A review of channel selection algorithms for EEG signal processing

Optimized seizure detection leveraging band-specific insights from limited EEG channels

Purpose

Effective seizure detection systems are crucial for health information systems and managing epilepsy, yet traditional multichannel EEG devices can be costly and complex. This study aims to optimize EEG channel selection and focus on specific frequency bands associated with epileptic activity, enhancing the system's usability and accuracy for clinical applications.

Methods

This work proposes a novel method by integrating channel selection with band-wise analysis for seizure detection. The channel selection uses an ensemble of mutual information (MI) and Random Forest (RF) techniques to select the most relevant channels. The signals from the selected channels are decomposed into different frequency bands using discrete wavelet transform (DWT). To evaluate the effectiveness of this approach, ten features are extracted from each frequency band and then classified using a support vector machine (SVM) classifier.

Results

This work has obtained a mean accuracy of 97.70%, a mean sensitivity of 86.70%, and a mean specificity of 99.66% for seizure patients from a well-established CHB-MIT dataset and an almost 80% reduction in processing time.

Conclusion

These benefits make seizure detection devices more wearable, less intrusive, and easier to integrate with other health monitoring systems, allowing for discreet and comfortable monitoring that supports an active lifestyle for patients.

Intra- and Inter-Regional Complexity in Multi-Channel Awake EEG Through Multivariate Multiscale Dispersion Entropy for Assessing Sleep Quality and Aging

Aging and poor sleep quality are associated with altered brain dynamics, yet current electroencephalography (EEG) analyses often overlook regional complexity. This study addresses this gap by introducing a novel integration of intra- and inter-regional complexity analysis using multivariate multiscale dispersion entropy (mvMDE) from awake resting-state EEG for the first time. Moreover, assessing both intra- and inter-regional complexity provides a comprehensive perspective on the dynamic interplay between localized neural activity and its coordination across brain regions, which is essential for understanding the neural substrates of aging and sleep quality. Data from 58 participants-24 young adults (mean age = 24.7 ± 3.4) and 34 older adults (mean age = 72.9 ± 4.2)-were analyzed, with each age group further divided based on Pittsburgh Sleep Quality Index (PSQI) scores. To capture inter-regional complexity, mvMDE was applied to the most informative group of sensors, with one sensor selected from each brain region using four methods: highest average correlation, highest entropy, highest mutual information, and highest principal component loading. This targeted approach reduced computational cost and enhanced the effect sizes (ESs), particularly at large scale factors (e.g., 25) linked to delta-band activity, with the PCA-based method achieving the highest ESs (1.043 for sleep quality in older adults). Overall, we expect that both inter- and intra-regional complexity will play a pivotal role in elucidating neural mechanisms as captured by various physiological data modalities-such as EEG, magnetoencephalography, and magnetic resonance imaging-thereby offering promising insights for a range of biomedical applications.

Entropy difference-based EEG channel selection technique for automated detection of ADHD

Attention deficit hyperactivity disorder (ADHD) is one of the common neurodevelopmental disorders in children. This paper presents an automated approach for ADHD detection using the proposed entropy difference (EnD)-based encephalogram (EEG) channel selection approach. In the proposed approach, we selected the most significant EEG channels for the accurate identification of ADHD using an EnD-based channel selection approach. Secondly, a set of features is extracted from the selected channels and fed to a classifier. To verify the effectiveness of the channels selected, we explored three sets of features and classifiers. More specifically, we explored discrete wavelet transform (DWT), empirical mode decomposition (EMD) and symmetrically-weighted local binary pattern (SLBP)-based features. To perform automated classification, we have used k-nearest neighbor (k-NN), Ensemble classifier, and support vectors machine (SVM) classifiers. Our proposed approach yielded the highest accuracy of 99.29% using the public database. In addition, the proposed EnD-based channel selection has consistently provided better classification accuracies than the entropy-based channel selection approach. Also, the developed method has outperformed the existing approaches in automated ADHD detection.

Correlating Data-Driven Muscle Selection Approaches to Synergies for Gait Prediction

Optimizing sensors for physiological input is critical to enhance performance as well as minimize the cost and complexity of assistive devices (e.g. lower-limb exoskeletons). Electromyography (EMG) data can trace muscle activation for gait kinematics prediction. However, identifying optimal muscle groups for electrode placement and the potential variance between users has not yet been established. In this study, we use data-driven channel selection techniques on EMG signals to find muscle group combinations that maximize prediction performance. We apply greedy search (Recursive Feature Elimination, RFE) and variance-based (Principal Component Analysis, PCA) methods to select muscle groups during gait, without prior knowledge of musculoskeletal inter-connectivity. The selected muscle subsets are evaluated using the normalized accuracy of a Multi-Layer Perceptron (MLP), mapping muscle activity to knee flexion angle in a one-step-ahead scheme. The RFE selection led to an average predicted knee angle validation accuracy of % higher than the PCA approach, suggesting that dynamic search is more appropriate than a variance analysis of the signals. Whilst the RFE-selected muscle groups differed across subjects, the selected muscles were consistently spread out over more than 80% of the extracted synergy groups. This study underlines the value of incorporating synergistic information when developing gait prediction models, and reveals that maximizing the number of synergy groups could constitute the basis of muscle selection frameworks.

A Task-Driven Adversarial Channel Selection Method for Binary Classification Based on Magnetocardiography

As the number of sensors in magnetocardiography (MCG) arrays increases to capture detailed cardiac activity, some channels contribute minimally to task performance, resulting in data redundancy and resource consumption. Although existing methods can reduce the number of channels required to meet task demands, they often struggle to balance computational time and the accuracy of the selected channels and overlook the scalability of the selected channels. This limitation means that when environmental conditions change, or when sensors malfunction, redesigning channel configurations becomes necessary, which increases experimental uncertainties. This study introduces a task-driven adversarial channel selection method tailored for binary classification of MCG signals. The optimal channel combination is determined through a group-wise search using a heuristic algorithm, whose objective function is designed to maximize the difference between the classification accuracy and cosine similarity of the selected channel. In evaluations using an MCG dataset from Qilu Hospital of Shandong University, the proposed method successfully reduced the number of channels from 36 to 5 without compromising classification performance. Furthermore, it outperforms existing hybrid sequential forward search method by achieving comparable accuracy with fewer channels, while also demonstrating superior scalability compared to both hybrid sequential forward search and pearson-rank methods. This approach strikes a balance between computational consumption and accuracy, while improving the scalability of the selected channel combinations, enhancing the efficiency and practicality of the MCG system.

Unlocking Dreams and Dreamless Sleep: Machine Learning Classification With Optimal EEG Channels

Research suggests that dreams play a role in the regulation of emotional processing and memory consolidation; electroencephalography (EEG) is useful for studying them, but manual annotation is time-consuming and prone to bias. This study was aimed at developing an EEG-based machine learning (ML) model to automatically identify dream and dreamless states in sleep. We extracted features from EEG data using common spatial patterns (CSPs) and the discrete wavelet transform (DWT) and used them to classify EEG signals into dream and dreamless states using ML models. To determine the most informative channels for classification, we used the permutation-based channel selection method and the nondominated sorting genetic algorithm II (NSGA-II). We evaluated our proposal using a public dataset that is part of the DREAM project, which was collected from 58 EEG channels during rapid eye movement (REM) and non-REM sleep, while 28 subjects reported dream or dreamless experiences. We achieved accuracies greater than 0.85 to distinguish dream and dreamless states using CSP-based feature extraction combined with k-nearest neighbors (KNN), as well as through multiple combinations of EEG channels identified by channel selection methods. Our findings suggest that as few as 8-10 EEG channels may be sufficient for dream recognition. Excluding one subject at a time during model training revealed challenges in generalizing the models to unseen subjects. Channel selection methods have proven to be effective in selecting relevant subsets of EEG channels to classify dreams and dreamless experiences. Our results demonstrate the feasibility of automatic dream detection and highlight the need to improve ML generalization.

