Single-channel EEG Research Articles

Automatic Sleep Staging Based on Contextual Scalograms and Attention Convolution Neural Network Using Single-Channel EEG.

Single-channel EEG based sleep staging is of interest to researchers due to its broad application prospect in daily sleep monitoring recently. We proposed using contextual scalograms as input and developed a convolutional neural network with attention modules named Co-ScaleNet for sleep staging. The contextual scalograms were obtained by combining the same color channels of three original RGB scalograms from consecutive epochs, and a simple and efficient data augmentation was designed according to their various forms. The Co-ScaleNet consists of two main parts. Firstly, three parallel convolutional branches with attention modules correspondingly extract and fuse features from contextual scalograms at the top layers. The remaining part is a stack of lightweight blocks. We achieved an overall accuracy of 87.0% for healthy individuals, 84.7% for depressed patients. And we obtained comparable performance on the public Sleep-EDFx (82.8%), ISRUC (84.6%) and SHHS datasets (87.7%), including a high recall of N1. The contextual scalograms of R channel as input achieved the best performance, which conform to the features of interest in visual scoring. The attention modules improved the recall of N1 and N3. Overall, the contextual scalograms provided a novel scheme for both contextual information extraction and data augmentation. Our study successfully expanded its application to depression datasets, as well as patients with sleep apnea, demonstrating its wide applicability.

Abnormally low sensorimotor α band nonlinearity serves as an effective EEG biomarker of Parkinson's disease.

Biomarkers obtained from the neurophysiological signals of patients with Parkinson's disease (PD) have objective value in assessing their motor condition for effective diagnosis, monitoring, and clinical intervention. Prominent cortical biomarkers of PD have typically been derived from various β band wave features. This study approached the topic from an alternative perspective and attempted to estimate a recently suggested measure representing α band nonlinear autocorrelative memory from a publicly available EEG dataset that involves 15 patients with earlier-stage PD (dopaminergic medication OFF and ON states) and 16 age-matched healthy controls. The cortical nonlinearity was elevated for the PD ON state compared with the OFF state for bilateral sensorimotor channels C3 and C4 (n = 26; P = 0.003). A similar statistical difference was also identified between PD OFF state and healthy subjects (n = 26; P = 0.049). Analysis over all channels revealed that the α band nonlinearity induced upon medication was constrained to sensorimotor regions. The α nonlinearity measure was compared with a well-accepted cortical biomarker of β-γ phase-amplitude coupling (PAC). They were in moderate negative correlation (r = -0.412; P = 0.036) for only healthy subjects, but not for the patients. The nonlinearity measure was found to be insusceptible to the nonstationary variations within the particular data. Our study provides further evidence that the α band nonlinearity measure can serve as a promising cortical biomarker of PD. The suggested measure can be estimated from a noninvasive low-resolution single scalp EEG channel of patients with relatively early-stage PD, who did not yet need to undergo deep brain stimulation operation.NEW & NOTEWORTHY This study suggests a nonlinearity measure that differentiates Parkinson's disease (PD) dopamine OFF-state scalp EEG data from those of dopamine ON-state patients and healthy subjects. Unlike typical PD cortical biomarkers based on β band activity, this metric shows elevation upon dopaminergic medication in the α band. We provide evidence supporting its potential as an early-stage promising PD biomarker that can be estimated from noninvasive EEG recordings with low resolution and SNR.

Classification of bruxism based on time-frequency and nonlinear features of single channel EEG

