Search Results (334)

Transformer-based models have accelerated EEG motor imagery (MI) decoding by using self-attention to capture long-range temporal structures while complementing spatial inductive biases. This systematic survey of Scopus-indexed works from 2020 to 2025 indicates that reported advances are concentrated in offline, protocol-heterogeneous settings; inconsistent preprocessing, non-standard data splits, and sparse efficiency frequently reporting cloud claims of generalization and real-time suitability. Under session- and subject-aware evaluation on the BCIC IV 2a/2b dataset, typical performance clusters are in the high-80% range for binary MI and the mid-70% range for multi-class tasks with gains of roughly 5–10 percentage points achieved by strong hybrids (CNN/TCN–Transformer; hierarchical attention) rather than by extreme figures often driven by leakage-prone protocols. In parallel, transformer-driven denoising—particularly diffusion–transformer hybrids—yields strong signal-level metrics but remains weakly linked to task benefit; denoise → decode validation is rarely standardized despite being the most relevant proxy when artifact-free ground truth is unavailable. Three priorities emerge for translation: protocol discipline (fixed train/test partitions, transparent preprocessing, mandatory reporting of parameters, FLOPs, per-trial latency, and acquisition-to-feedback delay); task relevance (shared denoise → decode benchmarks for MI and related paradigms); and adaptivity at scale (self-supervised pretraining on heterogeneous EEG corpora and resource-aware co-optimization of preprocessing and hybrid transformer topologies). Evidence from subject-adjusting evolutionary pipelines that jointly tune preprocessing, attention depth, and CNN–Transformer fusion demonstrates reproducible inter-subject gains over established baselines under controlled protocols. Implementing these practices positions transformer-driven BCIs to move beyond inflated offline estimates toward reliable, real-time neurointerfaces with concrete clinical and assistive relevance. Full article

Achieving a dataset of eye detection comprises a critical task in computer vision and image processing. The primary goal of this dataset is to accurately locate and identify the position of eyes in image or video frames. This process can firstly detect the face region and then focus on the eye regions. In this study, 14,980 examples of physiological signal recordings, most likely from EEG or similar sensors, were included in this dataset, which was created for the analysis of neural or sensor-based movement. The constant signals from specific sensor channels are represented by 14 numerical features (AF3, F7, F3, O1, O2, P7, P8, T8, FC5, FC6, etc.). These characteristics record complex changes in signal designs over time, which could suggest shifts in sensor or neuronal activity. Also, the dataset involves a binary target variable called eye detection, and this shows if an eye-related event—such as turning or an open/closed state—is identified during an individual case. The basic label of this dataset is eye detection in human beings, which has instances of (0,1). The eye detection dataset has 14 features and 14,980 instances that can be utilized for training a model. Full article

Children with Autism Spectrum Disorder (ASD) often experience cognitive difficulties that impact learning. This study explores the use of electroencephalogram data collected with the MUSE 2 headband during task-based cognitive sessions to understand how cognitive states in children with ASD change across three structured tasks: Shape Matching, Shape Sorting, and Number Matching. Following signal preprocessing using Independent Component Analysis (ICA), power across various frequency bands was extracted using the Welch method. These features were used to analyze cognitive states in children with ASD in comparison to typically developing (TD) peers. To capture dynamic changes in attention over time, Morlet wavelet transform was applied, revealing distinct brain signal patterns. Machine learning classifiers were then developed to accurately distinguish between ASD and TD groups using the EEG data. Models included Support Vector Machine, K-Nearest Neighbors, Random Forest, an Ensemble method, and a Neural Network. Among these, the Ensemble method achieved the highest accuracy at 0.90. Feature importance analysis was conducted to identify the most influential EEG features contributing to classification performance. Based on these findings, an ASD map was generated to visually highlight the key EEG regions associated with ASD-related cognitive patterns. These findings highlight the potential of EEG-based models to capture ASD-specific neural and attentional patterns during learning, supporting their application in developing more personalized educational approaches. However, due to the limited sample size and participant heterogeneity, these findings should be considered exploratory. Future studies with larger samples are needed to validate and generalize the results. Full article

