Multichannel EEG Signals Research Articles

Utilizing Graph Signal-Processing-Based Spectrum to Classify Mental Tasks With Multichannel EEG Signals

Utilizing Graph Signal-Processing-Based Spectrum to Classify Mental Tasks With Multichannel EEG Signals

A Dual-Branch Spatio-Temporal-Spectral Transformer Feature Fusion Network for EEG-Based Visual Recognition

Recognizing visual objects from single-trial electroencephalograph (EEG) signals is a promising brain-computer interface (BCI) technology. However, due to the redundant features from noisy multi-channel EEG signals, it is still a challenging task to achieve high precision recognition. Recent deep learning approaches commonly extract spatio-temporal features of EEG signals, which neglect important spectral-temporal features and may degrade the EEG recognition performance. To address the deficiency, we propose a novel channel attention weighting and multi-level adaptive spectral aggregation based dual-branch spatio-temporal-spectral Transformer feature fusion network (CAW-MASA-STST) for EEG-based visual recognition. Specially, we first develop a channel attention weighting (CAW) to automatically learn the channel weights of EEG signals. Then, a graph convolution-based multi-level adaptive spectral aggregation (MASA) is employed to aggregate spectral-temporal features of different sub-bands. Finally, a spatio-temporal-spectral Transformer (STST) is designed to fuse spatio-temporal and spectral-temporal features, which enhances the comprehensive learning ability by modeling the temporal dependencies of the fused features. Competitive experimental results on two public datasets demonstrate that the proposed method is able to achieve superior recognition performance compared with the state-of-the-art methods, indicating a feasible solution for visual recognition-based BCI technology. The code of our proposed method will be available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ljbuaa/VisualDecoding</uri> .

Brain Topology Modeling With EEG-Graphs for Auditory Spatial Attention Detection.

Despite recent advances, the decoding of auditory attention from brain signals remains a challenge. A key solution is the extraction of discriminative features from high-dimensional data, such as multi-channel electroencephalography (EEG). However, to our knowledge, topological relationships between individual channels have not yet been considered in any study. In this work, we introduced a novel architecture that exploits the topology of the human brain to perform auditory spatial attention detection (ASAD) from EEG signals. We propose EEG-Graph Net, an EEG-graph convolutional network, which employs a neural attention mechanism. This mechanism models the topology of the human brain in terms of the spatial pattern of EEG signals as a graph. In the EEG-Graph, each EEG channel is represented by a node, while the relationship between two EEG channels is represented by an edge between the respective nodes. The convolutional network takes the multi-channel EEG signals as a time series of EEG-graphs and learns the node and edge weights from the contribution of the EEG signals to the ASAD task. The proposed architecture supports the interpretation of the experimental results by data visualization. We conducted experiments on two publicly available databases. The experimental results showed that EEG-Graph Net significantly outperforms the state-of-the-art methods in terms of decoding performance. In addition, the analysis of the learned weight patterns provides insights into the processing of continuous speech in the brain and confirms findings from neuroscientific studies. We showed that modeling brain topology with EEG-graphs yields highly competitive results for auditory spatial attention detection. The proposed EEG-Graph Net is more lightweight and accurate than competing baselines and provides explanations for the results. Also, the architecture can be easily transferred to other brain-computer interface (BCI) tasks.

Notice of Removal: Removal of ocular artifacts using ICA and adaptive filter for motor imagery-based BCI

Preprocessing is the first step of Brain Computer Interface U+0028 BCI U+0029 based on Electroencephalogram U+0028 EEG U+0029, the most important aspect in this step is to remove Ocular Artifacts U+0028 OAs U+0029 included in EEG signals. OAs are the main interference signals to the EEG signals. In this paper, a new method called ICA-AF is proposed. This method using Independent Component Analysis U+0028 ICA U+0029 and Adaptive Filter U+0028 AF U+0029 can remove OAs from the EEG signals without measuring Electrooculogram U+0028 EOG U+0029. The method firstly decomposes the multi-channel EEG signals into the statistically independent components by ICA, then extracts the exact OAs that do not include the brain activity information in the OA-related independent components, and converts the exact OAs to the OAs at each electrode using inverse ICA U+0028 iICA U+0029. An adaptive filter uses this OA and the EEG signal in each channel as reference and input signal, respectively. Compared to ICA and ICA-RLS U+0028 Independent Component Analysis-Robust Least Square U+0029 methods, the proposed method can remove most of exact OAs and preserve as much brain activity information as possible. In addition, the average classification accuracy of the new method is 19 U+0025 and 8 U+0025 higher than the previous two methods, in the ratio of the average classification accuracy of the raw EEG, respectively. Besides, the new method is 1.45 times faster than ICA-RLS method, with respect to the execution time of ICA method.

