Search Results (1,558)

Transformer models have revolutionized fields like Natural Language Processing (NLP) by enabling machines to accurately understand and generate human language. However, these models’ inherent complexity and limited interpretability pose barriers to their broader adoption. To address these challenges, we propose a simplified query-only attention mechanism specifically for encoder-based transformer models to reduce complexity and improve interpretability. Unlike conventional attention mechanisms, which rely on query (Q), key (K), and value (V) vectors, our method uses only the Q vector for attention calculation. This approach reduces computational complexity while maintaining the model’s ability to capture essential relationships, enhancing interpretability. We evaluated the proposed query-only attention on an EEG conformer model, a state-of-the-art architecture for EEG signal classification. We demonstrated that it performs comparably to the original QKV attention mechanism, while simplifying the model’s architecture. Our findings suggest that query-only attention offers a promising direction for the development of more efficient and interpretable transformer-based models, with potential applications across various domains beyond NLP. Full article

Brain–computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial for real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically classification accuracy and the false positive rate, to optimize the temporal parameters of MI-BCI systems. We investigated the impact of time window duration on classification accuracy and false positive rate, employing Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) on data acquired from six post-stroke patients and on the external BCI IVa dataset. EEG signals were recorded and processed using the Common Spatial Patterns (CSP) algorithm for feature extraction. Our results indicate that longer time windows generally enhance classification accuracy and reduce false positives across all classifiers, with LDA performing the best. However, to maintain the real-time responsiveness, crucial for practical applications, a balance must be struck. The results suggest an optimal time window of 1–2 s, offering a trade-off between classification performance and excessive delay to guarantee the system responsiveness. These findings underscore the importance of temporal optimization in MI-BCI systems to improve usability in real rehabilitation scenarios. Full article

Electroencephalography (EEG) is useful for studying brain activity in major depressive disorder (MDD), particularly focusing on theta and alpha frequency bands via power spectral density (PSD). However, PSD-based analysis has often produced inconsistent results due to difficulties in distinguishing between periodic and aperiodic components of EEG signals. We analyzed EEG data from 114 young adults, including 74 healthy controls (HCs) and 40 MDD patients, assessing periodic and aperiodic components alongside conventional PSD at both source and electrode levels. Machine learning algorithms classified MDD versus HC based on these features. Sensor-level analysis showed stronger Hedge’s g effect sizes for parietal theta and frontal alpha activity than source-level analysis. MDD individuals exhibited reduced theta and alpha activity relative to HC. Logistic regression-based classifications showed that periodic components slightly outperformed PSD, with the best results achieved by combining periodic and aperiodic features (AUC = 0.82). Strong negative correlations were found between reduced periodic parietal theta and frontal alpha activities and higher scores on the Beck Depression Inventory, particularly for the anhedonia subscale. This study emphasizes the superiority of sensor-level over source-level analysis for detecting MDD-related changes and highlights the value of incorporating both periodic and aperiodic components for a more refined understanding of depressive disorders. Full article

Hyperventilation (HV) is an activation technique performed during clinical practices to trigger epileptiform activities, supporting the neurophysiological evaluation of patients with epilepsy. Although the role of HV has often been questioned, especially in the case of focal epilepsy, no studies have ever assessed how cortical structures respond to such a maneuver via intracranial EEG recordings. This work aims to fill this gap by evaluating the HV effects on the Stereo-EEG (SEEG) signals from a cohort of 10 patients with drug-resistant focal epilepsy. We extracted multiple quantitative metrics from the SEEG signals and compared the results obtained during HV, awake status, non-REM sleep, and seizure onset. Our findings show that the cortical connectivity, estimated via the phase transfer entropy (PTE) algorithm, strongly increases during the HV maneuver, similar to non-REM sleep. The opposite effect is observed during seizure onset, as ictal transitions involve the desynchronization of the brain structures within the epileptogenic zone. We conclude that HV promotes a conductive environment that may facilitate the propagation of epileptiform activities but is not sufficient to trigger seizures in focal epilepsy. Full article

