Search Results (17)

Background: Epilepsy is a chronic neurological disorder that affects individuals across all age groups. Early detection and intervention are crucial for minimizing both physical and psychological distress. However, the unpredictable nature of seizures presents considerable challenges for timely detection and accurate diagnosis. Method: To address the challenge of low recognition accuracy in small-sample, single-channel epileptic electroencephalogram (EEG) signals, this study proposes an automated seizure detection method using a micro-capsule network. First, we propose a dimensionality-increasing transformation technique for single-channel EEG signals to meet the network’s input requirements. Second, a streamlined micro-capsule network is designed by optimizing and simplifying the framework’s architecture. Finally, EEG features are encoded as feature vectors to better represent spatial hierarchical relationships between seizure patterns, enhancing the framework’s adaptability and improving detection accuracy. Result: Compared to existing EEG-based detection methods, our approach achieves higher accuracy on small-sample datasets while maintaining a reduction in computational complexity. Conclusions: By leveraging its micro-capsule network architecture, the framework demonstrates superior classification accuracy when analyzing single-channel epileptiform EEG signals, significantly outperforming both convolutional neural network-based implementations and established machine learning methodologies. Full article

Electroencephalogram (EEG) analysis is essential for diagnosing neurological disorders but typically requires expert interpretation and significant time. Purpose: This study aims to automate the classification of normal and abnormal EEG recordings to support clinical diagnosis and reduce manual workload. Automating the initial screening of EEGs can help clinicians quickly identify potential neurological abnormalities, enabling timely intervention and guiding further diagnostic and treatment strategies. Methodology: We utilized the Temple University Hospital EEG dataset to develop a DenseNet-based deep learning model. To enable a fair comparison of different EEG representations, we used three input types: signal images, spectrograms, and scalograms. To reduce dimensionality and simplify computation, we focused on two channels: T5 and O1. For interpretability, we applied Local Interpretable Model-agnostic Explanations (LIME) and Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize the EEG regions influencing the model’s predictions. Key Findings: Among the input types, spectrogram-based representations achieved the highest classification accuracy, indicating that time-frequency features are especially effective for this task. The model demonstrated strong performance overall, and the integration of LIME and Grad-CAM provided transparent explanations of its decisions, enhancing interpretability. This approach offers a practical and interpretable solution for automated EEG screening, contributing to more efficient clinical workflows and better understanding of complex neurological conditions. Full article

Background/Objectives: Electroencephalogram (EEG) signals, which reflect brain activity, are widely used in emotion recognition. However, the variety of EEG features presents significant challenges in identifying key features, reducing redundancy, and simplifying the computational process. Methods: To address these challenges, this paper proposes a multi-dimensional attention-based dynamic graph convolutional neural network (AttGraph) model. The model delves into the impact of different EEG features on emotion recognition by evaluating their sensitivity to emotional changes, providing richer and more accurate feature information. Results: Through the dynamic weighting of EEG features via a multi-dimensional attention convolution layer, the AttGraph method is able to precisely detect emotional changes and automatically choose the most discriminative features for emotion recognition tasks. This approach significantly improves the model’s recognition accuracy and robustness. Finally, subject-independent and subject-dependent experiments were conducted on two public datasets. Conclusions: Through comparisons and analyses with existing methods, the proposed AttGraph method demonstrated outstanding performances in emotion recognition tasks, with stronger generalization ability and adaptability. Full article

The objective of this study is to integrate and classify electroencephalogram (EEG), electrocardiogram (ECG), and galvanic skin response (GSR) signals from a participant exposed to emotional stimuli—happiness, anger, fear, and sadness. We used the LazyPredict library to identify the most effective classification model, leveraging its simplified implementation and wide range of models and performance metrics. The signals were processed in Python following a detailed workflow: (1) normalization, (2) band-pass filtering, (3) epoch extraction and selection, and (4) relative energy extraction using Discrete Wavelet Transform (DWT). After preprocessing, the data were input into LazyPredict, where the Extra Trees model consistently demonstrated the best performance for binary emotion classification. Our experience with LazyPredict proved to be practical and efficient, facilitating the exploration of high-performing models for emotion classification. Full article