Assessing operator stress in collaborative robotics: A multimodal approach

In the era of Industry 4.0, the study of Human-Robot Collaboration (HRC) in advancing modern manufacturing and automation is paramount. An operator approaching a collaborative robot (cobot) may have feelings of distrust, and experience discomfort and stress, especially during the early stages of training. Human factors cannot be neglected: for efficient implementation, the complex psycho-physiological state and responses of the operator must be taken into consideration. In this study, volunteers were asked to carry out a set of cobot programming tasks, while several physiological signals, such as electroencephalogram (EEG), electrocardiogram (ECG), Galvanic skin response (GSR), and facial expressions were recorded. In addition, a subjective questionnaire (NASA-TLX) was administered at the end, to assess if the derived physiological parameters are related to the subjective perception of stress. Parameters exhibiting a higher degree of alignment with subjective perception are mean Theta (76.67%), Alpha (70.53%) and Beta (67.65%) power extracted from EEG, recovery time (72.86%) and rise time (71.43%) extracted from GSR and heart rate variability (HRV) metrics PNN25 (71.58%), SDNN (70.53%), PNN50 (68.95%) and RMSSD (66.84%). Parameters extracted from raw RR Intervals appear to be more variable and less accurate (42.11%) so as recorded emotions (51.43%).

Optimal channel and feature selection for automatic prediction of functional brain age of preterm infant based on EEG

Introduction

Approximately 15 million premature infants are born each year, many of whom face risks of neurological impairments. Accurate assessment of brain maturity is crucial for timely intervention and treatment planning. Electroencephalography (EEG) is a noninvasive method commonly used for this purpose. However, using all channels and features for brain maturity assessment can lead to high computational burden and overfitting, which can decrease the performance of the prediction system.

Methods

In this study, we propose an automatic prediction framework based on EEG to predict functional brain age (FBA) for assessing brain maturity in preterm infants. To optimize channel selection, we combine Binary Particle Swarm Optimization (BPSO) with Forward Addition (FA) and Backward Elimination (BE) methods. For feature selection, we combine the Pearson Correlation Coefficient (PCC), Recursive Feature Elimination (RFE), and Support Vector Regression (SVR) model.

Results

The proposed framework achieved a prediction accuracy of 76.71% within ±1 week and 94.52% within ±2 weeks. Effective channel and feature selection significantly improved model performance while reducing computational costs.

Discussion

These results demonstrate that optimizing channel and feature selection can enhance the performance of FBA prediction in preterm infants, offering a more efficient and accurate tool for brain maturity assessment.

A cross-domain-based channel selection method for motor imagery

Selecting channels for motor imagery (MI)-based brain-computer interface (BCI) systems can not only enhance the portability of the systems, but also improve the decoding performance. Hence, we propose a cross-domain-based channel selection (CDCS) approach, which effectively minimizes the number of EEG channels used while maintaining high accuracy in MI recognition. The EEG source imaging (ESI) technique is employed to map scalp EEG into the cortical source domain. We divide the equivalent dipoles in the source domain into different regions by k-means clustering. Then, we calculate the band energy (5-40 Hz) of time series of dipoles in these regions by power spectral density (PSD), and the regions with the highest and lowest band energy are selected as the region of interests (ROIs) in the source domain. Subsequently, Pearson correlation coefficients between the dipole time series in ROIs and scalp EEG are used as the criterion for channel selection and a multi-trial-sorting-based channel selection strategy is proposed. Finally, we propose the CDCS-based MI classification framework, where common spatial pattern is applied to extract features and linear discriminant analysis is used to identify MI tasks. The CDCS method demonstrated significant improvement in decoding accuracy on two public datasets, achieving increases of 18.51% and 13.37% compared to all-channel method, and 10.74% and 3.43% compared to the three-channel method. The experimental results validated that CDCS is effective in selecting important channels.

Coherence-based channel selection and Riemannian geometry features for magnetoencephalography decoding

Magnetoencephalography (MEG) records the extremely weak magnetic fields on the surface of the scalp through highly sensitive sensors. Multi-channel MEG data provide higher spatial and temporal resolution when measuring brain activities, and can be applied for brain-computer interfaces as well. However, a large number of channels leads to high computational complexity and can potentially impact decoding accuracy. To improve the accuracy of MEG decoding, this paper proposes a new coherence-based channel selection method that effectively identifies task-relevant channels, reducing the presence of noisy and redundant information. Riemannian geometry is then used to extract effective features from selected channels of MEG data. Finally, MEG decoding is achieved by training a support vector machine classifier with the Radial Basis Function kernel. Experiments were conducted on two public MEG datasets to validate the effectiveness of the proposed method. The results from Dataset 1 show that Riemannian geometry achieves higher classification accuracy (compared to common spatial patterns and power spectral density) in the single-subject visual decoding task. Moreover, coherence-based channel selection significantly (P = 0.0002) outperforms the use of all channels. Moving on to Dataset 2, the results reveal that coherence-based channel selection is also significantly (P <0.0001) superior to all channels and channels around C3 and C4 in cross-session mental imagery decoding tasks. Additionally, the proposed method outperforms state-of-the-art methods in motor imagery tasks.

Predicting an EEG-Based hypnotic time estimation with non-linear kernels of support vector machine algorithm

Our ability to measure time is vital for daily life, technology use, and even mental health; however, separating pure time perception from other mental processes (like emotions) is a research challenge requiring precise tests to isolate and understand brain activity solely related to time estimation. To address this challenge, we designed an experiment utilizing hypnosis alongside electroencephalography (EEG) to assess differences in time estimation, namely underestimation and overestimation. Hypnotic induction is designed to reduce awareness and meta-awareness, facilitating a detachment from the immediate environment. This reduced information processing load minimizes the need for elaborate internal thought during hypnosis, further simplifying the cognitive landscape. To predict time perception based on brain activity during extended durations (5 min), we employed artificial intelligence techniques. Utilizing Support Vector Machines (SVMs) with both radial basis function (RBF) and polynomial kernels, we assessed their effectiveness in classifying time perception-related brain patterns. We evaluated various feature combinations and different algorithms to identify the most accurate configuration. Our analysis revealed an impressive 80.9% classification accuracy for time perception detection using the RBF kernel, demonstrating the potential of AI in decoding this complex cognitive function.

Combination of Channel Reordering Strategy and Dual CNN-LSTM for Epileptic Seizure Prediction Using Three iEEG Datasets

OBJECTIVE

Intracranial electroencephalogram (iEEG) signals are generally recorded using multiple channels, and channel selection is therefore a significant means in studying iEEG-based seizure prediction. For n channels, [Formula: see text] channel cases can be generated for selection. However, by this means, an increase in n can cause an exponential increase in computational consumption, which may result in a failure of channel selection when n is too large. Hence, it is necessary to explore reasonable channel selection strategies under the premise of controlling computational consumption and ensuring high classification accuracy. Given this, we propose a novel method of channel reordering strategy combined with dual CNN-LSTM for effectively predicting seizures.

METHOD

First, for each patient with n channels, interictal and preictal iEEG samples from each single channel are input into the CNN-LSTM model for classification. Then, the F1-score of each single channel is calculated, and the channels are reordered in descending order according to the size of F1-scores (channel reordering strategy). Next, iEEG signals with an increasing number of channels are successively fed into the CNN-LSTM model for classification again. Finally, according to the classification results from n channel cases, the channel case with the highest classification rate is selected.