BackgroundIn the classification of bruxism patients based on electroencephalogram (EEG), feature extraction is essential. The method of using multi-channel EEG fusing electrocardiogram (ECG) and Electromyography (EMG) signal features has been proved to have good performance in bruxism classification, but the classification performance based on single channel EEG signal is still understudied. We investigate the efficacy of single EEG channel in bruxism classification.MethodsWe have extracted time-domain, frequency-domain, and nonlinear features from single EEG channel to classify bruxism. Five common bipolar EEG recordings from 2 bruxism patients and 4 healthy controls during REM sleep were analyzed. The time domain (mean, standard deviation, root mean squared value), frequency domain (absolute, relative and ratios power spectral density (PSD)), and non-linear features (sample entropy) of different EEG frequency bands were analyzed from five EEG channels of each participant. Fine tree algorithm was trained and tested for classifying sleep bruxism with healthy controls using five-fold cross-validation.ResultsOur results demonstrate that the C4P4 EEG channel was most effective for classification of sleep bruxism that yielded 95.59% sensitivity, 98.44% specificity, 97.84% accuracy, and 94.20% positive predictive value (PPV).ConclusionsOur results illustrate the feasibility of sleep bruxism classification using single EEG channel and provides an experimental foundation for the development of a future portable automatic sleep bruxism detection system.

Deep transfer learning for automated single-lead EEG sleep staging with channel and population mismatches.

Introduction: Automated sleep staging using deep learning models typically requires training on hundreds of sleep recordings, and pre-training on public databases is therefore common practice. However, suboptimal sleep stage performance may occur from mismatches between source and target datasets, such as differences in population characteristics (e.g., an unrepresented sleep disorder) or sensors (e.g., alternative channel locations for wearable EEG). Methods: We investigated three strategies for training an automated single-channel EEG sleep stager: pre-training (i.e., training on the original source dataset), training-from-scratch (i.e., training on the new target dataset), and fine-tuning (i.e., training on the original source dataset, fine-tuning on the new target dataset). As source dataset, we used the F3-M2 channel of healthy subjects (N = 94). Performance of the different training strategies was evaluated using Cohen's Kappa (κ) in eight smaller target datasets consisting of healthy subjects (N = 60), patients with obstructive sleep apnea (OSA, N = 60), insomnia (N = 60), and REM sleep behavioral disorder (RBD, N = 22), combined with two EEG channels, F3-M2 and F3-F4. Results: No differences in performance between the training strategies was observed in the age-matched F3-M2 datasets, with an average performance across strategies of κ = .83 in healthy, κ = .77 in insomnia, and κ = .74 in OSA subjects. However, in the RBD set, where data availability was limited, fine-tuning was the preferred method (κ = .67), with an average increase in κ of .15 to pre-training and training-from-scratch. In the presence of channel mismatches, targeted training is required, either through training-from-scratch or fine-tuning, increasing performance with κ = .17 on average. Discussion: We found that, when channel and/or population mismatches cause suboptimal sleep staging performance, a fine-tuning approach can yield similar to superior performance compared to building a model from scratch, while requiring a smaller sample size. In contrast to insomnia and OSA, RBD data contains characteristics, either inherent to the pathology or age-related, which apparently demand targeted training.

Developing A method to Detect Driver Drowsiness Based on A single EEG Channel and Discriminated Features

Developing A method to Detect Driver Drowsiness Based on A single EEG Channel and Discriminated Features

Developing a method to detect driver drowsiness based on a single EEG channel and discriminated features

Developing a method to detect driver drowsiness based on a single EEG channel and discriminated features

A Dual-Branch Interactive Fusion Network to Remove Artifacts From Single-Channel EEG

A Dual-Branch Interactive Fusion Network to Remove Artifacts From Single-Channel EEG

A FUSION OF A DISCRETE WAVELET TRANSFORM-BASED AND TIME-DOMAIN FEATURES EXTRACTION FOR MOTOR IMAGERY CLASSIFICATION

A motor imagery (MI)-based brain-computer interface (BCI) has performed successfully as a control mechanism with multiple electroencephalogram (EEG) channels. For practicality, fewer EEG channels are preferable. This paper investigates a single-channel EEG signal for MI. However, there are insufficient features that can be extracted due to a single-channel EEG signal being used in one region of the brain. An effective feature extraction technique plays a critical role in overcoming this limitation. Therefore, this study proposes a fusion of discrete wavelet transform (DWT)-based and time-domain feature extraction to provide more relevant information for classification. The highest accuracy obtained on the BCI Competition III (IVa) dataset is 87.5% with logistic regression (LR) while the OpenBMI dataset attained the highest accuracy of 93% with support vector machine (SVM) as the classifier. Addressing the potential of enhancing the performance of a single EEG channel located on the forehead, the achieved result is relatively promising.