Regional-asymmetric Adaptive Graph Convolutional Neural Network for Diagnosis of Autism in Children with Resting-state EEG.

Currently, resting-state electroencephalography (rs-EEG) has become an effective and low-cost evaluation way to identify autism spectrum disorders (ASD) in children. However, it is of great challenge to extract useful features from raw rs-EEG data to improve diagnosis performance. Traditional methods mainly rely on the design of manual feature extractors and classifiers, which are separately performed and cannot be optimized simultaneously. To this end, this paper proposes a new end-to-end diagnostic method based on a recently emerged graph convolutional neural network for the diagnosis of ASD in children. Inspired by related neuroscience findings on the abnormal brain functional connectivity and hemispheric asymmetry characteristics observed in autism patients, we design a new Regional-asymmetric Adaptive Graph Convolutional Neural Network (RAGNN). It utilizes a hierarchical feature extraction and fusion process to learn separable spatiotemporal EEG features from different brain regions, two hemispheres, and a global brain. In the temporal feature extraction section, we utilize a convolutional layer that spans from the brain area to the hemisphere. This allows for effectively capturing temporal features both within and between brain areas. To better capture spatial characteristics of multi-channel EEG signals, we employ adaptive graph convolutional learning to capture non-Euclidean features within the brain's hemispheres. Additionally, an attention layer is introduced to highlight different contributions of the left and right hemispheres, and the fused features are used for classification. We conducted a subject-independent cross-validation experiment on rs-EEG data from 45 children with ASD and 45 typically developing (TD) children. Experimental results have shown that our proposed RAGNN model outperformed several existing deep learning-based methods (ShaollowNet, EEGNet, TSception, ST-GCN, and CGRU-MDGN).

Causal Graph Convolutional Neural Network for Emotion Recognition

Graph convolutional neural network (GCNN) based methods have been widely used in electroencephalogram(EEG) related works due to their advantages of considering the symmetrical connections of brain regions. However, the current GCNN based methods do not fully explore other correlations between EEG channels. Many studies have proved that definite causal connections exist between brain regions. Therefore, this paper proposes a Causal Graph Convolutional Neural Network (CGCNN) using Granger causality test to calculate inter-channel interactions. First, we consider causal relations between EEG channels and construct an asymmetric causal graph with direction. Then, we adopt depthwise separable convolution to extract emotional features from multi-channel EEG signals. Experiments carried out on SEED and SEED-IV show that CGCNN has the ability to represent the causal information flow in different emotional states, and improve the classification accuracy to 93.36% on SEED and 75.48% on SEED-IV respectively. The results outperform other existing methods, indicating that Granger causality is more effective in revealing the correlations between EEG channels in emotion recognition.

Detection and Severity Identification of Neonatal Seizure Using Deep Convolutional Neural Networks from Multichannel EEG Signal.

One of the most frequent neurological conditions in newborns is neonatal seizures, which may indicate severe neurological dysfunction. These seizures may have very subtle or very modest clinical indications because patterns like oscillatory (spike) trains begin with relatively low amplitude and gradually increase over time. This becomes very challenging and erroneous if clinical observation is the primary basis for identifying newborn seizures. In this study, a diagnosis system using deep convolutional neural networks is proposed to determine and classify the severity level of neonatal seizures using multichannel neonatal EEG data. Datasets from publicly accessible online sources were used to compile clinical multichannel EEG datasets. Various preprocessing steps were taken, including the conversion of 2D time series data to equivalent waveform pictures. The proposed models have undergone training, and evaluations of their performance were conducted. The proposed CNN was used to perform binary classification with an accuracy of 92.6%, F1-score of 92.7%, specificity of 92.8%, and precision of 92.6%. To detect newborn seizures, this model is utilized. Using the proposed CNN model, multiclassification was performed with accuracy rates of 88.6%, specificity rates of 92.18%, F1-score rates of 85.61%, and precision rates of 88.9%. The results demonstrated that the suggested strategy can assist medical professionals in making accurate diagnoses close to healthcare institutions. The developed system was capable of detecting neonatal seizures and has the potential to be used as a decision-making tool in resource-limited areas with a scarcity of expert neurologists.