Background: In experimental and clinical studies of pharmacological treatments for Alzheimer’s disease (AD), the electroencephalogram (EEG) frequency spectrum approach has demonstrated its efficacy in determining the characteristics of pathological changes in the functioning of different cerebral structures, interconnections between them, and disturbances in the brain neurotransmitter systems. The main results have been obtained in frames of traditionally used so-called “classical” EEG frequency bands: delta, theta, alpha, and beta. Objective: This unified approach simplifies comparing data from different studies but loses the dynamic peculiarities of the effects because of their time-dependent transition through the borders of the “classical” bands. Methods: In this study on non-narcotized freely moving 5xFAD transgenic mice, a model of AD, chronically pretreated with a non-selective dopamine (DA) receptor agonist, apomorphine (APO), we analyze the transitory EEG effects of acute APO injection in different brain areas by use of our “time–frequency” clustering program. The acute injection of APO was used to compare DA receptor sensitivity in 5xFAD mice pretreated with either APO or saline vs. wild-type (WT) mice pretreated with saline. Results: After acute APO injection, the clusters of enhanced EEG activity centered in the theta–alpha frequency range observed in WT mice disappeared in 5xFAD mice pretreated with saline and practically recovered in 5xFAD mice pretreated with APO. Conclusions: In 5xFAD mice pretreated with saline, the sensitivity of DA receptors was disturbed; chronic APO pretreatment mainly recovered this characteristic in 5xFAD mice. The “clustering” of pharmacological EEG effects and their time-dependent transition between classical frequency bands is a new effective approach for analyzing cerebral neurotransmission in neurodegenerative pathologies. Full article

Machine learning (ML) methods are increasingly being applied to analyze biological signals. For example, ML methods have been successfully applied to the human electroencephalogram (EEG) to classify neural signals as pathological or non-pathological and to predict working memory performance in healthy and psychiatric patients. ML approaches can quickly process large volumes of data to reveal patterns that may be missed by humans. This study investigated the accuracy of ML methods at classifying the brain’s electrical activity to cognitive events, i.e., event-related brain potentials (ERPs). ERPs are extracted from the ongoing EEG and represent electrical potentials in response to specific events. ERPs were evoked during a visual Go/NoGo task. The Go/NoGo task requires a button press on Go trials and response withholding on NoGo trials. NoGo trials elicit neural activity associated with inhibitory control processes. We compared the accuracy of six ML algorithms at classifying the ERPs associated with each trial type. The raw electrical signals were fed to all ML algorithms to build predictive models. The same raw data were then truncated in length and fitted to multiple dynamic state space models of order $n_x$ using a continuous-time subspace-based system identification algorithm. The $4n_x$ numerator and denominator parameters of the transfer function of the state space model were then used as substitutes for the data. Dimensionality reduction simplifies classification, reduces noise, and may ultimately improve the predictive power of ML models. Our findings revealed that all ML methods correctly classified the electrical signal associated with each trial type with a high degree of accuracy, and accuracy remained high after parameterization was applied. We discuss the models and the usefulness of the parameterization. Full article

Central nervous system (CNS) disorders are among the most frequent presentations in critically ill children. Status epilepticus (SE) is a frequent scenario in the resuscitation bay. In patients with altered mental status, non-convulsive SE (NCSE) is often underrecognized and critically impacts the neurological outcome and duration of hospitalization. An electroencephalogram (EEG) is required to diagnose NCSE. However, standard EEG recordings are time- and staff-intensive, and their availability is limited, especially outside regular working hours. We aimed to improve patient care by developing a simplified EEG recording method, using a reduced lead montage (point-of-care EEG—pocEEG), that is suitable for use in pediatric emergency departments. The objective was to devise a cost-effective unit with low space requirements that fitted the existing technical infrastructure. We present two technical options for clinical pocEEG acquisition using patient monitors (GE Carescape, Philips IntelliVue) that enable data collection for educational and research purposes. A simplified, rapid response EEG like the pocEEG enables neuromonitoring of patients with CNS disorders in pediatric emergency settings, facilitating timely diagnosis and treatment initiation when standard EEG is not readily available. Full article

Because of its ability to objectively reflect people’s emotional states, electroencephalogram (EEG) has been attracting increasing research attention for emotion classification. The classification method based on spatial-domain analysis is one of the research hotspots. However, most previous studies ignored the complementarity of information between different frequency bands, and the information in a single frequency band is not fully mined, which increases the computational time and the difficulty of improving classification accuracy. To address the above problems, this study proposes an emotion classification method based on dynamic simplifying graph convolutional (SGC) networks and a style recalibration module (SRM) for channels, termed SGC-SRM, with multi-band EEG data as input. Specifically, first, the graph structure is constructed using the differential entropy characteristics of each sub-band and the internal relationship between different channels is dynamically learned through SGC networks. Second, a convolution layer based on the SRM is introduced to recalibrate channel features to extract more emotion-related features. Third, the extracted sub-band features are fused at the feature level and classified. In addition, to reduce the redundant information between EEG channels and the computational time, (1) we adopt only 12 channels that are suitable for emotion classification to optimize the recognition algorithm, which can save approximately 90.5% of the time cost compared with using all channels; (2) we adopt information in the θ, α, β, and γ bands, consequently saving 23.3% of the time consumed compared with that in the full bands while maintaining almost the same level of classification accuracy. Finally, a subject-independent experiment is conducted on the public SEED dataset using the leave-one-subject-out cross-validation strategy. According to experimental results, SGC-SRM improves classification accuracy by 5.51–15.43% compared with existing methods. Full article