RESULTS

Our method is evaluated on the three iEEG datasets: the Freiburg, the SWEC-ETHZ and the American Epilepsy Society Seizure Prediction Challenge (AES-SPC). At the event-based level, the sensitivities of 100%, 100% and 90.5%, and the false prediction rates (FPRs) of 0.10/h, 0/h and 0.47/h, are achieved for the three datasets, respectively. Moreover, compared to an unspecific random predictor, our method also shows a better performance for all patients and dogs from the three datasets. At the segment-based level, the sensitivities-specificities-accuracies-AUCs of 88.1%-94.0%-93.5%-0.9101, 99.1%-99.7%-99.6%-0.9935, and 69.2%-79.9%-78.2%-0.7373, are attained for the three datasets, respectively.

CONCLUSION

Our method can effectively predict seizures and address the challenge of an excessive number of channels during channel selection.

A comprehensive survey of evolutionary algorithms and metaheuristics in brain EEG-based applications

Electroencephalography (EEG) has emerged as a primary non-invasive and mobile modality for understanding the complex workings of the human brain, providing invaluable insights into cognitive processes, neurological disorders, and brain-computer interfaces. Nevertheless, the volume of EEG data, the presence of artifacts, the selection of optimal channels, and the need for feature extraction from EEG data present considerable challenges in achieving meaningful and distinguishing outcomes for machine learning algorithms utilized to process EEG data. Consequently, the demand for sophisticated optimization techniques has become imperative to overcome these hurdles effectively. Evolutionary algorithms (EAs) and other nature-inspired metaheuristics have been applied as powerful design and optimization tools in recent years, showcasing their significance in addressing various design and optimization problems relevant to brain EEG-based applications. This paper presents a comprehensive survey highlighting the importance of EAs and other metaheuristics in EEG-based applications. The survey is organized according to the main areas where EAs have been applied, namely artifact mitigation, channel selection, feature extraction, feature selection, and signal classification. Finally, the current challenges and future aspects of EAs in the context of EEG-based applications are discussed.

Automatic detection of Alzheimer's disease from EEG signals using an improved AFS-GA hybrid algorithm

Alzheimer's Disease (AD) is a neurodegenerative disorder characterized by energy diffusion and partial disconnection in the brain, with its main feature being an insidious onset and subtle clinical symptoms. Electroencephalogram (EEG) as a primary tool for assessing and aiding in the diagnosis of brain diseases has been widely used in AD detection. Accurate diagnosis is crucial for preventing the transition from early cognitive impairment to AD and providing early treatment for AD patients. This study aims to establish a hybrid model based on the Improved Artificial Fish Swarm Algorithm (IAFS) and Genetic Algorithm (GA)-IAFS-GA, to determine the optimal channel combination for AD detection under multiple EEG signals. Geometric features and complexity features of AD EEG signals were extracted using Second Order Difference Plot (SODP) and entropy analysis across the full frequency band. Subsequently, Pearson correlation was used for feature ranking, selecting the six least correlated features for each channel. The Relief algorithm was then used to fuse these selected features, with one fused feature representing one channel. Based on this, a feature selection optimization algorithm, IAFS-GA, combining the improved artificial fish swarm algorithm and genetic algorithm, was proposed. Finally, the feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. The feature combination was input into a Naive Bayes classifier for the identification of AD patients and normal controls. Using a five-fold cross-validation strategy across the entire frequency band, the classification accuracy reached 93.53%, with a sensitivity of 98.74%, specificity of 98.25%, and an AUC area of 97.82%. This framework can quickly select appropriate brain channels to enhance the efficiency of detecting AD and other neurological diseases. Moreover, it is the first time that an improved artificial fish swarm genetic combination algorithm and SODP features has been used for channel selection in EEG, proving to be an effective method for AD detection. It is based on SODP analysis, entropy analysis, and intelligent algorithms, which can assist clinicians in rapidly diagnosing AD, reducing the misdiagnosis rate of false positives, and expanding our understanding of brain function in patients with neurological diseases.

A zero precision loss framework for EEG channel selection: enhancing efficiency and maintaining interpretability

The brain-computer interface (BCI) systems based on motor imagery typically rely on a large number of electrode channels to acquire information. The rational selection of electroencephalography (EEG) channel combinations is crucial for optimizing computational efficiency and enhancing practical applicability. However, evaluating all potential channel combinations individually is impractical. This study aims to explore a strategy for quickly achieving a balance between maximizing channel reduction and minimizing precision loss. To this end, we developed a spatio-temporal attention perception network named STAPNet. Based on the channel contributions adaptively generated by its subnetwork, we propose an extended step bi-directional search strategy that includes variable ratio channel selection (VRCS) and strided greedy channel selection (SGCS), designed to enhance global search capabilities and accelerate the optimization process. Experimental results show that on the High Gamma and BCI Competition IV 2a public datasets, the framework respectively achieved average maximum accuracies of 91.47% and 84.17%. Under conditions of zero precision loss, the average number of channels was reduced by a maximum of 87.5%. Additionally, to investigate the impact of neural information loss due to channel reduction on the interpretation of complex brain functions, we employed a heatmap visualization algorithm to verify the universal importance and complete symmetry of the selected optimal channel combination across multiple datasets. This is consistent with the brain's cooperative mechanism when processing tasks involving both the left and right hands.

Unsupervised separation of nonlinearly mixed event-related potentials using manifold clustering and non-negative matrix factorization

Event-related potentials (ERPs) can quantify brain responses to reveal the neural mechanisms of sensory perception. However, ERPs often reflect nonlinear mixture responses to multiple sources of sensory stimuli, and an accurate separation of the response to each stimulus remains a challenge. This study aimed to separate the ERP into nonlinearly mixed source components specific to individual stimuli. We developed an unsupervised learning method based on clustering of manifold structures of mixture signals combined with channel optimization for signal source reconstruction using non-negative matrix factorization (NMF). Specifically, we first implemented manifold learning based on Local Tangent Space Alignment (LTSA) to extract the spatial manifold structure of multi-resolution sub-signals separated via wavelet packet transform. We then used fuzzy entropy to extract the dynamical process of the manifold structures and performed a k-means clustering to separate different sources. Lastly, we used NMF to obtain the optimal contributions of multiple channels to ensure accurate source reconstructions. We evaluated our developed approach using a simulated ERP dataset with known ground truth of two components of ERP mixture signals. Our results show that the correlation coefficient between the reconstructed source signal and the true source signal was 92.8 % and that the separation accuracy in ERP amplitude was 91.6 %. The results show that our unsupervised separation approach can accurately separate ERP signals from nonlinear mixture source components. The outcomes provide a promising way to isolate brain responses to multiple stimulus sources during multisensory perception.

Scalp Electroencephalogram-Derived Involvement Indexes during a Working Memory Task Performed by Patients with Epilepsy

Electroencephalography (EEG) wearable devices are particularly suitable for monitoring a subject's engagement while performing daily cognitive tasks. EEG information provided by wearable devices varies with the location of the electrodes, the suitable location of which can be obtained using standard multi-channel EEG recorders. Cognitive engagement can be assessed during working memory (WM) tasks, testing the mental ability to process information over a short period of time. WM could be impaired in patients with epilepsy. This study aims to evaluate the cognitive engagement of nine patients with epilepsy, coming from a public dataset by Boran et al., during a verbal WM task and to identify the most suitable location of the electrodes for this purpose. Cognitive engagement was evaluated by computing 37 engagement indexes based on the ratio of two or more EEG rhythms assessed by their spectral power. Results show that involvement index trends follow changes in cognitive engagement elicited by the WM task, and, overall, most changes appear most pronounced in the frontal regions, as observed in healthy subjects. Therefore, involvement indexes can reflect cognitive status changes, and frontal regions seem to be the ones to focus on when designing a wearable mental involvement monitoring EEG system, both in physiological and epileptic conditions.