Objective: This study aimed to explore the impact of sanda sports experience on cognitive control using electroencephalography (EEG). Methods: The study involved 38 male participants, including 19 sanda athletes with over 5 years of training and 19 ordinary college students. A 2 × 4 mixed experimental design was used, with group (sanda athletes vs. ordinary college students) as the between-subjects variable and four experimental conditions (consistent in the previous and current trials, consistent in the previous but inconsistent in the current trials, inconsistent in the previous but consistent in the current trials, and inconsistent in both previous and current trials) as the within-subjects variable. The classic color-word Stroop task was employed to measure cognitive control function through reaction time, accuracy, and event-related potential (ERP) amplitude. Results: Sanda athletes exhibited significantly shorter reaction times than ordinary college students across all conditions (p < 0.05). There was no significant difference in accuracy between the two groups (p > 0.05). ERP results showed that sanda athletes had significantly larger amplitudes for the N200 and P300 components in incongruent trials compared to congruent trials (p < 0.05), and significantly larger N400 amplitudes in incongruent trials than ordinary college students (p < 0.05). Conclusions: Sanda athletes demonstrated faster response speed and enhanced cognitive control abilities, as indicated by ERP components, without sacrificing task accuracy. Full article

Electroencephalography signal generation remains a challenging task due to its non-stationarity, multi-scale oscillations, and strong spatiotemporal coupling. Conventional generative models, including VAEs and GAN variants such as DCGAN, WGAN, and WGAN-GP, often yield blurred waveforms, unstable spectral distributions, or lack semantic controllability, limiting their effectiveness in emotion-related applications. To address these challenges, this research proposes a Transformer-based conditional variational autoencoder–generative adversarial network (Trans-cVAE-GAN) that combines Transformer-driven temporal modeling, label-conditioned latent inference, and adversarial learning. A multi-dimensional structural loss further constrains generation by preserving temporal correlation, frequency-domain consistency, and statistical distribution. Experiments on three SEED-family datasets—SEED, SEED-FRA, and SEED-GER—demonstrate high similarity to real EEG, with representative mean ± SD correlations of Pearson ≈ 0.84 ± 0.08/0.74 ± 0.12/0.84 ± 0.07 and Spearman ≈ 0.82 ± 0.07/0.72 ± 0.12/0.83 ± 0.08, together with low spectral divergence (KL ≈ 0.39 ± 0.15/0.41 ± 0.20/0.37 ± 0.18). Comparative analyses show consistent gains over classical GAN baselines, while ablations verify the indispensable roles of the Transformer encoder, label conditioning, and cVAE module. In downstream emotion recognition, augmentation with generated EEG raises accuracy from 86.9% to 91.8% on SEED (with analogous gains on SEED-FRA and SEED-GER), underscoring enhanced generalization and robustness. These results confirm that the proposed approach simultaneously ensures fidelity, stability, and controllability across cohorts, offering a scalable solution for affective computing and brain–computer interface applications. Full article

Background/Objectives: The Adaptive Control Hypothesis posits varying control demands across language contexts in production, but its role in comprehension is underexplored. We investigated if trilinguals, who manage three dual-language contexts (L1–L2, L2–L3, L1–L3), exhibit differential proactive and reactive control demands during comprehension across these contexts. Methods: Thirty-six Uyghur–Chinese–English trilinguals completed an auditory word-picture matching task across three dual-language contexts during EEG recording. We employed behavioral analysis, drift-diffusion modeling, event-related potential (ERP) analysis, and multivariate pattern analysis (MVPA) to examine comprehension efficiency, evidence accumulation, and neural mechanisms. The design crossed context (L1–L2, L2–L3, L1–L3) with trial type (switch vs. repetition) and switching direction (to dominant vs. non-dominant language). Results: Despite comparable behavioral performance, drift-diffusion modeling revealed distinct processing profiles across contexts, with the L1–L2 context showing the lowest comprehension efficiency due to slower evidence accumulation. In the L1–L3 context, comprehension-specific proactive control was indexed by a larger P300 and smaller N400 for L1-to-L3 switches. Notably, no reactive control (switch costs) was observed across any dual-language context. MVPA successfully classified contexts and switching directions, revealing distinct spatiotemporal neural patterns. Conclusions: Trilingual comprehension switching mechanisms differ from production. Reactive control is not essential, while proactive control is context-dependent, emerging only in the high-conflict L1–L3 context. This proactive strategy involves allocating more bottom-up attention to the weaker L3, which, unlike in production, enhances rather than hinders overall efficiency. Full article