Monitoring the driver’s physical and mental state based on wearable EEG acquisition equipment, especially the detection and early warning of fatigue, is a key issue in the research of the brain–computer interface in human–machine intelligent fusion driving. Comparing and analyzing the waking (alert) state and fatigue state by simulating EEG data during simulated driving, this paper proposes a brain functional network construction method based on a phase locking value (PLV) and phase lag index (PLI), studies the relationship between brain regions, and quantitatively analyzes the network structure. The characteristic parameters of the brain functional network that have significant differences in fatigue status are screened out and constitute feature vectors, which are then combined with machine learning algorithms to complete classification and identification. The experimental results show that this method can effectively distinguish between alertness and fatigue states. The recognition accuracy rates of 52 subjects are all above 70%, with the highest recognition accuracy reaching 89.5%. Brain network topology analysis showed that the connectivity between brain regions was weakened under a fatigue state, especially under the PLV method, and the phase synchronization relationship between delta and theta frequency bands was significantly weakened. The research results provide a reference for understanding the interdependence of brain regions under fatigue conditions and the development of fatigue driving detection systems. Full article

Background: Traditional physical rehabilitation involves participants performing repetitive body movements with the assistance of physiotherapists. Owing to the exercises’ monotonous nature and lack of reward, participants may become disinterested and cease their recovery. Games could be used as tools to engage participants in the rehabilitation process. Consequently, participants could perform rehabilitation exercises while playing the game, receiving rewards from the experience. Maintaining the players’ engagement requires regularly adjusting the game difficulty. The players’ engagement can be measured using questionnaires and biosignals (e.g., electroencephalography signals—EEG). This study aims to determine whether there is a significant difference in players’ engagement between two game modes with different game difficulty adjustments: non-tailored and tailored modes. Methods: We implemented two game modes which were controlled using hand movements. The features of the game rewards (position and size) were changed in the game scene; hence, the game difficulty could be modified. The non-tailored mode set the features of rewards in the game scene randomly. Conversely, the tailored mode set the features of rewards in the game scene based on the participants’ range of motion using fuzzy logic. Consequently, the game difficulty was adjusted dynamically. Additionally, engagement was computed from 53 healthy participants in both game modes using two EEG sensors: Bitalino Revolution and Unicorn. Specifically, the theta (θ) and alpha (α) bands from the frontal and parietal lobes were computed from the EEG data. A questionnaire was applied to participants after finishing playing both game modes to collect their impressions on the following: their favorite game mode, the game mode that was the easiest to play, the game mode that was the least frustrating to play, the game mode that was the least boring to play, the game mode that was the most entertaining to play, and the game mode that had the fastest game response time. Results: The non-tailored game mode reported the following means of engagement: 6.297 ± 11.274 using the Unicorn sensor, and 3.616 ± 0.771 using the Bitalino sensor. The tailored game mode reported the following means of engagement: 4.408 ± 6.243 using the Unicorn sensor, and 3.619 ± 0.551 using Bitalino. The non-tailored mode reported the highest mean engagement (6.297) when the Unicorn sensor was used to collect EEG signals. Most participants selected the non-tailored game mode as their favorite, and the most entertaining mode, irrespective of the EEG sensor. Conversely, most participants chose the tailored game mode as the easiest, and the least frustrating mode to play, irrespective of the EEG sensor. Conclusions: A Wilcoxon-Signed-Rank test revealed that there was only a significant difference in engagement between game modes when the EEG signal was collected via the Unicorn sensor (p value = 0.04054). Fisher’s exact tests showed significant associations between the game modes (non-tailored, tailored) and the following players’ variables: ease of play using the Unicorn sensor (p value = 0.009341), and frustration using Unicorn sensor (p value = 0.0466). Full article

Introduction: Accurately detecting arousal events during sleep is essential for evaluating sleep quality and diagnosing sleep disorders, such as sleep apnea/hypopnea syndrome. While the American Academy of Sleep Medicine guidelines associate arousal events with electroencephalogram (EEG) signal variations, EEGs are often not recorded during home sleep testing (HST) using wearable devices or smartphone applications. Objectives: The primary objective of this study was to explore the potential of alternatively relying on combinations of easily measurable physiological signals during HST for arousal detection where EEGs are not recorded. Methods: We conducted a data-driven retrospective study following an incremental device-agnostic analysis approach, where we simulated a limited-channel setting using polysomnography data and used deep learning to automate the detection task. During the analysis, we tested multiple signal combinations to evaluate their potential effectiveness. We trained and evaluated the model on the Multi-Ethnic Study of Atherosclerosis dataset. Results: The results demonstrated that combining multiple signals significantly improved performance compared with single-input signal models. Notably, combining thoracic effort, heart rate, and a wake/sleep indicator signal achieved competitive performance compared with the state-of-the-art DeepCAD model using electrocardiogram as input with an average precision of 61.59% and an average recall of 56.46% across the test records. Conclusions: This study demonstrated the potential of combining easy-to-record HST signals to characterize the autonomic markers of arousal better. It provides valuable insights to HST device designers on signals that improve EEG-free arousal detection. Full article