Rapid Mental Workload Detection of Air Traffic Controllers with Three EEG Sensors

Air traffic controllers' mental workload significantly impacts their operational efficiency and safety. Detecting their mental workload rapidly and accurately is crucial for preventing aviation accidents. This study introduces a mental workload detection model for controllers based on power spectrum features related to gamma waves. The model selects the feature with the highest classification accuracy, β + θ + α + γ, and utilizes the mRMR (Max-Relevance and Min-Redundancy) algorithm for channel selection. Furthermore, the channels that were less affected by ICA processing were identified, and the reliability of this result was demonstrated by artifact analysis brought about by EMG, ECG, etc. Finally, a model for rapid mental workload detection for controllers was developed and the detection rate for the 34 subjects reached 1, and the accuracy for the remaining subjects was as low as 0.986. In conclusion, we validated the usability of the mRMR algorithm in channel selection and proposed a rapid method for detecting mental workload in air traffic controllers using only three EEG channels. By reducing the number of EEG channels and shortening the data processing time, this approach simplifies equipment application and maintains detection accuracy, enhancing practical usability.

Effects of tDCS on emotion recognition and brain oscillations

INTRODUCTION

Emotion recognition, the ability to interpret the emotional state of individuals by looking at their facial expressions, is essential for healthy social interactions and communication. There is limited research on the effects of tDCS on emotion recognition in the literature. This study aimed to investigate the effects of anodal stimulation of the ventromedial prefrontal cortex (vmPFC), a key region for emotion recognition from facial expressions, on emotion recognition and brain oscillations.

METHOD

A single-blind randomized-controlled study was conducted with 54 healthy participants. Before and after brain stimulation emotion recognition tasks were administered and resting-state EEG were recorded. The changes in task performances and brain oscillations were analyzed using repeated-measures two-way ANOVA analysis.

RESULTS

There was no significant difference in the emotion recognition tasks between groups in pre-post measurements. The changes in delta, theta, alpha, beta and gamma frequency bands in the frontal, temporal, and posterio-occipital regions, which were determined as regions of interest in resting state EEG data before and after tDCS, were compared between groups. The results showed that there was a significant difference between groups only in delta frequency before and after tDCS in the frontal and temporal regions. While an increase in delta activity was observed in the experimental group in the frontal and temporal regions, a decrease was observed in the control group.

CONCLUSIONS

The tDCS may not have improved emotion recognition because it may not have had the desired effect on the vmPFC, which is in the lower part of the prefrontal lobe. The changes in EEG frequencies observed section tDCS may be similar to those seen in some pathological processes, which could explain the lack of improvement in emotion recognition. Future studies to be carried out for better understand this effect are important.

Scalp EEG Correlates of Anti-Seizure Medications in Adult Epilepsy

An anti-seizure medication (ASM) regimen that relieves seizure burden for patients with epilepsy can take weeks to months to establish or become ineffective over time and require revision. There is no clear clinical algorithm for choosing one specific ASM regimen over another, and an ASM is often chosen based on a patient's individual characteristics and electroencephalogram (EEG). These approaches can vary from patient to patient and may be prohibitive in low-resource settings. In this work, we present an objective, quantitative, and automated approach to measure ASM efficacy utilizing scalp EEG from three groups of adults: epilepsy patients on ineffective ASMs, epilepsy patients on effective ASMs, and healthy controls. For each patient, we build a dynamical network model (DNM) from resting state EEG that estimates regional interactions over time using a novel source-sink (SS) index. We demonstrate that patients with ineffective ASMs exhibit more abrupt changes in the SS index throughout a scalp EEG than patients with effective ASMs or healthy controls. Our proposed process may provide a quantitative correlate for ASMs that can be used to compare regimens for individual patients.

Schizophrenia detection using Entropy Difference-based Electroencephalogram Channel Selection Approach

In this work, we propose a novel approach for identifying schizophrenia using an entropy difference (ED)- based electroencephalogram (EEG) channel selection algorithm. At the core of our approach is an ED-based channel selection algorithm, which selects the most significant EEG channels that contain discriminative information for schizophrenia detection using entropy difference values. This process not only selects the discriminative channels but also reduces the computational complexity of schizophrenia detection. After selecting the significant channels, we decompose the selected EEG signals into subbands using discrete wavelet transform (DWT). Furthermore, we extract symmetrically-weighted local binary patterns to capture subband variations. The features are then subjected to the support vector machine (SVM) to differentiate individuals with schizophrenia based on their EEG signals. The proposed approach achieves a classification accuracy of 100% when features from only one channel are used, outperforming the existing approaches in schizophrenia detection. Also, the ED-based channel selection approach outperforms the existing entropy-based channel selection approach in schizophrenia detection.

Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

An Explainable and Generalizable Recurrent Neural Network Approach for Differentiating Human Brain States on EEG Dataset

Electroencephalogram (EEG) is one of the most widely used brain computer interface (BCI) approaches. Despite the success of existing EEG approaches in brain state recognition studies, it is still challenging to differentiate brain states via explainable and generalizable deep learning approaches. In other words, how to explore meaningful and distinguishing features and how to overcome the huge variability and overfitting problem still need to be further studied. To alleviate these challenges, in this work, a multiple random fragment search-based multilayer recurrent neural network (MRFS-MRNN) is proposed to improve the differentiating performance and explore meaningful patterns. Specifically, an explainable MRNN module is proposed to capture the temporal dependences preserved in EEG time series. Besides, a MRFS module is designed to cut multiple random fragments from the entire EEG signal time course to improve the effectiveness of brain state differentiating ability. MRFS-MRNN is concatenatedto effectively overcome the huge variabilities and overfitting problems. Experiment results demonstrate that the proposed MRFS-MRNN model not only has excellent differentiating performance, but also has good explanation and generalization ability. The classification accuracies reach as high as 95.18% for binary classification and 89.19% for four-category classification on the individual level. Similarly, 95.53% and 85.84% classification accuracies are obtained for the binary and four-category classification on the group level. What's more, 94.28% and 85.43% classification accuracies of binary and four-category classifications are achieved for predicting brand new subjects. The experiment results showed that the proposed method outperformed other state-of-the-art (SOTA) models on the same underlying data and improved the explanation and generalization ability.

Selecting EEG channels and features using multi-objective optimization for accurate MCI detection: validation using leave-one-subject-out strategy

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice.

Two-stage sparse multi-objective evolutionary algorithm for channel selection optimization in BCIs

Background

Channel selection has become the pivotal issue affecting the widespread application of non-invasive brain-computer interface systems in the real world. However, constructing suitable multi-objective problem models alongside effective search strategies stands out as a critical factor that impacts the performance of multi-objective channel selection algorithms. This paper presents a two-stage sparse multi-objective evolutionary algorithm (TS-MOEA) to address channel selection problems in brain-computer interface systems.

Methods

In TS-MOEA, a two-stage framework, which consists of the early and late stages, is adopted to prevent the algorithm from stagnating. Furthermore, The two stages concentrate on different multi-objective problem models, thereby balancing convergence and population diversity in TS-MOEA. Inspired by the sparsity of the correlation matrix of channels, a sparse initialization operator, which uses a domain-knowledge-based score assignment strategy for decision variables, is introduced to generate the initial population. Moreover, a Score-based mutation operator is utilized to enhance the search efficiency of TS-MOEA.