Epilepsy is a severe neurological disorder that is usually diagnosed by using an electroencephalogram (EEG). However, EEG signals are complex, nonlinear, and dynamic, thus generating large amounts of data polluted by many artefacts, lowering the signal-to-noise ratio, and hampering expert interpretation. The traditional seizure-detection method of professional review of long-term EEG signals is an expensive, time-consuming, and challenging task. To reduce the complexity and cost of the task, researchers have developed several seizure-detection approaches, primarily focusing on classification systems and spectral feature extraction. While these methods can achieve high/optimal performances, the system may require retraining and following up with the feature extraction for each new patient, thus making it impractical for real-world applications. Herein, we present a straightforward manual/automated detection system based on the simple seizure feature amplification analysis to minimize these practical difficulties. Our algorithm (a simplified version is available as additional material), borrowing from the telecommunication discipline, treats the seizure as the carrier of information and tunes filters to this specific bandwidth, yielding a viable, computationally inexpensive solution. Manual tests gave 93% sensitivity and 96% specificity at a false detection rate of 0.04/h. Automated analyses showed 88% and 97% sensitivity and specificity, respectively. Moreover, our proposed method can accurately detect seizure locations within the brain. In summary, the proposed method has excellent potential, does not require training on new patient data, and can aid in the localization of seizure focus/origin. Full article

In this work, we propose a solution to the problem of identification of sources in the brain from measurements of the electrical potential, recorded on the scalp EEG (electroencephalogram), where boundary problems are used to model the skull, brain region, and scalp, solving the inverse problem from the EEG measurements, the so-called Electroencephalographic Inverse Problem (EIP), which is ill-posed in the Hadamard sense since the problem has numerical instability. We focus on the identification of volumetric dipolar sources of the EEG by constructing and modeling a simplification to reduce the multilayer conductive medium (two layers or regions ${\Omega }_1$ and ${\Omega }_2$) to a problem of a single layer of a homogeneous medium with a null Neumann condition on the boundary. For this simplification purpose, we consider the Cauchy problem to be solved at each time. We compare the results we obtained solving the multiple layers problem with those obtained by our simplification proposal. In both cases, we solve the direct and inverse problems for two different sources, as synthetic results for dipolar sources resembling epileptic foci, and a similar case with an external stimulus (intense light, skin stimuli, sleep problems, etc). For the inverse problem, we use the Tikhonov regularization method to handle its numerical instability. Additionally, we build an algorithm to solve both models (multiple layers problem and our simplification) in time, showing optimization of the problem when considering 128 divisions in the time interval $[0,1]$ s, solving the inverse problem at each time (interval division) and comparing the recovered source with the initial one in the algorithm. We observed a significant decrease in the computation times when simplifying the numerical calculations, resulting in a decrease up to $50\%$ in the execution times, between the EIP multilayer model and our simplification proposal, to a single layer homogeneous problem of a homogeneous medium, which translates into a numerical efficiency in this type of problem. Full article

Background. Motor imagery engages much of the same neural circuits as an overt movement. Therefore, the mental rehearsal of movements is often used to supplement physical training and might aid motor neurorehabilitation after stroke. One attempt to capture the brain’s involvement in imagery involves the use, as a marker, of the depression or event-related desynchronization (ERD) of thalamocortical sensorimotor rhythms found in a human electroencephalogram (EEG). Using fast real-time processing, it is possible to make the subject aware of their own brain reactions or—even better—to turn them into actions through a technology called the brain–computer interface (BCI). However, it remains unclear whether BCI-enabled imagery facilitates a stronger or qualitatively different brain response compared to the open-loop training. Methods. Seven healthy volunteers who were experienced in both closed and open-loop motor imagery took part in six experimental sessions over a period of 4.5 months, in which they performed kinesthetic imagery of a previously known set of finger and arm movements with simultaneous 30-channel EEG acquisition. The first and the last session mostly consisted of feedback trials in which the subjects were presented with the classification results of the EEG patterns in real time; during the other sessions, no feedback was provided. Spatiotemporal and amplitude features of the ERD patterns concomitant with imagery were compared across experimental days and between feedback conditions using linear mixed-effects modeling. Results. The main spatial sources of ERD appeared to be highly stable across the six experimental days, remaining nearly identical in five of seven subjects (Pearson’s ρ > 0.94). Only in one subject did the spatial pattern of activation statistically significantly differ (p = 0.009) between the feedback and no-feedback conditions. Real-time visual feedback delivered through the BCI did not significantly increase the ERD strength. Conclusion. The results imply that the potential benefits of MI could be yielded by well-habituated subjects with a simplified open-loop setup, e.g., through at-home self-practice. Full article