This study introduces a machine learning–driven extended reality (XR) interaction framework that leverages electroencephalography (EEG) for decoding consumer intentions in immersive decision-making tasks, demonstrated through functional food purchasing within a simulated autonomous vehicle setting. Recognizing inherent limitations in traditional “Preference vs. Non-Preference” EEG paradigms for immersive product evaluation, we propose a novel and robust “Rest vs. Intention” classification approach that significantly enhances cognitive signal contrast and improves interpretability. Eight healthy adults participated in immersive XR product evaluations within a simulated autonomous driving environment using the Microsoft HoloLens 2 headset (Microsoft Corp., Redmond, WA, USA). Participants assessed 3D-rendered multivitamin supplements systematically varied in intrinsic (ingredient, origin) and extrinsic (color, formulation) attributes. Event-related potentials (ERPs) were extracted from 64-channel EEG recordings, specifically targeting five neurocognitive components: N1 (perceptual attention), P2 (stimulus salience), N2 (conflict monitoring), P3 (decision evaluation), and LPP (motivational relevance). Four ensemble classifiers (Extra Trees, LightGBM, Random Forest, XGBoost) were trained to discriminate cognitive states under both paradigms. The ‘Rest vs. Intention’ approach achieved high cross-validated classification accuracy (up to 97.3% in this sample), and area under the curve (AUC > 0.97) SHAP-based interpretability identified dominant contributions from the N1, P2, and N2 components, aligning with neurophysiological processes of attentional allocation and cognitive control. These findings provide preliminary evidence of the viability of ERP-based intention decoding within a simulated autonomous-vehicle setting. Our framework serves as an exploratory proof-of-concept foundation for future development of real-time, BCI-enabled in-transit commerce systems, while underscoring the need for larger-scale validation in authentic AV environments and raising important considerations for ethics and privacy in neuromarketing applications. Full article

The ability of police officers to make correct decisions under emotional stress is critical, as errors in high-pressure situations can have severe legal and physical consequences. This study aims to evaluate the neurophysiological responses of police academy cadets during stressful decision-making scenarios and to predict individual stress levels from those responses. Fifty-eight police academy cadets from three cohorts watched a custom-made, naturalistic video scene and then chose the appropriate course of action. Simultaneous 32-channel electroencephalography (EEG) and electrocardiography (ECG) captured brain and heart activity. Event-related potentials (ERPs) and band-specific power features (particularly delta) were extracted, and machine-learning models were trained with nested cross-validation to predict perceived stress scores. Global and broadband EEG activity was suppressed during the video stimulus and did not return to baseline during the cooldown phase. Widespread ERPs and pronounced delta-band dynamics emerged during decision-making, correlating with both cohort rank and self-reported stress. Crucially, a combined EEG + cohort model predicted perceived stress with an out-of-fold R² of 0.32, outperforming EEG-only (R² = 0.23) and cohort-only (R² = 0.17) models. To our knowledge, this is the first study to both characterize EEG dynamics during stressful naturalistic decision tasks and demonstrate their predictive utility. These findings lay the groundwork for neurofeedback-based training paradigms that help officers modulate stress responses and calibrate decision-making under pressure. Full article

To uncover neurobiological indicators related to autism spectrum disorders and developmental dyslexia, this article gives a full overview of the most recent advances in machine learning and deep learning methods based on electroencephalography. We look into methodological pipelines that include signal gathering, preprocessing, feature engineering, model selection, and interpretability procedures. We based these pipelines on 15 peer-reviewed research papers published between 2013 and 2025. Most of the research employed the 10–20 system for resting-state EEG and followed MATLAB, MNE-Python, or EEGLAB guidelines for preprocessing. The feature sets included spectral power, functional connectivity, task-evoked potentials, and entropy measures. People used many standard ML methods, such as support vector machines and random forests, as well as more advanced models, like deep neural networks and transformer-based architectures. Several studies found that both dyslexic and ASD groups did well at classifying, with accuracy scores between 82% and 99.2%. The new models could be used in therapeutic settings, but there are still problems with how easy they are to understand and how well they apply to a wide range of situations. This is especially true for ASD because its spectrum is so varied. Full article