Results

The performance of TS-MOEA and five other state-of-the-art multi-objective algorithms has been evaluated using a 62-channel EEG-based brain-computer interface system for fatigue detection tasks, and the results demonstrated the effectiveness of TS-MOEA.

Conclusion

The proposed two-stage framework can help TS-MOEA escape stagnation and facilitate a balance between diversity and convergence. Integrating the sparsity of the correlation matrix of channels and the problem-domain knowledge can effectively reduce the computational complexity of TS-MOEA while enhancing its optimization efficiency.

Motor Imagery Classification Using Effective Channel Selection of Multichannel EEG

Electroencephalography (EEG) is effectively employed to describe cognitive patterns corresponding to different tasks of motor functions for brain-computer interface (BCI) implementation. Explicit information processing is necessary to reduce the computational complexity of practical BCI systems. This paper presents an entropy-based approach to select effective EEG channels for motor imagery (MI) classification in brain-computer interface (BCI) systems. The method identifies channels with higher entropy scores, which is an indication of greater information content. It discards redundant or noisy channels leading to reduced computational complexity and improved classification accuracy. High entropy means a more disordered pattern, whereas low entropy means a less disordered pattern with less information. The entropy of each channel for individual trials is calculated. The weight of each channel is represented by the mean entropy of the channel over all the trials. A set of channels with higher mean entropy are selected as effective channels for MI classification. A limited number of sub-band signals are created by decomposing the selected channels. To extract the spatial features, the common spatial pattern (CSP) is applied to each sub-band space of EEG signals. The CSP-based features are used to classify the right-hand and right-foot MI tasks using a support vector machine (SVM). The effectiveness of the proposed approach is validated using two publicly available EEG datasets, known as BCI competition III-IV(A) and BCI competition IV-I. The experimental results demonstrate that the proposed approach surpasses cutting-edge techniques.

Multilayer network-based channel selection for motor imagery brain-computer interface

Objective. The number of electrode channels in a motor imagery-based brain-computer interface (MI-BCI) system influences not only its decoding performance, but also its convenience for use in applications. Although many channel selection methods have been proposed in the literature, they are usually based on the univariate features of a single channel. This leads to a loss of the interaction between channels and the exchange of information between networks operating at different frequency bands.Approach. We integrate brain networks containing four frequency bands into a multilayer network framework and propose a multilayer network-based channel selection (MNCS) method for MI-BCI systems. A graph learning-based method is used to estimate the multilayer network from electroencephalogram (EEG) data that are filtered by multiple frequency bands. The multilayer participation coefficient of the multilayer network is then computed to select EEG channels that do not contain redundant information. Furthermore, the common spatial pattern (CSP) method is used to extract effective features. Finally, a support vector machine classifier with a linear kernel is trained to accurately identify MI tasks.Main results. We used three publicly available datasets from the BCI Competition containing data on 12 healthy subjects and one dataset containing data on 15 stroke patients to validate the effectiveness of our proposed method. The results showed that the proposed MNCS method outperforms all channels (85.8% vs. 93.1%, 84.4% vs. 89.0%, 71.7% vs. 79.4%, and 72.7% vs. 84.0%). Moreover, it achieved significantly higher decoding accuracies on MI-BCI systems than state-of-the-art methods (pairedt-tests,p< 0.05).Significance. The experimental results showed that the proposed MNCS method can select appropriate channels to improve the decoding performance as well as the convenience of the application of MI-BCI systems.

Channel Selection for Stereo- Electroencephalography (SEEG)-Based Invasive Brain-Computer Interfaces Using Deep Learning Methods

Brain-computer interfaces (BCIs) can enable direct communication with assistive devices by recording and decoding signals from the brain. To achieve high performance, many electrodes will be used, such as the recently developed invasive BCIs with channel numbers up to hundreds or even thousands. For those high-throughput BCIs, channel selection is important to reduce signal redundancy and invasiveness while maintaining decoding performance. However, such endeavour is rarely reported for invasive BCIs, especially those using deep learning methods. Two deep learning-based methods, referred to as Gumbel and STG, were proposed in this paper. They were evaluated using the Stereo-electroencephalography (SEEG) signals, and compared with three other methods, including manual selection, mutual information-based method (MI), and all channels (all channels without selection). The task is to classify the SEEG signals into five movements using channels selected by each method. When 10 channels were selected, the mean classification accuracies using Gumbel, STG (referred to as STG-10), manual selection, and MI selection were 65%, 60%, 60%, and 47%, respectively, whilst the accuracy was 59% using all channels (no selection). In addition, an investigation of the selected channels showed that Gumbel and STG have successfully identified the pre-central and post-central areas, which are closely related to motor control. Both Gumbel and STG successfully selected the informative channels in SEEG recordings while maintaining decoding accuracy. This study enables future high-throughput BCIs using deep learning methods, to identify useful channels and reduce computing and wireless transmission pressure.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

Decoding Bilingual EEG Signals With Complex Semantics Using Adaptive Graph Attention Convolutional Network

Decoding neural signals of silent reading with Brain-Computer Interface (BCI) techniques presents a fast and intuitive communication method for severely aphasia patients. Electroencephalogram (EEG) acquisition is convenient and easily wearable with high temporal resolution. However, existing EEG-based decoding units primarily concentrate on individual words due to their low signal-to-noise ratio, rendering them insufficient for facilitating daily communication. Decoding at the word level is less efficient than decoding at the phrase or sentence level. Furthermore, with the popularity of multilingualism, decoding EEG signals with complex semantics under multiple languages is highly urgent and necessary. To the best of our knowledge, there is currently no research on decoding EEG signals during silent reading of complex semantics, let alone decoding silent reading EEG signals with complex semantics for bilingualism. Moreover, the feasibility of decoding such signals remains to be investigated. In this work, we collect silent reading EEG signals of 9 English Phrases (EP), 7 English Sentences (ES), 10 Chinese Phrases (CP), and 7 Chinese Sentences (CS) from the subject within 26 days. We propose a novel Adaptive Graph Attention Convolution Network (AGACN) for classification. Experimental results demonstrate that our proposed method outperforms state-of-the-art methods, achieving the highest classification accuracy of 54.70%, 62.26%, 44.55%, and 57.14% for silent reading EEG signals of EP, ES, CP, and CS, respectively. Moreover, our results prove the feasibility of complex semantics EEG signal decoding. This work will aid aphasic patients in achieving regular communication while providing novel ideas for neural signal decoding research.

Toward practical machine-learning-based diagnosis for drug-naïve women with major depressive disorder using EEG channel reduction approach

BACKGROUND

A machine-learning-based computer-aided diagnosis (CAD) system can complement the traditional diagnostic error for major depressive disorder (MDD) using trait-like neurophysiological biomarkers. Previous studies have shown that the CAD system has the potential to differentiate between female MDD patients and healthy controls. The aim of this study was to develop a practically useful resting-state electroencephalography (EEG)-based CAD system to assist in the diagnosis of drug-naïve female MDD patients by considering both the drug and gender effects. In addition, the feasibility of the practical use of the resting-state EEG-based CAD system was evaluated using a channel reduction approach.

METHODS

Eyes-closed, resting-state EEG data were recorded from 49 drug-naïve female MDD patients and 49 sex-matched healthy controls. Six different EEG feature sets were extracted: power spectrum densities (PSDs), phase-locking values (PLVs), and network indices for both sensor- and source-level, and four different EEG channel montages (62, 30, 19, and 10-channels) were designed to investigate the channel reduction effects in terms of classification performance.