Multi-View Graph Contrastive Learning via Adaptive Channel Optimization for Depression Detection in EEG Signals.

Automated detection of depression using Electroencephalogram (EEG) signals has become a promising application in advanced bioinformatics technology. Although current methods have achieved high detection performance, several challenges still need to be addressed: (1) Previous studies do not consider data redundancy when modeling multi-channel EEG signals, resulting in some unrecognized noise channels remaining. (2) Most works focus on the functional connection of EEG signals, ignoring their spatial proximity. The spatial topological structure of EEG signals has not been fully utilized to capture more fine-grained features. (3) Prior depression detection models fail to provide interpretability. To address these challenges, this paper proposes a new model, Multi-view Graph Contrastive Learning via Adaptive Channel Optimization (MGCL-ACO) for depression detection in EEG signals. Specifically, the proposed model first selects the critical channels by maximizing the mutual information between tracks and labels of EEG signals to eliminate data redundancy. Then, the MGCL-ACO model builds two similarity metric views based on functional connectivity and spatial proximity. MGCL-ACO constructs the feature extraction module by graph convolutions and contrastive learning to capture more fine-grained features of different perspectives. Finally, our model provides interpretability by visualizing a brain map related to the significance scores of the selected channels. Extensive experiments have been performed on public datasets, and the results show that our proposed model outperforms the most advanced baselines. Our proposed model not only provides a promising approach for automated depression detection using optimal EEG signals but also has the potential to improve the accuracy and interpretability of depression diagnosis in clinical practice.

Detection and classification of adult epilepsy using hybrid deep learning approach

The electroencephalogram (EEG) has emerged over the past few decades as one of the key tools used by clinicians to detect seizures and other neurological abnormalities of the human brain. The proper diagnosis of epilepsy is crucial due to its distinctive nature and the subsequent negative effects of epileptic seizures on patients. The classification of minimally pre-processed, raw multichannel EEG signal recordings is the foundation of this article’s unique method for identifying seizures in pre-adult patients. The new method makes use of the automatic feature learning capabilities of a three-dimensional deep convolution auto-encoder (3D-DCAE) associated with a neural network-based classifier to build an integrated framework that endures training in a supervised manner to attain the highest level of classification precision among brain state signals, both ictal and interictal. A pair of models were created and evaluated for testing and assessing our method, utilizing three distinct EEG data section lengths, and a tenfold cross-validation procedure. Based on five evaluation criteria, the labelled hybrid convolutional auto-encoder (LHCAE) model, which utilizes a classifier based on bidirectional long short-term memory (Bi-LSTM) and an EEG segment length of 4 s, had the best efficiency. This proposed model has 99.08 ± 0.54% accuracy, 99.21 ± 0.50% sensitivity, 99.11 ± 0.57% specificity, 99.09 ± 0.55% precision, and an F1-score of 99.16 ± 0.58%, according to the publicly available Children’s Hospital Boston (CHB) dataset. Based on the obtained outcomes, the proposed seizure classification model outperforms the other state-of-the-art method’s performance in the same dataset.

Efficient space learning based on kernel trick and dimension reduction technique for multichannel motor imagery EEG signals classification

Efficient space learning based on kernel trick and dimension reduction technique for multichannel motor imagery EEG signals classification

Lightweight convolution transformer for cross-patient seizure detection in multi-channel EEG signals