SleepFC: Feature Pyramid and Cross-Scale Context Learning for Sleep Staging.

Automated sleep staging is essential to assess sleep quality and treat sleep disorders, so the issue of electroencephalography (EEG)-based sleep staging has gained extensive research interests. However, the following difficulties exist in this issue: 1) how to effectively learn the intrinsic features of salient waves from single-channel EEG signals; 2) how to learn and capture the useful information of sleep stage transition rules; 3) how to address the class imbalance problem of sleep stages. To handle these problems in sleep staging, we propose a novel method named SleepFC. This method comprises convolutional feature pyramid network (CFPN), cross-scale temporal context learning (CSTCL), and class adaptive fine-tuning loss function (CAFTLF) based classification network. CFPN learns the multi-scale features from salient waves of EEG signals. CSTCL extracts the informative multi-scale transition rules between sleep stages. CAFTLF-based classification network handles the class imbalance problem. Extensive experiments on three public benchmark datasets demonstrate the superiority of SleepFC over the state-of-the-art approaches. Particularly, SleepFC has a significant performance advantage in recognizing the N1 sleep stage, which is challenging to distinguish.

Real-Time Attention Regulation and Cognitive Monitoring Using a Wearable EEG-based BCI.

Attention regulation is an essential ability in daily life that affects learning and work efficiency and is closely related to mental health. The effectiveness of brain-computer interface (BCI) systems in attention regulation has been proven, but most of these systems rely on bulky and expensive equipment and are still in the experimental stage. This study proposes a wearable BCI system for real-time attention regulation and cognitive monitoring. The BCI system integrates a wearable singlechannel electroencephalogram (EEG) headband with wireless data streaming for real-time analysis. Twenty healthy subjects participated in the long-term attention regulation experiment and were evenly divided into an experimental group and a control group based on the presence of realtime neurofeedback. The neurofeedback is represented by output value of attention, which calculated from singlechannel EEG data. Before and after the regulation sessions, baseline assessments were conducted for each subject, incorporating multi-channel EEG data analysis and cognitive behavioral evaluations, to verify the effectiveness of system for attention regulation. The online experimental results indicate that the average attention level in the experimental group increased from 0.625 to 0.812, while no significant improvement was observed in the control group. Further comparative analysis revealed the reasons for the enhancement of attention regulation ability in terms of both brain network patterns and cognitive performance. The proposed wearable BCI system is effective at improving attention regulation ability and could be a promising tool for assisting people with attention disorders.

Strength of ensemble learning in automatic sleep stages classification using single-channel EEG and ECG signals.

Healthy sleep plays an essential role in human daily life. Classification of sleep stages is a crucial tool for assisting physicians in diagnosing and treating sleep disorders. In this study, a strong ensemble learning model is proposed to enhance the ability of classification models in accurate sleep staging, particularly in multi-class classification. We asserted that high-accuracy sleep classification is achievable using only single-channel electroencephalogram (EEG) and electrocardiogram (ECG) by combining their best-extractable features in the time and frequency domains we recommended. More importantly, the superiority of the recommended method, which is the simultaneous use of stacking and bagging, over conventional machine learning classifiers in sleep staging was demonstrated, using the MIT-BIH Polysomnographic and Sleep-EDF expanded databases. Finally, K-fold cross-validation was used to fairly estimate these models. The best mean test accuracy rates for distinguishing between two classes of "sleep vs. wake," "rapid vs. non-rapid eye movement," and "deep vs. light sleep," were obtained 99.93%, 99.64%, and 99.69%, respectively. Furthermore, our proposed method achieved accuracies of 97.14%, 95.18%, 92.7%, and 85.64% for separating three, four, five, and six sleep classes, respectively. Compared to recent studies, our method outperforms other sleep stage classification schemes, especially in multi-class staging.

Evaluation of Parkinson's disease early diagnosis using single-channel EEG features and auditory cognitive assessment.