RESULTS

The classification performances for each feature set were evaluated using a support vector machine with leave-one-out cross-validation. The optimum classification performance was achieved when using sensor-level PLVs (accuracy: 83.67 % and area under curve: 0.92). Moreover, the classification performance was maintained until the number of EEG channels was reduced to 19 (over 80 % accuracy).

CONCLUSION

We demonstrated the promising potential of sensor-level PLVs as diagnostic features when developing a resting-state EEG-based CAD system for the diagnosis of drug-naïve female MDD patients and verified the feasibility of the practical use of the developed resting-state EEG-based CAD system using the channel reduction approach.

A Robust Gaze Estimation Approach via Exploring Relevant Electrooculogram Features and Optimal Electrodes Placements

Gaze estimation, as a technique that reflects individual attention, can be used for disability assistance and assisting physicians in diagnosing diseases such as autism spectrum disorder (ASD), Parkinson's disease, and attention deficit hyperactivity disorder (ADHD). Various techniques have been proposed for gaze estimation and achieved high resolution. Among these approaches, electrooculography (EOG)-based gaze estimation, as an economical and effective method, offers a promising solution for practical applications.

OBJECTIVE

In this paper, we systematically investigated the possible EOG electrode locations which are spatially distributed around the orbital cavity. Afterward, quantities of informative features to characterize physiological information of eye movement from the temporal-spectral domain are extracted from the seven differential channels.

METHODS AND PROCEDURES

To select the optimum channels and relevant features, and eliminate irrelevant information, a heuristical search algorithm (i.e., forward stepwise strategy) is applied. Subsequently, a comparative analysis of the impacts of electrode placement and feature contributions on gaze estimation is evaluated via 6 classic models with 18 subjects.

RESULTS

Experimental results showed that the promising performance was achieved both in the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) within a wide gaze that ranges from -50° to +50°. The MAE and RMSE can be improved to 2.80° and 3.74° ultimately, while only using 10 features extracted from 2 channels. Compared with the prevailing EOG-based techniques, the performance improvement of MAE and RMSE range from 0.70° to 5.48° and 0.66° to 5.42°, respectively.

CONCLUSION

We proposed a robust EOG-based gaze estimation approach by systematically investigating the optimal channel/feature combination. The experimental results indicated not only the superiority of the proposed approach but also its potential for clinical application. Clinical and translational impact statement: Accurate gaze estimation is a key step for assisting disabilities and accurate diagnosis of various diseases including ASD, Parkinson's disease, and ADHD. The proposed approach can accurately estimate the points of gaze via EOG signals, and thus has the potential for various related medical applications.

Electroencephalogram-Based Subject Matching Learning (ESML): A Deep Learning Framework on Electroencephalogram-Based Biometrics and Task Identification

An EEG signal (Electroencephalogram) is a bioelectric phenomenon reflecting human brain activities. In this paper, we propose a novel deep learning framework ESML (EEG-based Subject Matching Learning) using raw EEG signals to learn latent representations for EEG-based user identification and tack classification. ESML consists of two parts: one is the ESML1 model via an LSTM-based method for EEG-user linking, and one is the ESML2 model via a CNN-based method for EEG-task linking. The new model ESML is simple, but effective and efficient. It does not require any restrictions for EEG data collection on motions and thinking for users, and it does not need any EEG preprocessing operations, such as EEG denoising and feature extraction. The experiments were conducted on three public datasets and the results show that ESML performs the best and achieves significant performance improvement when compared to baseline methods (i.e., SVM, LDA, NN, DTS, Bayesian, AdaBoost and MLP). The ESML1 model provided the best precision at 96% with 109 users and the ESML2 model achieved 99% precision at 3-Class task classification. These experimental results provide direct evidence that EEG signals can be used for user identification and task classification.

Differentiating brain states via multi-clip random fragment strategy-based interactive bidirectional recurrent neural network

EEG is widely adopted to study the brain and brain computer interface (BCI) for its non-invasiveness and low costs. Specifically EEG can be applied to differentiate brain states, which is important for better understanding the working mechanisms of the brain. Recurrent neural network (RNN)-based learning strategy has been widely utilized to differentiate brain states, because its optimization architectures improve the classification performance for differentiating brain states at the group level. However, present classification performance is still far from satisfactory. We have identified two major focal points for improvements: one is about organizing the input EEG signals, and the other is related to the design of the RNN architecture. To optimize the above-mentioned issues and achieve better brain state classification performance, we propose a novel multi-clip random fragment strategy-based interactive bidirectional recurrent neural network (McRFS-IBiRNN) model in this work. This model has two advantages over previous methods. First, the McRFS component is designed to re-organize the input EEG signals to make them more suitable for the RNN architecture. Second, the IBiRNN component is an innovative design to model the RNN layers with interaction connections to enhance the fusion of bidirectional features. By adopting the proposed model, promising brain states classification performances are obtained. For example, 96.97% and 99.34% of individual and group level four-category classification accuracies are successfully obtained on the EEG motor/imagery dataset, respectively. A 99.01% accuracy can be observed for four-category classification tasks with new subjects not seen before, which demonstrates the generalization of our proposed method. Compared with existing methods, our model outperforms them with superior results. Overall, the proposed McRFS-IBiRNN model demonstrates great superiority in differentiating brain states on EEG signals.

Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.

Depression Recognition From EEG Signals Using an Adaptive Channel Fusion Method via Improved Focal Loss

Depression is a serious and common psychiatric disease characterized by emotional and cognitive dysfunction. In addition, the rates of clinical diagnosis and treatment for depression are low. Therefore, the accurate recognition of depression is important for its effective treatment. Electroencephalogram (EEG) signals, which can objectively reflect the inner states of human brains, are regarded as promising physiological tools that can enable effective and efficient clinical depression diagnosis and recognition. However, one of the challenges regarding EEG-based depression recognition involves sufficiently optimizing the spatial information derived from the multichannel space of EEG signals. Consequently, we propose an adaptive channel fusion method via improved focal loss (FL) functions for depression recognition based on EEG signals to effectively address this challenge. In this method, we propose two improved FL functions that can enhance the separability of hard examples by upweighting their losses as optimization objectives and can optimize the channel weights by a proposed adaptive channel fusion framework. The experimental results obtained on two EEG datasets show that the developed channel fusion method can achieve improved classification performance. The learned channel weights include the individual characteristics of each EEG epoch, which can effectively optimize the spatial information of each EEG epoch via the channel fusion method. In addition, the proposed method performs better than the state-of-the-art channel fusion methods.

Kernel-based Nonlinear Manifold Learning for EEG-based Functional Connectivity Analysis and Channel Selection with Application to Alzheimer's Disease

Dynamical, causal, and cross-frequency coupling analysis using the electroencephalogram (EEG) has gained significant attention for diagnosing and characterizing neurological disorders. Selecting important EEG channels is crucial for reducing computational complexity in implementing these methods and improving classification accuracy. In neuroscience, measures of (dis)similarity between EEG channels are often used as functional connectivity (FC) features, and important channels are selected via feature selection. Developing a generic measure of (dis)similarity is important for FC analysis and channel selection. In this study, learning of (dis)similarity information within the EEG is achieved using kernel-based nonlinear manifold learning. The focus is on FC changes and, thereby, EEG channel selection. Isomap and Gaussian Process Latent Variable Model (Isomap-GPLVM) are employed for this purpose. The resulting kernel (dis)similarity matrix is used as a novel measure of linear and nonlinear FC between EEG channels. The analysis of EEG from healthy controls (HC) and patients with mild to moderate Alzheimer's disease (AD) are presented as a case study. Classification results are compared with other commonly used FC measures. Our analysis shows significant differences in FC between bipolar channels of the occipital region and other regions (i.e. parietal, centro-parietal, and fronto-central) between AD and HC groups. Furthermore, our results indicate that FC changes between channels along the fronto-parietal region and the rest of the EEG are important in diagnosing AD. Our results and its relation to functional networks are consistent with those obtained from previous studies using fMRI, resting-state fMRI and EEG.