This study introduces a novel methodology for classifying cognitive states using convolutional neural networks (CNNs) on electroencephalography (EEG) data of 41 students, aimed at streamlining the traditionally labor-intensive analysis procedures utilized in EEGLAB. Concentrating on the 30–40 Hz frequency range within the gamma band, we developed a CNN model to analyze EEG signals recorded from the inferior parietal lobule during various cognitive tasks. The model demonstrated substantial efficacy, achieving an accuracy of 91.42%, precision of 71.41%, and recall of 72.51%, effectively distinguishing between high and low gamma activity states. This performance surpasses traditional machine learning methods for EEG analysis, such as support vector machines and random forests, which typically achieve accuracies between 70–85% for similar tasks. Our approach offers significant time savings over manual EEGLAB methods. The integration of event-related spectral perturbation (ERSP) analysis with a novel CNN architecture enables capture of both fine-grained and broad spectral EEG features, advancing the field of computational neuroscience. This research has implications for brain-computer interfaces, clinical diagnostics, and cognitive monitoring, offering a more efficient and accurate alternative to current EEG analysis methods. Full article

Emotion is an intricate cognitive state that, when identified, can serve as a crucial component of the brain–computer interface. This study examines the identification of two categories of positive and negative emotions through the development and implementation of a dry electrode electroencephalogram (EEG). To achieve this objective, a dry EEG electrode is created using the silver-copper sintering technique, which is assessed through Scanning Electron Microscope (SEM) and Energy Dispersive X-ray Analysis (EDXA) evaluations. Subsequently, a database is generated utilizing the designated electrode, which is based on the musical stimulus. The collected data are fed into an improved deep network for automatic feature selection/extraction and classification. The deep network architecture is structured by combining type 2 fuzzy sets (FT2) and deep convolutional graph networks. The fabricated electrode demonstrated superior performance, efficiency, and affordability compared to other electrodes (both wet and dry) in this study. Furthermore, the dry EEG electrode was examined in noisy environments and demonstrated robust resistance across a diverse range of Signal-To-Noise ratios (SNRs). Furthermore, the proposed model achieved a classification accuracy of 99% for distinguishing between positive and negative emotions, an improvement of approximately 2% over previous studies. The manufactured dry EEG electrode is very economical and cost-effective in terms of manufacturing costs when compared to recent studies. The proposed deep network, combined with the fabricated dry EEG electrode, can be used in real-time applications for long-term recordings that do not require gel. Full article

EEG-based biometrics represent a relatively recent research field that aims to recognize individuals based on their recorded brain activity using electroencephalography (EEG). Among the numerous features that have been proposed, connectivity-based approaches represent one of the more promising methods tested so far. In this paper, using the phase lag index (PLI) and the phase locking value (PLV) methods, we investigate how the performance of a connectivity-based EEG biometric system varies with respect to different time windows (using epochs of different lengths ranging from 0.5 s to 12 s with a step of 0.5 s) to understand if it is possible to define the optimal duration of the EEG signal required to extract those distinctive features. All the analyses were performed on two freely available EEG datasets, including 109 and 23 subjects, respectively. Overall, as expected, the results have shown a pronounced effect of the time window length on the biometric performance measured in terms of EER (equal error rate) and AUC (area under the curve), with an evident increase in the biometric performance as the time window increases. Furthermore, our initial findings strongly suggest that enlarging the window size beyond a specific maximum threshold fails to enhance the performance of biometric systems. In conclusions, we want to highlight that EEG connectivity has the potential to represent an optimal candidate as an EEG fingerprint and that, in this context, it is essential to establish an adequate time window capable of capturing subject-specific features. Furthermore, we speculate that the poor performance obtained with short time windows mainly depends on the difficulty of correctly estimating the connectivity metrics from very small EEG epochs (shorter than 8 s). Full article

Conductive polymer composites are commonly present in flexible electrodes for neural interfaces, implantable sensors, and aerospace applications. Fused filament fabrication (FFF) is a widely used additive manufacturing technology, where conductive filaments frequently contain carbon-based fillers. In this study, the static and dynamic mechanical properties and the electrical properties (resistance, signal transmission, resistance measurements during cyclic tensile, bending and temperature tests) were investigated for polylactic acid (PLA)-based, acrylonitrile butadiene styrene (ABS)-based, thermoplastic polyurethane (TPU)-based, and polyamide (PA)-based conductive filaments with carbon-based additives. Scanning electron microscopy (SEM) was implemented to evaluate the results. Cytotoxicity measurements were performed. The conductive ABS specimens have a high gauge factor between 0.2% and 1.0% strain. All tested materials, except the PA-based conductive composite, are suitable for low-voltage applications such as 3D-printed EEG and EMG sensors. ABS-based and TPU-based conductive composites are promising raw materials suitable for temperature measuring and medical applications. Full article