BackgroundEpilepsy is a neurological illness affecting the brain that makes people more likely to experience frequent, spontaneous seizures. There has to be an accurate automated method for measuring seizures frequency and severity to assess the efficacy of pharmacological therapy for epilepsy. The drug quantities are often derived from patient reports which may cause significant issues owing to inadequate or inaccurate descriptions of seizures and their frequencies. Methods and materialsThis study proposes a novel deep learning architecture-based Lightweight Convolution Transformer (LCT). The Transformer model is able to learn spatial and temporal correlated information simultaneously from the multi-channel electroencephalogram (EEG) signal to detect seizures at smaller segment lengths. In the proposed work, the lack of translation equivariance and localization of ViT is reduced using convolution tokenization, and rich information from the Transformer encoder is extracted by sequence pooling instead of the learnable class token. ResultsExtensive experimental results demonstrate that the proposed model on cross-patient learning can effectively detect seizures from the raw EEG signals. The accuracy and F1-score of seizure detection in the cross-patient case on the CHB-MIT dataset are 96.31% and 96.32%, respectively, at 0.5 sec segment length. In addition, the performance metrics show that the inclusion of inductive biases and attention-based pooling in the model enhances the performance and reduces the number of Transformer encoder layers, which significantly reduces the computational complexity. In this research, we provide a novel approach to enhance efficiency and simplify the architecture for multi-channel automated seizure detection.

MMPosE: Movie-Induced Multi-Label Positive Emotion Classification Through EEG Signals

Emotional information plays an important role in various multimedia applications. Movies, as a widely available form of multimedia content, can induce multiple positive emotions and stimulate people's pursuit of a better life. Different from negative emotions, positive emotions are highly correlated and difficult to distinguish in the emotional space. Since different positive emotions are often induced simultaneously by movies, traditional single-target or multi-class methods are not suitable for the classification of movie-induced positive emotions. In this paper, we propose TransEEG, a model for multi-label positive emotion classification from a viewer's brain activities when watching emotional movies. The key features of TransEEG include (1) explicitly modeling the spatial correlation and temporal dependencies of multi-channel EEG signals using the Transformer structure based model, which effectively addresses long-distance dependencies, (2) exploiting the label-label correlations to guide the discriminative EEG representation learning, for that we design an Inter-Emotion Mask for guiding the Multi-Head Attention to learn the inter-emotion correlations, and (3) constructing an attention score vector from the representation-label correlation matrix to refine emotion-relevant EEG features. To evaluate the ability of our model for multi-label positive emotion classification, we demonstrate our model on a state-of-the-art positive emotion database CPED. Extensive experimental results show that our proposed method achieves superior performance over the competitive approaches.

Алгоритм детектирования эпилептиформной активности ЭЭГ при отсроченной ишемии головного мозга

An algorithm for automatic detection of epileptiform activity in EEG monitoring data with delayed ischemia after hemorrhage in the subarachnoid space of the brain is proposed and described. The algorithm is based on the formalization of the visual characteristics of epileptiform activity in the form of a peak-wave discharge pattern and analysis of the mutual correlation of multichannel EEG signals with the selected pattern. Fragments of epileptiform activity in each pair of bipolar electrodes were determined from three conditions according to the description of peak-wave discharges of epileptiform activity: 1) the value of positive mutual correlation at the peak of the correlation function should be greater than 0.4; 2) a positive peak of mutual correlation should be followed by a peak with a negative correlation; 3) the width of the peak of negative mutual correlation at half-altitude should be at least 2 times greater than that of the previous positive peak of positive mutual correlation. As with the visual detection of epileptiform activity, the neurophysiologist selected simultaneous peak-wave discharges in several bipolar electrodes. The results of testing the algorithm on an hour-long EEG recording of a patient with delayed ischemia are presented. Fragments with epileptiform activity during the hour under review were identified 17 in the right hemisphere and 2 in the left. Interhemispheric asymmetry is caused by a right-sided aneurysm in patient. The operating time of the algorithm on a modern personal computer is no more than 5 minutes to process 16 bipolar signals, so it can be used to calculate the hourly amount of epileptiform activity in almost real time of the manifestation of this indicator of delayed ischemia after aneurysmal subarachnoid hemorrhage.

Parameterized aperiodic and periodic components of single-channel EEG enables reliable seizure detection.