Multidomain Convolution Neural Network Models for Improved Event-Related Potential Classification

Two convolution neural network (CNN) models are introduced to accurately classify event-related potentials (ERPs) by fusing frequency, time, and spatial domain information acquired from the continuous wavelet transform (CWT) of the ERPs recorded from multiple spatially distributed channels. The multidomain models fuse the multichannel Z-scalograms and the V-scalograms, which are generated from the standard CWT scalogram by zeroing-out and by discarding the inaccurate artifact coefficients that are outside the cone of influence (COI), respectively. In the first multidomain model, the input to the CNN is generated by fusing the Z-scalograms of the multichannel ERPs into a frequency-time-spatial cuboid. The input to the CNN in the second multidomain model is formed by fusing the frequency-time vectors of the V-scalograms of the multichannel ERPs into a frequency-time-spatial matrix. Experiments are designed to demonstrate (a) customized classification of ERPs, where the multidomain models are trained and tested with the ERPs of individual subjects for brain-computer interface (BCI)-type applications, and (b) group-based ERP classification, where the models are trained on the ERPs from a group of subjects and tested on single subjects not included in the training set for applications such as brain disorder classification. Results show that both multidomain models yield high classification accuracies for single trials and small-average ERPs with a small subset of top-ranked channels, and the multidomain fusion models consistently outperform the best unichannel classifiers.

Seizure detection with reduced electroencephalogram channels: research trends and outlook

Epilepsy is a prevalent condition characterized by recurrent, unpredictable seizures. Monitoring with surface electroencephalography (EEG) is the gold standard for diagnosing epilepsy, but a time-consuming, uncomfortable and sometimes ineffective process for patients. Further, using EEG over a brief monitoring period has variable success, dependent on patient tolerance and seizure frequency. The availability of hospital resources and hardware and software specifications inherently restrict the options for comfortable, long-term data collection, resulting in limited data for training machine-learning models. This mini-review examines the current patient journey, providing an overview of the current state of EEG monitoring with reduced electrodes and automated channel reduction methods. Opportunities for improving data reliability through multi-modal data fusion are suggested. We assert the need for further research in electrode reduction to advance brain monitoring solutions towards portable, reliable devices that simultaneously offer patient comfort, perform ultra-long-term monitoring and expedite the diagnosis process.

Driving drowsiness detection using spectral signatures of EEG-based neurophysiology

Introduction: Drowsy driving is a significant factor causing dire road crashes and casualties around the world. Detecting it earlier and more effectively can significantly reduce the lethal aftereffects and increase road safety. As physiological conditions originate from the human brain, so neurophysiological signatures in drowsy and alert states may be investigated for this purpose. In this preface, A passive brain-computer interface (pBCI) scheme using multichannel electroencephalography (EEG) brain signals is developed for spatially localized and accurate detection of human drowsiness during driving tasks.

Methods: This pBCI modality acquired electrophysiological patterns of 12 healthy subjects from the prefrontal (PFC), frontal (FC), and occipital cortices (OC) of the brain. Neurological states are recorded using six EEG channels spread over the right and left hemispheres in the PFC, FC, and OC of the sleep-deprived subjects during simulated driving tasks. In post-hoc analysis, spectral signatures of the δ, θ, α, and β rhythms are extracted in terms of spectral band powers and their ratios with a temporal correlation over the complete span of the experiment. Minimum redundancy maximum relevance, Chi-square, and ReliefF feature selection methods are used and aggregated with a Z-score based approach for global feature ranking. The extracted drowsiness attributes are classified using decision trees, discriminant analysis, logistic regression, naïve Bayes, support vector machines, k-nearest neighbors, and ensemble classifiers. The binary classification results are reported with confusion matrix-based performance assessment metrics.

Results: In inter-classifier comparison, the optimized ensemble model achieved the best results of drowsiness classification with 85.6% accuracy and precision, 89.7% recall, 87.6% F1-score, 80% specificity, 70.3% Matthews correlation coefficient, 70.2% Cohen’s kappa score, and 91% area under the receiver operating characteristic curve with 76-ms execution time. In inter-channel comparison, the best results were obtained at the F8 electrode position in the right FC of the brain. The significance of all the results was validated with a p-value of less than 0.05 using statistical hypothesis testing methods.

Conclusions: The proposed scheme has achieved better results for driving drowsiness detection with the accomplishment of multiple objectives. The predictor importance approach has reduced the feature extraction cost and computational complexity is minimized with the use of conventional machine learning classifiers resulting in low-cost hardware and software requirements. The channel selection approach has spatially localized the most promising brain region for drowsiness detection with only a single EEG channel (F8) which reduces the physical intrusiveness in normal driving operation. This pBCI scheme has a good potential for practical applications requiring earlier, more accurate, and less disruptive drowsiness detection using the spectral information of EEG biosignals.

Input Shape Effect on Classification Performance of Raw EEG Motor Imagery Signals with Convolutional Neural Networks for Use in Brain-Computer Interfaces

EEG signals are interpreted, analyzed and classified by many researchers for use in brain-computer interfaces. Although there are many different EEG signal acquisition methods, one of the most interesting is motor imagery signals. Many different signal processing methods, machine learning and deep learning models have been developed for the classification of motor imagery signals. Among these, Convolutional Neural Network models generally achieve better results than other models. Because the size and shape of the data is important for training Convolutional Neural Network models and discovering the right relationships, researchers have designed and experimented with many different input shape structures. However, no study has been found in the literature evaluating the effect of different input shapes on model performance and accuracy. In this study, the effects of different input shapes on model performance and accuracy in the classification of EEG motor imagery signals were investigated, which had not been specifically studied before. In addition, signal preprocessing methods, which take a long time before classification, were not used; rather, two CNN models were developed for training and classification using raw data. Two different datasets, BCI Competition IV 2A and 2B, were used in classification processes. For different input shapes, 53.03-89.29% classification accuracy and 2-23 s epoch time were obtained for 2A dataset, 64.84-84.94% classification accuracy and 4-10 s epoch time were obtained for 2B dataset. This study showed that the input shape has a significant effect on the classification performance, and when the correct input shape is selected and the correct CNN architecture is developed, feature extraction and classification can be done well by the CNN architecture without any signal preprocessing.

Applying correlation analysis to electrode optimization in source domain

In brain computer interface-based neurorehabilitation system, a large number of electrodes may increase the difficulty of signal acquisition and the time consumption of decoding algorithm for motor imagery EEG (MI-EEG). The traditional electrode optimization methods were limited by the low spatial resolution of scalp EEG. EEG source imaging (ESI) was further applied to reduce the number of electrodes, in which either the electrodes covering activated cortical areas were selected, or the reconstructed electrodes of EEGs with higher Fisher scores were retained. However, the activated dipoles do not all contribute equally to decoding, and the Fisher score cannot represent the correlations between electrodes and dipoles. In this paper, based on ESI and correlation analysis, a novel electrode optimization method, denoted ECCEO, was developed. The scalp MI-EEG was mapped to cortical regions by ESI, and the dipoles with larger amplitudes were chosen to designate a region of interest (ROI). Then, Pearson correlation coefficients between each dipole of the ROI and the corresponding electrode were calculated, averaged, and ranked to obtain two average correlation coefficient sequences. A small but important group of electrodes for each class were alternately added to the predetermined basic electrode set to form a candidate electrode set. Their features were extracted and evaluated to determine the optimal electrode set. Experiments were conducted on two public datasets, the average decoding accuracies achieved 95.99% and 88.30%, and the reduction of computational cost were 65% and 56%, respectively; statistical significance was examined as well.