Parkinson's disease (PD) often presents with subtle early signs, making diagnosis difficult. F-DOPA PET imaging provides a reliable measure of dopaminergic function and is a primary tool for early PD diagnosis. This study aims to evaluate the ability of machine-learning (ML) extracted EEG features to predict F-DOPA results and distinguish between PD and non-PD patients. These features, extracted using a single-channel EEG during an auditory cognitive assessment, include EEG feature A0 associated with cognitive load in healthy subjects, and EEG feature L1 associated with cognitive task differentiation. Participants in this study are comprised of cognitively healthy patients who had undergone an F-DOPA PET scan as a part of their standard care (n = 32), and cognitively healthy controls (n = 20). EEG data collected using the Neurosteer system during an auditory cognitive task, was decomposed using wavelet-packet analysis and machine learning methods for feature extraction. These features were used in a connectivity analysis that was applied in a similar manner to fMRI connectivity. A preliminary model that relies on the features and their connectivity was used to predict initially unrevealed F-DOPA test results. Then, generalized linear mixed models (LMM) were used to discern between PD and non-PD subjects based on EEG variables. The prediction model correctly classified patients with unrevealed scores as positive F-DOPA. EEG feature A0 and the Delta band revealed distinct activity patterns separating between study groups, with controls displaying higher activity than PD patients. In controls, EEG feature L1 showed variations between resting state and high-cognitive load, an effect lacking in PD patients. Our findings exhibit the potential of single-channel EEG technology in combination with an auditory cognitive assessment to distinguish positive from negative F-DOPA PET scores. This approach shows promise for early PD diagnosis. Additional studies are needed to further verify the utility of this tool as a potential biomarker for PD.

EEG-Based Emotion Recognition Using Trainable Adjacency Relation Driven Graph Convolutional Network

In recent years, there has been a growing research interest in using deep learning to resolve the issue of Electroencephalogram (EEG)-based emotion recognition. Current research emphasizes exploiting the useful information from each single EEG channel or each individual set of multi-channel EEG, but overlooks the correlation information among different multi-channel EEG sets. To explore such discriminative correlation information, we propose a novel and effective method“, Trainable Adjacency Relation Driven Graph Convolutional Network (TARDGCN)", which contains two complementary modules, TAR and GCN. TAR optimizes the local pair-wise positions of multi-channel EEG sets, which helps form an improved graphic representation for GCN to learn the global correlation among these sets for classification. The proposed method is capable of dealing with the problem of small sample size but large data variation in this issue. Our experimental results conducted on the databases DREAMER and DEAP in the subject-dependent and subject-independent modes show that TARDGCN outperforms the state-of-the-art approaches in classifying all of valence, arousal, and dominance.

Restoration of motion-corrupted EEG signals using attention-guided operational CycleGAN

Electroencephalogram (EEG) signals suffer substantially from motion artifacts even in ambulatory settings. Signal processing techniques for removing motion artifacts from EEG signals have limitations, and the potential of classical or deep machine-learning algorithms for this task remains largely unexplored. We propose Attention-Guided Operational CycleGAN (AGO-CycleGAN), a novel CycleGAN-based framework to remove motion artifacts and enhance the quality of corrupted EEG signals. It incorporates self-generative operational neurons and an attention-guided Feature Pyramid Network with modified bottlenecks as generators and PatchGAN-based discriminators. AGO-CycleGAN was trained and tested on a single-channel EEG dataset from 23 subjects, using a subject-independent Jackknife cross-validation approach. It outperformed other methods and was evaluated through qualitative and quantitative analysis, employing robust metrics in both temporal and frequency domains. The results indicate its effectiveness in restoring EEG signals affected by severe motion artifacts. AGO-CycleGAN achieves state-of-the-art EEG restoration performance in the temporal domain, gaining improvements in signal-to-noise ratio (ΔSNR) and temporal correlation (ηtemp) by 26.497 dB and 87.2%, respectively. It also showed excellent performance in preserving the spectral EEG components (delta, theta, alpha, beta, and gamma), evaluated through band power ratio before and after restoration. Spectral correlation (ηspec) improved by 93.5% after cleaning the motion artifacts. Qualitative evaluations showed excellently reconstructed clean EEG waveforms upon restoration. Spectral restoration visualized through Power Spectral Density (PSD) plots and per-band topographic maps showed a uniform removal of high-power motion artifact components throughout the spectrum. AGO-CycleGAN significantly outperformed existing techniques in EEG artifact removal and can be extended to multi-channel EEG systems.