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain–computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding. Full article

Decoding semantic concepts for imagination and perception tasks (SCIP) is important for rehabilitation medicine as well as cognitive neuroscience. Electroencephalogram (EEG) is commonly used in the relevant fields, because it is a low-cost noninvasive technique with high temporal resolution. However, as EEG signals contain a high noise level resulting in a low signal-to-noise ratio, it makes decoding EEG-based semantic concepts for imagination and perception tasks (SCIP-EEG) challenging. Currently, neural network algorithms such as CNN, RNN, and LSTM have almost reached their limits in EEG signal decoding due to their own short-comings. The emergence of transformer methods has improved the classification performance of neural networks for EEG signals. However, the transformer model has a large parameter set and high complexity, which is not conducive to the application of BCI. EEG signals have high spatial correlation. The relationship between signals from different electrodes is more complex. Capsule neural networks can effectively model the spatial relationship between electrodes through vector representation and a dynamic routing mechanism. Therefore, it achieves more accurate feature extraction and classification. This paper proposes a spatio-temporal capsule network with a self-correlation routing mechaninsm for the classification of semantic conceptual EEG signals. By improving the feature extraction and routing mechanism, the model is able to more effectively capture the highly variable spatio-temporal features from EEG signals and establish connections between capsules, thereby enhancing classification accuracy and model efficiency. The performance of the proposed model was validated using the publicly accessible semantic concept dataset for imagined and perceived tasks from Bath University. Our model achieved average accuracies of 94.9%, 93.3%, and 78.4% in the three sensory modalities (pictorial, orthographic, and audio), respectively. The overall average accuracy across the three sensory modalities is 88.9%. Compared to existing advanced algorithms, the proposed model achieved state-of-the-art performance, significantly improving classification accuracy. Additionally, the proposed model is more stable and efficient, making it a better decoding solution for SCIP-EEG decoding. Full article

Background: Developing and testing methods for reliably measuring the state of consciousness of individuals is important for both basic research and clinical purposes. In recent years, several promising measures of consciousness, grounded in theoretical developments, have been proposed. However, the degrees to which these measures are affected by changes in brain activity that are not related to changes in the degree of consciousness has not been well tested. In this study, we examined whether several of these measures are modulated by the loading of cognitive resources. Methods: We recorded electroencephalography (EEG) from 12 participants in two conditions: (1) while passively attending to sensory stimuli related to the measures and (2) during increased cognitive load consisting of a demanding working memory task. We investigated whether a set of proposed objective EEG-based measures of consciousness differed between the passive and the cognitively demanding conditions. Results: The P300b event-related potential (sensitive to conscious awareness of deviance from an expected pattern in auditory stimuli) was significantly affected by concurrent performance on a working memory task, whereas various measures based on signal diversity of spontaneous and perturbed EEG were not. Conclusion: Because signal diversity-based measures of spontaneous or perturbed EEG are not sensitive to the degree of cognitive load, we suggest that these measures may be used in clinical situations where attention, sensory processing, or command following might be impaired. Full article

Mixed Reality (MR) environments hold immense potential for inducing a sense of embodiment, where users feel like their bodies are present within the virtual space. This subjective experience has been traditionally assessed using subjective reports and behavioral measures. However, neurophysiological approaches offer unique advantages in objectively characterizing embodiment. This review article explores the current state of the art in utilizing neurophysiological techniques, particularly Electroencephalography (EEG), Photoplethysmography (PPG), and Electrodermal activity (EDA), to investigate the neural and autonomic correlates of embodiment in MR for out-of-the-lab applications. More specifically, it was investigated how EEG, with its high temporal resolution, PPG, and EDA, can capture transient brain activity associated with specific aspects of embodiment, such as visuomotor synchrony, visual feedback of a virtual body, and manipulations of virtual body parts. The potential of such neurophysiological signals to differentiate between subjective experiences of embodiment was discussed, with a particular regard to identify the neural and autonomic markers of early embodiment formation during MR exposure in real settings. Finally, the strengths and limitations of the neurophysiological approach in the context of MR embodiment research were discussed, in order to achieve a more comprehensive understanding of this multifaceted phenomenon. Full article