Background/Objectives: Mental fatigue during driving, whether passive (arising from monotony) or active (caused by cognitive overload), is a critical factor for road safety. Despite the growing interest in monitoring techniques based on neurophysiological signals, current biomarkers are primarily validated only for detecting passive mental fatigue under monotonous conditions. The objective of this study is to evaluate the sensitivity of the MDrow index, which is based on EEG Alpha band activity, previously validated for detecting passive mental fatigue, with respect to active mental fatigue, i.e., the mental fatigue occurring in cognitively demanding driving scenarios. Methods: A simulated experimental protocol was developed featuring three driving scenarios with increasing complexity: monotonous, urban, and urban with dual tasks. Nineteen participants took part in the experiment, during which electroencephalogram (EEG), photoplethysmogram (PPG), and electrodermal activity (EDA) data were collected in addition to subjective assessments, namely the Karolinska Sleepiness Scale (KSS) and the Driving Activity Load Index (DALI) questionnaires. Results:The findings indicate that MDrow shows sensitivity to both passive and active mental fatigue (p < 0.001), thereby demonstrating stability even in the presence of additional cognitive demands. Furthermore, Heart Rate (HR) and Heart Rate Variability (HRV) increased significantly during the execution of more complex tasks, thereby suggesting a heightened response to mental workload in comparison to mental fatigue alone. Conversely, electrodermal measures evidenced no sensitivity to mental fatigue-related changes. Conclusions: These findings confirm the MDrow index’s validity as an objective and continuous marker of mental fatigue, even under cognitively demanding conditions. Full article

Background: the Skill, Rule, and Knowledge (S-R-K) model is a framework used to describe and analyze human behaviour and decision-making in complex environments based on the nature of the task and kind of cognitive control required. The S-R-K model is particularly useful in fields like human factor engineering, system design, and safety-critical industries because it helps to understand human errors and how they relate to different levels of cognitive control. However, the S-R-K model is still qualitative and lacks specific and quantifiable metrics for determining what kind of cognitive control a person is using at any given time. This aspect makes difficult to directly measure and compare performance across the three levels. This study aimed therefore to characterize the S-R-K model from a neurophysiological perspective by analyzing the operator’s cerebral cortical activity. Methods: in this study, participants carried out experimental tasks able to replicate the Skill (tracking task), Rule (rule-based navigation) and Knowledge conditions (unfamiliar situations). Results: participants’ Electroencephalogram (EEG) was recorded during tasks execution and then Global Field Power (GFP) was estimated in the different EEG frequency bands. Brodmann areas (BAs) and EEG features were then used to characterize the S-R-K pattern over the cerebral cortex and as inputs to build up the machine learning-based model to estimate participants’ cognitive control behaviours while dealing with tasks. Conclusions: the results demonstrate the possibility of objectively measuring the different S, R and K levels in terms of brain activations. Furthermore, such evidence is consistent with the scientific literature in terms of cognitive functions corresponding to the different levels of cognitive control. Full article

The aim of this study is to analyze the signal generated in the brain for a specific motor task and to identify the region where it occurs. For this purpose, electroencephalography (EEG) signals were divided into delta, theta, alpha, and beta frequency sub-bands, and feature extraction was performed by looking at the time-frequency characteristics of the signals belonging to the obtained sub-bands. The epoch corresponding to motor imagery or action and the signal source in the brain were determined by power spectral density features. This study focused on a hand open–close motor task as an example. A machine learning structure was used for signal recognition and classification. The highest accuracy of 92.9% was obtained with the neural network in relation to signal recognition and action realization. In addition to the classification framework, this study also incorporated advanced preprocessing and energy analysis techniques. Eye blink artifacts were automatically detected and removed using independent component analysis (ICA), enabling more reliable spectral estimation. Furthermore, a detailed channel-based and sub-band energy analysis was performed using fast Fourier transform (FFT) and power spectral density (PSD) estimation. The results revealed that frontal electrodes, particularly Fp1 and AF7, exhibited dominant energy patterns during both real and imagined motor tasks. Delta band activity was found to be most pronounced during rest with T1 and T2, while higher-frequency bands, especially beta, showed increased activity during motor imagery, indicating cognitive and motor planning processes. Although 30 s epochs were initially used, event-based selection was applied within each epoch to mark short task-related intervals, ensuring methodological consistency with the 2–4 s windows commonly emphasized in the literature. After artifact removal, motor activity typically associated with the C3 region was also observed with greater intensity over the frontal electrode sites Fp1, Fp2, AF7, and AF8, demonstrating hemispheric symmetry. The delta band power was found to be higher than that of other frequency bands across T0, T1, and T2 conditions. However, a marked decrease in delta power was observed from T0 to T1 and T2. In contrast, beta band power increased by approximately 20% from T0 to T2, with a similar pattern also evident in gamma band activity. These changes indicate cognitive and motor planning processes. The novelty of this study lies in identifying the electrode that exhibits the strongest signal characteristics for a specific motor activity among 64-channel EEG recordings and subsequently achieving high-performance classification of the corresponding motor activity. Full article