Trends in EEG signal feature extraction applications

This paper will focus on electroencephalogram (EEG) signal analysis with an emphasis on common feature extraction techniques mentioned in the research literature, as well as a variety of applications that this can be applied to. In this review, we cover single and multi-dimensional EEG signal processing and feature extraction techniques in the time domain, frequency domain, decomposition domain, time-frequency domain, and spatial domain. We also provide pseudocode for the methods discussed so that they can be replicated by practitioners and researchers in their specific areas of biomedical work. Furthermore, we discuss artificial intelligence applications such as assistive technology, neurological disease classification, brain-computer interface systems, as well as their machine learning integration counterparts, to complete the overall pipeline design for EEG signal analysis. Finally, we discuss future work that can be innovated in the feature extraction domain for EEG signal analysis.

An Efficient Machine Learning-Based Emotional Valence Recognition Approach Towards Wearable EEG

Emotion artificial intelligence (AI) is being increasingly adopted in several industries such as healthcare and education. Facial expressions and tone of speech have been previously considered for emotion recognition, yet they have the drawback of being easily manipulated by subjects to mask their true emotions. Electroencephalography (EEG) has emerged as a reliable and cost-effective method to detect true human emotions. Recently, huge research effort has been put to develop efficient wearable EEG devices to be used by consumers in out of the lab scenarios. In this work, a subject-dependent emotional valence recognition method is implemented that is intended for utilization in emotion AI applications. Time and frequency features were computed from a single time series derived from the Fp1 and Fp2 channels. Several analyses were performed on the strongest valence emotions to determine the most relevant features, frequency bands, and EEG timeslots using the benchmark DEAP dataset. Binary classification experiments resulted in an accuracy of 97.42% using the alpha band, by that outperforming several approaches from literature by ~3-22%. Multiclass classification gave an accuracy of 95.0%. Feature computation and classification required less than 0.1 s. The proposed method thus has the advantage of reduced computational complexity as, unlike most methods in the literature, only two EEG channels were considered. In addition, minimal features concluded from the thorough analyses conducted in this study were used to achieve state-of-the-art performance. The implemented EEG emotion recognition method thus has the merits of being reliable and easily reproducible, making it well-suited for wearable EEG devices.

An AI-Inspired Spatio-Temporal Neural Network for EEG-Based Emotional Status

The accurate identification of the human emotional status is crucial for an efficient human-robot interaction (HRI). As such, we have witnessed extensive research efforts made in developing robust and accurate brain-computer interfacing models based on diverse biosignals. In particular, previous research has shown that an Electroencephalogram (EEG) can provide deep insight into the state of emotion. Recently, various handcrafted and deep neural network (DNN) models were proposed by researchers for extracting emotion-relevant features, which offer limited robustness to noise that leads to reduced precision and increased computational complexity. The DNN models developed to date were shown to be efficient in extracting robust features relevant to emotion classification; however, their massive feature dimensionality problem leads to a high computational load. In this paper, we propose a bag-of-hybrid-deep-features (BoHDF) extraction model for classifying EEG signals into their respective emotion class. The invariance and robustness of the BoHDF is further enhanced by transforming EEG signals into 2D spectrograms before the feature extraction stage. Such a time-frequency representation fits well with the time-varying behavior of EEG patterns. Here, we propose to combine the deep features from the GoogLeNet fully connected layer (one of the simplest DNN models) together with the OMTLBP_SMC texture-based features, which we recently developed, followed by a K-nearest neighbor (KNN) clustering algorithm. The proposed model, when evaluated on the DEAP and SEED databases, achieves a 93.83 and 96.95% recognition accuracy, respectively. The experimental results using the proposed BoHDF-based algorithm show an improved performance in comparison to previously reported works with similar setups.

Exploiting the Cone of Influence for Improving the Performance of Wavelet Transform-Based Models for ERP/EEG Classification

Features extracted from the wavelet transform coefficient matrix are widely used in the design of machine learning models to classify event-related potential (ERP) and electroencephalography (EEG) signals in a wide range of brain activity research and clinical studies. This novel study is aimed at dramatically improving the performance of such wavelet-based classifiers by exploiting information offered by the cone of influence (COI) of the continuous wavelet transform (CWT). The COI is a boundary that is superimposed on the wavelet scalogram to delineate the coefficients that are accurate from those that are inaccurate due to edge effects. The features derived from the inaccurate coefficients are, therefore, unreliable. In this study, it is hypothesized that the classifier performance would improve if unreliable features, which are outside the COI, are zeroed out, and the performance would improve even further if those features are cropped out completely. The entire, zeroed out, and cropped scalograms are referred to as the "same" (S)-scalogram, "zeroed out" (Z)-scalogram, and the "valid" (V)-scalogram, respectively. The strategy to validate the hypotheses is to formulate three classification approaches in which the feature vectors are extracted from the (a) S-scalogram in the standard manner, (b) Z-scalogram, and (c) V-scalogram. A subsampling strategy is developed to generate small-sample ERP ensembles to enable customized classifier design for single subjects, and a strategy is developed to select a subset of channels from multiple ERP channels. The three scalogram approaches are implemented using support vector machines, random forests, k-nearest neighbor, multilayer perceptron neural networks, and deep learning convolution neural networks. In order to validate the performance hypotheses, experiments are designed to classify the multi-channel ERPs of five subjects engaged in distinguishing between synonymous and non-synonymous word pairs. The results confirm that the classifiers using the Z-scalogram features outperform those using the S-scalogram features, and the classifiers using the V-scalogram features outperform those using the Z-scalogram features. Most importantly, the relative improvement of the V-scalogram classifiers over the standard S-scalogram classifiers is dramatic. Additionally, enabling the design of customized classifiers for individual subjects is an important contribution to ERP/EEG-based studies and diagnoses of patient-specific disorders.

An Efficient AP-ANN-Based Multimethod Fusion Model to Detect Stress through EEG Signal Analysis

Stress is a universal emotion that every human experiences daily. Psychologists say stress may lead to heart attack, depression, hypertension, strokes, or even sudden death. Many technical explorations like stress detection through facial expression, speech, text, physical behaviors, etc., were explored, but no consensus has been reached on the best method. The advancement in biomedical engineering yielded a rapid development of electroencephalogram (EEG) signal analysis that has inspired the idea of a multimethod fusion approach for the first time which employs multiple techniques such as discrete wavelet transform (DWT) for de-noising, adaptive synthetic sampling (ADASYN) for class balancing, and affinity propagation (AP) as a stratified sampling model along with the artificial neural network (ANN) as the classifier model for human emotion classification. From the EEG recordings of the DEAP dataset, the artifacts are removed, the signal is decomposed using a DWT, and features are extracted and fused to form the feature vector. As the dataset is high-dimensional, feature selection is done and ADASYN is used to address the imbalance of classes resulting in large-scale data. The innovative idea of the proposed system is to perform sampling using affinity propagation as a stratified sampling-based clustering algorithm as it determines the number of representative samples automatically which makes it superior to the K-Means, K-Medoid, that requires the K-value. Those samples are used as inputs to various classification models, the comparison of the AP-ANN, AP-SVM, and AP-RF is done, and their most important five performance metrics such as accuracy, precision, recall, F1-score, and specificity were compared. From our experiment, the AP-ANN model provides better accuracy of 86.8% and greater precision of 85.7%, a higher F1 score of 84.9%, a recall rate of 84.1%, and a specificity value of 89.2% which altogether provides better results than the other existing algorithms.