Although it is clinically important, a reliable and economical solution to automatic seizure detection for patients at home is yet to be developed. Traditional algorithms rely on multi-channel EEG signals and features of canonical EEG power description. This study is aimed to propose an effective single-channel EEG seizure detection method centered on novel EEG power parameterization and channel selection algorithms.We employed the publicly available multi-channel CHB-MIT Scalp EEG database to gauge the effectiveness of our approach. We first adapted a power spectra parameterization algorithm to characterize the aperiodic and periodic components of the ictal and inter-ictal EEGs. We selected four features based on their statistical significance and interpretability, and developed a ranking approach to channel selection for each patient. We then tested the effectiveness of our approaches to channel and feature selection for automatic seizure detection using support vector machine (SVM) as the classifier. The performance of our algorithm was evaluated using five-fold cross-validation and compared to those methods of comparable complexity (using one or two channels of EEG), in terms of accuracy, specificity, sensitivity, precision and F1 score.Some channels of EEG signals show strikingly different distributions of PSD features between the ictal and inter-ictal states. Four features including the offset and exponent parameters for the aperiodic component and the first and second highest total power (TPW1 and TPW2) form the basis of channel selection and the input of SVM classifier. The selected channel is found to be patient-specific. Our approach has achieved a mean sensitivity of 95.6%, specificity of 99.2%, accuracy of 98.6%, precision of 95.5%, and F1 score of 95.5%. Compared with algorithms in previous studies that used one or two channels of EEG signals, ours outperforms in specificity and accuracy with comparable sensitivity.EEG power spectra parameterization to feature extraction and feature ranking-based channel selection are found to enable efficient and effective automatic seizure detection based on single-channel EEG signal.

EEG Emotion Recognition based on Multi scale Self Attention Convolutional Networks

A multi-view self-attention module is proposed and paired with a multi-scale convolutional model to builda multi-view self-attention convolutional network for multi-channel EEG emotion recognition. First, timeand frequency domain characteristics are extracted from multi-channel EEG signals, and a three-dimensionalfeature matrix is built using spatial mapping connections. Then, a multi-scale convolutional network extractsthe high-level abstract features from the feature matrix, and a multi-view self-attention network strengthensthe features. Finally, use the multilayer perceptron for sentiment classification. The experimental results revealthat the multi-view self-attention convolutional network can effectively integrate the time domain, frequencydomain, and spatial domain elements of EEG signals using the DEAP public emotion dataset. The multi-viewself-attention module can eliminate superfluous data, apply attention weight to the network to hasten networkconvergence, and enhance model recognition precision.

Emotion Recognition Using Hierarchical Spatiotemporal Electroencephalogram Information from Local to Global Brain Regions.

To understand human emotional states, local activities in various regions of the cerebral cortex and the interactions among different brain regions must be considered. This paper proposes a hierarchical emotional context feature learning model that improves multichannel electroencephalography (EEG)-based emotion recognition by learning spatiotemporal EEG features from a local brain region to a global brain region. The proposed method comprises a regional brain-level encoding module, a global brain-level encoding module, and a classifier. First, multichannel EEG signals grouped into nine regions based on the functional role of the brain are input into a regional brain-level encoding module to learn local spatiotemporal information. Subsequently, the global brain-level encoding module improved emotional classification performance by integrating local spatiotemporal information from various brain regions to learn the global context features of brain regions related to emotions. Next, we applied a two-layer bidirectional gated recurrent unit (BGRU) with self-attention to the regional brain-level module and a one-layer BGRU with self-attention to the global brain-level module. Experiments were conducted using three datasets to evaluate the EEG-based emotion recognition performance of the proposed method. The results proved that the proposed method achieves superior performance by reflecting the characteristics of multichannel EEG signals better than state-of-the-art methods.

Ocular Artifacts Elimination From Multivariate EEG Signal Using Frequency-Spatial Filtering

The electroencephalogram (EEG) signals record electrical activities generated by the brain cells and are used as a state-of-the-art diagnosis tool for various neural disorders. However, the unwanted artifacts often contaminate the recorded EEG signals and disturb the interpretation of the neuronal activity. This paper aims to propose an efficient automatic method to eliminate the ocular artifacts (OAs) from the multi-channel EEG signals with novel frequency-spatial filtering. The method combines dictionary-based spatial filtering and frequency based signal decomposition method, namely empirical wavelet transform (EWT). The artifact dictionary needed for spatial filtering is isolated from the raw data by (1) selecting the contaminated channels and (2) frequency-domain filtering. More precisely, the δ-rhythms of identified highly contaminated channels are selected and placed into an artifact dictionary. Afterward, the δ-rhythms of multi-channel EEG signals are spatially filtered using the built dictionary to seclude the OAs within a limited number of components. Further, the artifact components are eliminated and clean δ-rhythms are recovered using inverse spatial filtering technique. Finally, the clean δ-rhythms are combined with other EEG rhythms to reconstruct the OA-free signals. The proposed method is applied to OA contaminated synthetic and real multi-channel EEG signals with a convincing performance as compared to state of the art approaches. The proposed method removes the OAs without affecting the background EEG information. The proposed method can ease sensor signal interpretation and further processing, e.g. for BCI applications.