SleePyCo: Automatic sleep scoring with feature pyramid and contrastive learning

Automatic sleep scoring is essential for the diagnosis and treatment of sleep disorders and enables longitudinal sleep tracking in home environments. Conventionally, learning-based automatic sleep scoring on single-channel electroencephalogram (EEG) is actively studied because obtaining multi-channel signals during sleep is difficult. However, learning representation from raw EEG signals is challenging owing to the following issues: (1) sleep-related EEG patterns occur on different temporal and frequency scales and (2) sleep stages share similar EEG patterns. To address these issues, we propose an automatic Sleep scoring framework that incorporates (1) a feature Pyramid and (2) supervised Contrastive learning, named SleePyCo. For the feature pyramid, we propose a backbone network named SleePyCo-backbone to consider multiple feature sequences on different temporal and frequency scales. Supervised contrastive learning allows the network to extract class discriminative features by minimizing the distance between intra-class features and simultaneously maximizing that between inter-class features. Comparative analyses on four public datasets demonstrate that SleePyCo consistently outperforms existing frameworks based on single-channel EEG. Extensive ablation experiments show that SleePyCo exhibited an enhanced overall performance, with significant improvements in discrimination between sleep stages, especially for N1 and rapid eye movement (REM). Source code is available at https://github.com/gist-ailab/SleePyCo.

Mental fatigue assessment by an arbitrary channel EEG based on morphological features and LSTM-CNN

In order to achieve more sensitive mental fatigue assessment (MFA) based on an arbitrary channel EEG, this study proposed a series of feature extraction methods that combine mathematical morphology (MM), as well as an LSTM-CNN architecture. Firstly, 37 subjects had their resting-state EEGs collected at rested wakefulness (RW) and after 24 h of sleep deprivation (SD) using a 30-channel EEG acquisition device, the RW and SD groups were regarded as the negative and positive groups of mental fatigue, respectively, and the EEG collection were further categorized into two conditions: eye-opened state (EO) and eye-closed state (EC). Then, since MM can reflect the morphological characteristics of EEG rhythms and their potentials relatively independently of the time-frequency analysis and phase calculation, the MM methods were found to better reflect the mental fatigue after SD statistically, whether for single features (ANOVA: p<0.000001), multiple features (clustering by K-means, t-test: p<0.01), or time series feature spaces (calculating CD, t-test: p<0.01) of a single channel. Finally, the LSTM-CNN enhanced the generalization ability when dealing with different single-channel EEG by combining GRUs with convolutional layers: comparing the AUCs of different architectures for MFA based on an arbitrary channel, LSTM-CNN (0.992) > LSTM network (0.94) > CNN (0.831) > MLP (0.754). Moreover, the use of MM also improved the accuracy of analyzed architectures, and the true/false positive rate (TPR/FPR) of the LSTM-CNN architecture for MFA based on an arbitrary channel reached 97.024 %/3.497 %, which provided a feasible solution for the arbitrary channel EEG-based MFA.

Leveraging discriminative features for automatic sleep stage classification based on raw single-channel EEG