In addition to helping develop products that aid the disabled, brain–computer interface (BCI) technology can also become a modality of entertainment for all people. However, most BCI games cannot be widely promoted due to the poor control performance or because they easily cause fatigue. In this paper, we propose a P300 brain–computer-interface game (MindGomoku) to explore a feasible and natural way to play games by using electroencephalogram (EEG) signals in a practical environment. The novelty of this research is reflected in integrating the characteristics of game rules and the BCI system when designing BCI games and paradigms. Moreover, a simplified Bayesian convolutional neural network (SBCNN) algorithm is introduced to achieve high accuracy on limited training samples. To prove the reliability of the proposed algorithm and system control, 10 subjects were selected to participate in two online control experiments. The experimental results showed that all subjects successfully completed the game control with an average accuracy of 90.7% and played the MindGomoku an average of more than 11 min. These findings fully demonstrate the stability and effectiveness of the proposed system. This BCI system not only provides a form of entertainment for users, particularly the disabled, but also provides more possibilities for games. Full article

The design of efficient electroencephalogram (EEG) classification systems for the detection of mental states is still an open problem. Such systems can be used to provide assistance to humans in tasks where a certain level of alertness is required, like in surgery or in the operation of heavy machines, among others. In this work, we extend a previous study where a classification system is proposed using a Common Spatial Pattern (CSP) and Linear Discriminant Analysis (LDA) for the classification of two mental states, namely a relaxed and a normal state. Here, we propose an enhanced feature extraction algorithm (Augmented Feature Extraction with Genetic Programming, or ${}^{+}$FEGP) that improves upon previous results by employing a Genetic-Programming-based methodology on top of the CSP. The proposed algorithm searches for non-linear transformations that build new features and simplify the classification task. Although the proposed algorithm can be coupled with any classifier, LDA achieves 78.8% accuracy, the best predictive accuracy among tested classifiers, significantly improving upon previously published results on the same real-world dataset. Full article

The purpose of this paper is to record and analyze induced gamma-band activity (GBA) (30–60 Hz) in cerebral motor areas during imaginary movement and to compare it quantitatively with activity recorded in the same areas during actual movement using a simplified electroencephalogram (EEG). Brain activity (basal activity, imaginary motor task and actual motor task) is obtained from 12 healthy volunteer subjects using an EEG (Cz channel). GBA is analyzed using the mean power spectral density (PSD) value. Event-related synchronization (ERS) is calculated from the PSD values of the basal GBA (GBAb), the GBA of the imaginary movement (GBAim) and the GBA of the actual movement (GBAac). The mean GBAim and GBAac values for the right and left hands are significantly higher than the GBAb value (p = 0.007). No significant difference is detected between mean GBA values during the imaginary and actual movement (p = 0.242). The mean ERS values for the imaginary movement (ERSimM (%) = 23.52) and for the actual movement (ERSacM = 27.47) do not present any significant difference (p = 0.117). We demonstrated that ERS could provide a useful way of indirectly checking the function of neuronal motor circuits activated by voluntary movement, both imaginary and actual. These results, as a proof of concept, could be applied to physiology studies, brain–computer interfaces, and diagnosis of cognitive or motor pathologies. Full article

Left and right hand motor imagery electroencephalogram (MI-EEG) signals are widely used in brain-computer interface (BCI) systems to identify a participant intent in controlling external devices. However, due to a series of reasons, including low signal-to-noise ratios, there are great challenges for efficient motor imagery classification. The recognition of left and right hand MI-EEG signals is vital for the application of BCI systems. Recently, the method of deep learning has been successfully applied in pattern recognition and other fields. However, there are few effective deep learning algorithms applied to BCI systems, particularly for MI based BCI. In this paper, we propose an algorithm that combines continuous wavelet transform (CWT) and a simplified convolutional neural network (SCNN) to improve the recognition rate of MI-EEG signals. Using the CWT, the MI-EEG signals are mapped to time-frequency image signals. Then the image signals are input into the SCNN to extract the features and classify them. Tested by the BCI Competition IV Dataset 2b, the experimental results show that the average classification accuracy of the nine subjects is 83.2%, and the mean kappa value is 0.651, which is 11.9% higher than that of the champion in the BCI Competition IV. Compared with other algorithms, the proposed CWT-SCNN algorithm has a better classification performance and a shorter training time. Therefore, this algorithm could enhance the classification performance of MI based BCI and be applied in real-time BCI systems for use by disabled people. Full article