Deep Representation of EEG Signals Using Spatio-Spectral Feature Images

Modern deep neural networks (DNNs) have shown promising results in brain studies involving multi-channel electroencephalogram (EEG) signals. The representations produced by the layers of a DNN trained on EEG signals remain, however, poorly understood. In this paper, we propose an approach to interpret deep representations of EEG signals. Our approach produces spatio-spectral feature images (SSFIs) that encode the EEG input patterns that activate the neurons in each layer of a DNN. We evaluate our approach using the PhyAAt dataset of multi-channel EEG signals for auditory attention. First, we train the same convolutional neural network (CNN) architecture on 25 separate sets of EEG signals from 25 subjects and conduct individual model analysis and inter-subject dependency analysis. Then we generate the SSFI input patterns that activate the layers of each trained CNN. The generated SSFI patterns can identify the main brain regions involved in a given auditory task. Our results show that low-level CNN features focus on larger regions and high-level features focus on smaller regions. In addition, our approach allows us to discern patterns in different frequency bands. Further SSFI saliency analysis reveals common brain regions associated with a specific activity for each subject. Our approach to investigate deep representations using SSFI can be used to enhance our understanding of the brain activity and effectively realize transfer learning.

Combining temporal and spatial attention for seizure prediction.

Approximately 1% of the world population is currently suffering from epilepsy. Successful seizure prediction is necessary for those patients. Influenced by neurons in their own and surrounding locations, the electroencephalogram (EEG) signals collected by scalp electrodes carry information of spatiotemporal interactions. Therefore, it is a great challenge to exploit the spatiotemporal information of EEG signals fully. In this paper, a new seizure prediction model called Gatformer is proposed by fusing the graph attention network (GAT) and the Transformer. The temporal and spatial attention are combined to extract EEG information from the perspective of spatiotemporal interactions. The model aims to explore the temporal dependence of single-channel EEG signals and the spatial correlations among multi-channel EEG signals. It can automatically identify the most noteworthy interaction in brain regions and achieve accurate seizure prediction. Compared with the baseline models, the performance of our model is significantly improved. The false prediction rate (FPR) on the private dataset is 0.0064/h. The average accuracy, specificity and sensitivity are 98.25%, 99.36% and 97.65%. The proposed model is comparable to the state of the arts. Experiments on different datasets show that it has good robustness and generalization performance. The high sensitivity and low FPR prove that this model has great potential to realize clinical assistance for diagnosis and treatment.

An iterative thresholding-based algorithm for brain–computer interface (BCI) application

The EEG signals are recorded using surgical (invasive) or non-surgical (non-invasive) BCI neuroimaging modalities. Basically, we are dealing with a huge amount of data and long signal recordings.The classic solution to deal with the huge amount of data has been data compression, where the data is first collected in its original large format and then converted to a compressed format of smaller size for storage or transmission. This has become a traditional solution to the problem of handling the massive volume of data.Compressive sensing is a novel technique that senses the signal in a compressed format using a sub-Nyquist–Shannon sampling rate and reconstructs it when the data from the compressed sensed signal is required.In the context of applying CS, the first issue is how to construct the linear measurement matrix to ensure that compressive sensing meets the requirements of the application. The second issue depends on the way in which the sparse signal can be obtained from a small sample of observations. In this paper, nuclear norm minimization is proposed to enforce sparsity and low-rank structures in the reconstructed multi-channel EEG signals. To compute the optimization, we propose two new algorithms which we call: a weighted thresholding algorithm and a weighted thresholding orthogonal matching pursuit algorithm based on compressive sensing. We perform the experiments on the insomnia EEG dataset. Computer simulations provide and show the good behavior of these algorithms and the NNM norm, compared to others in the literature.