The current study aimed to investigate the impact of externally evoked mental workload on the level of an artificial hand ownership sensation, a component of the embodiment phenomenon (feeling an external object, in this case a fake upper limb, as part of one’s body). The process of embodiment is extensively investigated in the literature also to find solutions for promoting the acceptance of prosthetic limbs. Before a traditional procedure for summoning in healthy subjects a Rubber Hand Illusion (RHI), the participants performed memory-related tasks in easy or demanding conditions to generate, respectively, low and high mental workloads. Alongside the behavioral correlates of the body ownership in the form of a proprioceptive drift (the measure of the correspondence between the perceived position of the actual limb and the fake one), EEG data was also collected. The results, both behavioral and neural, suggest that a high mental workload before the RHI experience leads to a low level of body ownership, whereas a low one enhances it. This can be interpreted as a consequence of distracting mental resources (possibly a specific type of them) from the embodiment stimulation session. Full article

Background/Objectives: Motor decline in older adults can hinder cognitive assessments. To address this, we developed a brain–computer interface (BCI) using electroencephalography (EEG) and event-related potentials (ERPs) as a motor-independent EEG Switch. ERPs reflect attention-related neural activity and may serve as biomarkers for cognitive function. This study evaluated the feasibility of using ERP-based task success rates as indicators of cognitive abilities. The main goal of this article is the development and baseline evaluation of the Neurodetector system (incorporating the EEG Switch) as a motor-independent tool for cognitive assessment in healthy adults. Methods: We created a system called Neurodetector, which measures cognitive function through the ability to perform tasks using a virtual one-button EEG Switch. EEG data were collected from 40 healthy adults, mainly under 60 years of age, during three cognitive tasks of increasing difficulty. Results: The participants controlled the EEG Switch above chance level across all tasks. Success rates correlated with task difficulty and showed individual differences, suggesting that cognitive ability influences performance. In addition, we compared the pattern-matching method for ERP decoding with the conventional peak-based approaches. The pattern-matching method yielded a consistently higher accuracy and was more sensitive to task complexity and individual variability. Conclusions: These results support the potential of the EEG Switch as a reliable, non-motor-dependent cognitive assessment tool. The system is especially useful for populations with limited motor control, such as the elderly or individuals with physical disabilities. While Mild Cognitive Impairment (MCI) is an important future target for application, the present study involved only healthy adult participants. Future research should examine the sources of individual differences and validate EEG switches in clinical contexts, including clinical trials involving MCI and dementia patients. Our findings lay the groundwork for a novel and accessible approach for cognitive evaluation using neurophysiological data. Full article

Background: Older adults often struggle to comprehend speech in noisy environments, a challenge influenced by declines in both auditory processing and cognitive functions. This study aimed to investigate how differences in speech-in-noise perception among individual with clinically normal hearing thresholds (ranging from normal to mild hearing loss in older adults) are related to neural speech tracking and cognitive function, particularly working memory. Method: Specifically, we examined delta (1–4 Hz) and theta (4–8 Hz) EEG oscillations during speech recognition tasks to determine their association with cognitive performance in older adults. EEG data were collected from 23 young adults (20–35 years) and 23 older adults (65–80 years). Cognitive assessments were administered to older adults, and both groups completed an EEG task involving speech recognition in Speech-Shaped Noise (SSN) at individualized noise levels based on their Sentence Recognition Scores (SRS). Results: The results showed that age significantly impacted hit rates and reaction times in noisy speech recognition tasks. Theta-band neural tracking was notably stronger in older adults, while delta-band tracking showed no age-related difference. Pearson’s correlations indicated significant associations between age-related cognitive decline, reduced hearing sensitivity, and Mini-Mental State Examination (MMSE) scores. Regression analyses showed that theta-band neural tracking at specific SRS levels significantly predicted word list recognition in the higher SRT group, while constructional recall was strongly predicted in the lower SRT group. Conclusions: These findings suggest that older adults may rely on theta-band neural tracking as a compensatory mechanism. However, regression results alone were not sufficient to fully explain how working memory affects neural tracking, and additional cognitive and linguistic factors should be considered in future studies. Furthermore, cognitive assessments were administered only to older adults, which limits the ability to determine whether group differences are driven by age, hearing, or cognitive status—a major limitation that should be addressed in future research. Full article