Sleep staging is the basis for assessing sleep quality. In the process of scoring each sleep stage, some automatic sleep staging models often fail to effectively capture the more accurate long-range correlation coupling between the input sleep EEG signals and the output sleep stage, which leads to the extracted features cannot effectively distinguish the different sleep stages. We propose an automatic end-to-end sleep stage classification method based on the original single-channel sleep EEG signal to perform feature learning on the source domain information of critical parts of the sleep EEG signals and solve the long-term time series problem. The method uses a convolutional neural network (CNN) to extract the time–frequency domain features of signals. It introduces a squeeze-and-excitation block (SE-Block) on CNN to enhance the feature representation ability of CNN. At the same time, a bidirectional recurrent unit (Bi-GRU) is used to learn the conversion rules of sleep stages, and an attention mechanism is added to the decoding part of Bi-GRU to enhance the long-term memory capacity of Bi-GRU and highlight the influence of essential features. According to the particularity of sleep signals, this method combines multiple models and techniques and creatively blends them to improve the performance of automatic staging. To validate the accuracy and stability of the model, the Fpz-Cz channel and the Pz-Oz channel EEG signals in the Sleep-EDF sleep dataset are used for 10-fold cross-validation. The classification accuracy was 88.48% and 87.56%, respectively. The results show that under the same model architecture and dataset, our model has a more vital ability to extract essential features, better representation ability, more stable performance, and a relatively simple model structure.

Sequence signal reconstruction based multi-task deep learning for sleep staging on single-channel EEG

The temporal context information between sleep stage sequence contains sleep transition rules, which is important for improving sleep staging performance. Existing multi-task learning methods reconstruct EEG signals from one sleep stage, ignoring the importance of sequential temporal context in capturing long-term dependencies to enhance representation learning. To address these issues, we propose a multi-task deep learning model to jointly reconstruct sequence signal and segment time series. The model enhances the ability of time series segmentation task to capture sequential temporal context and improves the performance of single-channel EEG by optimizing the common encoder for sequence signal reconstruction task. In addition, we design a one-dimensional channel attention module to enhance the feature representation extracted for sleep sequence signal. The experimental results on four datasets show that the multi-task deep learning model can improve the generalization using sequence signal reconstruction. Compared with other state-of-the-art methods, the method proposed in this study obtained competitive performance in terms of metrics such as accuracy, which is 85.6% on the 2013 version of Sleep-EDF Database Expanded, 83.4% on the 2018 version of Sleep-EDF Database Expanded, 85.6% on Sleep Heart Health Study, and 77.4% on CAP Sleep Database.

EOG Artifacts Suppression From single channel EEG Signals by VME-GMETV model

Nowadays the usage of portable electroencephalography (EEG) recorded systems are raised for recording of neuro activities of the brain, which are useful in clinical diagnosis such as brain–computer interface (BCI) applications. The eye movements or blinks are unavoidable activities, which reflects the electrooculogram (EOG) artifacts in the recorded EEG signals, which leads deceptive interpretation of the underlying brain state. In this paper a novel framework is proposed as Variational Mode Extraction (VME) method is integrated with Generalized Moreau Envelope Total Variation (GMETV) technique to filter the EOG artifacts. Initially, the contaminated EEG is applied to the VME method which extracts the EOG artifact segment. Then, this EOG artifact segment is given to the GMETV technique and it separates the wanted component of the EEG residue from the EOG artifact segment. The EEG residue is added back to the non EOG artifact segment signal which gives the final denoised EEG. Matlab simulations are done on both simulated and real time EEG databases to evolute the proposed VME-GMETV technique performance in terms of Relative Root Mean Square Error (RRMSE), Correlation Coefficient (CC) and Mean Absolute Error (MAE). From the experimental results, the proposed technique is outperformed the existing methods by averaged low RRMSE (0.1557), MAE (5.0714e−04) and averaged high CC (0.9695).

An Eye Tracking and Brain–Computer Interface-Based Human–Environment Interactive System for Amyotrophic Lateral Sclerosis Patients

Amyotrophic Lateral Sclerosis (ALS) patients suffer a great inconvenience in their daily lives due to the gradual loss of their motion abilities. In order to help ALS patients regain their self-care abilities at a certain level, an eye-tracking and brain-computer interface (BCI) based human-environment interactive (HEI) system is proposed. Through a single-channel EEG recorder and a pair of eye-tracking glasses, the user’s attention levels and gaze points are detected. Based on the two types of intention information, the target objects are recognized by a YOLOv5 (You Only Look Once v5) model. Then according to voice instructions, users can control the household electric appliances. The system performed a high success rate of 89.3% experimentally, providing a reliable and capable assistive solution for ALS patients.