallel fusion method of multiple sources signals

APPROACH

First, the heart rate variability (HRV) is extracted from EOG with the Weight Calculation Algorithm (WCA) and an "HYF" RR interval detection algorithm. Second, three feature sets were extracted from HRV segments and EOG segments: time-domain features, frequency domain features and nonlinear-domain features. The frequency domain features and nonlinear-domain features were extracted by using Discrete Wavelet Transform (DWT), Autoregressive (AR), and Power Spectral entropy (PSE), and Refined Composite Multiscale Dispersion Entropy (RCMDE). Third, a new "Parallel Fusion Method" (PFM) for sleep stage classification is proposed. Three kinds of feature sets from EOG and HRV segments are fused by using PFM. Fourth, Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) classification models is employed for sleep staging.

MAIN RESULTS

Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the new sleep staging approach. The performance of the proposed method is testedby evaluating the average accuracy, Kappa coefficient. The average accuracy of sleep classification results by using XGBoost classification model with PFM is 82.7% and the kappa coefficient is 0.711, also by using SVM classification model with the PFM is 83.7%, and the kappa coefficient is 0.724. Experimental results show that the performance of the proposed method is competitive with the most current methods and results, and the recognition rate of S1 stage is significantly improved. Significance： As a consequence, it would enable one to improve the quality of automatic sleep staging models when the EOG and HRV signals are fused, which can be beneficial for monitor sleep quality and keep abreast of health conditions. Besides, our study provides good research ideas and methods for scholars, doctors and individuals.

A Novel Microwave Treatment for Sleep Disorders and Classification of Sleep Stages Using Multi-Scale Entropy

The aim of this study was to develop an integrated system of non-contact sleep stage detection and sleep disorder treatment for health monitoring. Hence, a method of brain activity detection based on microwave scattering technology instead of scalp electroencephalogram was developed to evaluate the sleep stage. First, microwaves at a specific frequency were used to penetrate the functional sites of the brain in patients with sleep disorders to change the firing frequency of the activated areas of the brain and analyze and evaluate statistically the effects on sleep improvement. Then, a wavelet packet algorithm was used to decompose the microwave transmission signal, the refined composite multiscale sample entropy, the refined composite multiscale fluctuation-based dispersion entropy and multivariate multiscale weighted permutation entropy were obtained as features from the wavelet packet coefficient. Finally, the mutual information-principal component analysis feature selection method was used to optimize the feature set and random forest was used to classify and evaluate the sleep stage. The results show that after four times of microwave modulation treatment, sleep efficiency improved continuously, the overall maintenance was above 80%, and the insomnia rate was reduced gradually. The overall classification accuracy of the four sleep stages was 86.4%. The results indicate that the microwaves with a certain frequency can treat sleep disorders and detect abnormal brain activity. Therefore, the microwave scattering method is of great significance in the development of a new brain disease treatment, diagnosis and clinical application system.

Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG

BACKGROUND AND OBJECTIVE

In recent years, several automatic sleep stage classification methods based on convolutional neural networks (CNN) by learning hierarchical feature representation automatically from raw EEG data have been proposed. However, the state-of-the-art of such methods are quite complex. Using a simple CNN architecture to classify sleep stages is important for portable sleep devices. In addition, employing CNNs to learn rich and diverse representations remains a challenge. Therefore, we propose a novel CNN model for sleep stage classification.

METHODS

Generally, EEG signals are better described in the frequency domain; thus, we convert EEG data to a time-frequency representation via Hilbert-Huang transform. To learn rich and effective feature representations, we propose an orthogonal convolutional neural network (OCNN). First, we construct an orthogonal initialization of weights. Second, to avoid destroying the orthogonality of the weights in the training process, orthogonality regularizations are proposed to maintain the orthogonality of weights. Simultaneously, a squeeze-and-excitation (SE) block is employed to perform feature recalibration across different channels.

RESULTS

The proposed method achieved a total classification accuracy of 88.4% and 87.6% on two public datasets, respectively. The classification performances of different convolutional neural networks models were compared to that of the proposed method. The experiment results demonstrated that the proposed method is effective for sleep stage classification.

CONCLUSIONS

Experiment results indicate that the proposed OCNN can learn rich and diverse feature representations from time-frequency images of EEG data, which is important for deep learning. In addition, the proposed orthogonality regularization is simple and can be easily adapted to other architectures.

Complex-valued unsupervised convolutional neural networks for sleep stage classification

BACKGROUND AND OBJECTIVE

Despite numerous deep learning methods being developed for automatic sleep stage classification, almost all the models need labeled data. However, obtaining labeled data is a subjective process. Therefore, the labels will be different between two experts. At the same time, obtaining labeled data also is a time-consuming task. Even an experienced expert requires hours to annotate the sleep stage patterns. More important, as the development of wearable sleep devices, it is very difficult to obtain labeled sleep data. Therefore, unsupervised training algorithm is very important for sleep stage classification. Hence, a new sleep stage classification method named complex-valued unsupervised convolutional neural networks (CUCNN) is proposed in this study.

METHODS

The CUCNN operates with complex-valued inputs, outputs, and weights, and its training strategy is greedy layer-wise training. It is composed of three phases: phase encoder, unsupervised training and complex-valued classification. Phase encoder is used to translate real-valued inputs into complex numbers. In the unsupervised training phase, the complex-valued K-means is used to learn filters which will be used in the convolution.

RESULTS

The classification performances of handcrafted features are compared with those of learned features via CUCNN. The total accuracy (TAC) and kappa coefficient of the sleep stage from UCD dataset are 87% and 0.8, respectively. Moreover, the comparison experiments indicate that the TACs of the CUCNN from UCD and MIT-BIH datasets outperform these of unsupervised convolutional neural networks (UCNN) by 12.9% and 13%, respectively. Additionally, the convergence of CUCNN is much faster than that of UCNN in most cases.

CONCLUSIONS

The proposed method is fully automated and can learn features in an unsupervised fashion. Results show that unsupervised training and automatic feature extraction on sleep data are possible, which are very important for home sleep monitoring.