Search Results (828)

Electroencephalogram (EEG) signals hold significant research value in brain function decoding, disease diagnosis, and brain–computer interfaces (BCIs). Few-channel EEG recording devices feature superior portability, simple operation, and facilitated real-time monitoring implementation. However, few-channel motor imagery (MI) EEG signals inherently suffer from data scarcity and limited spatial discriminative information, which pose critical challenges, including insufficient feature extraction and poor robustness in classification tasks. To address these issues, this paper presents EEG–ShuffleFormer, a hybrid network that integrates two complementary views of EEG signals: time–frequency representations obtained via continuous wavelet transform and the original raw signal representations. A lightweight ShuffleNet backbone extracts local features, followed by a Transformer encoder that models long-range temporal dependencies. Evaluated on the BCI Competition IV Dataset 2b, the proposed method achieves an average classification accuracy of 82.23%, with a substantial improvement on challenging subjects compared to the closest baseline method. Compared with existing methods, the proposed multi-view fusion strategy raises the performance floor while maintaining high accuracy on typical subjects, demonstrating its potential to enhance robustness for different subjects in few-channel scenarios. Full article

Imagined speech decoding has attracted growing interest in brain–computer interface (BCI) research, as it may enable language-related information to be recovered from non-overt neural activity. Current studies in this area are often treated as a single, unified research problem, despite substantial differences in decoding target, output constraints, and system output forms. This review examines recent imagined speech decoding research from a task-oriented perspective, with a focus on how different neural decoding tasks are defined, constrained by their output spaces, and expressed through different output pathways. The included studies are organized into four main task levels: semantic/intent, phoneme/syllable, word, and sentence/language decoding. They are further compared along two auxiliary dimensions: output-space property and output pathway, with particular attention to closed-set and open-vocabulary settings. The review shows that current studies span markedly different linguistic granularities and communication objectives, from low-bandwidth intent recognition to text or speech reconstruction. Finally, it concludes that imagined speech should not be treated as a single homogeneous decoding problem, and that a task-oriented framework provides a clearer basis for comparing heterogeneous studies and guiding future communication-oriented BCI research. Full article

Social robots hold promise for enhancing later-life support, but user needs and preferences for multimodal interaction modalities remain underexplored. This study explores awareness, willingness, perceived barriers, and modality–function associations across multiple interaction modalities among middle-aged and older adults, and proposes a conceptual five-layer architecture for design guidance. A questionnaire survey with 199 Chinese respondents (aged 45–64: 89.4%, 65+: 10.6%) examined perceptions of voice, visual, gestural, affective, sEMG, and brain–computer interface interactions. Voice and visual modalities were the most preferred; gesture and affective interactions were moderately accepted; awareness of sEMG was high but may reflect confusion with other sensor technologies; and BCI awareness and willingness were low. Based on survey findings and the literature, a conceptual five-layer architecture is presented to inform future social-robot design. The sample predominantly comprised middle-aged participants, so findings reflect prospective later-life users rather than the broader older-adult population. This study offers user-centered insights into multimodal social-robot interaction and provides design implications for future development rather than evaluating emotional-health interventions. Full article

Auditory neurofeedback training (NFT) based on brain–computer interfaces (BCIs) has recently entered the precision motor domain as a task-embedded neural state regulation paradigm. Compared to traditional standalone NFT approaches (e.g., relaxation or attention training designed to enhance general cognitive abilities), task-embedded paradigms integrate feedback directly into the motor task execution process. However, this design inevitably creates a dual-task scenario, and the effects of such a scenario on neural activity and behavioral performance have received limited systematic investigation in the existing literature. This study designed and implemented a closed-loop BCI system employing five-level heartbeat sound feedback and used this system as a research platform to examine the immediate neural mechanism changes and potential dual-task interference effects induced by single-session auditory NFT in moderately skilled shooters. The system maps real-time EEG features onto graded auditory signals varying in playback rate and volume intensity, incorporating a dynamic threshold adjustment mechanism. Twenty-two moderately skilled shooters completed three within-subject conditions (no-sound baseline, SMR enhancement, and theta suppression) in a single session with 32-channel EEG and behavioral data recorded simultaneously. Analyses employed whole-brain cluster-based permutation tests, cross-frequency coupling analysis, and functional connectivity analysis. Cluster-based permutation tests revealed that theta feedback induced a significant frontal 4–7 Hz suppression cluster (cluster p = 0.004), whereas SMR feedback did not produce significant 12–15 Hz enhancement at the group level. Theta feedback elicited cross-frequency spillover as follows: sensorimotor SMR power decreased significantly in theta responders (d = −0.69), with frontal theta and sensorimotor SMR changes positively correlated (r = 0.67, p < 0.001). Functional connectivity analysis using debiased weighted phase lag index (dwPLI) further demonstrated significant theta-band network reorganization (cluster p = 0.034). At the neural level, clear modulation effects were observed, but shooting ring values did not improve significantly under feedback conditions, and aiming time was significantly prolonged—a behavioral pattern consistent with potential dual-task interference from task-embedded auditory feedback. Single-session auditory NFT can act on the prefrontal cognitive control network and induce cross-frequency network reorganization, but the feedback channel itself constitutes a parallel task that may limit the short-term transfer of induced neural states to behavioral performance. This study examined the neural mechanisms of task-embedded auditory NFT and reported the dual-task costs that have been less characterized in prior “task + feedback” research, providing design considerations and preliminary mechanistic evidence for future development of auditory NFT in precision motor skill training. Full article

Real-time detection of motor intent using electroencephalography (EEG) with high accuracy remains a technical challenge for neurorehabilitation. Brain–computer interface-based neurofeedback training (BCI-NFT) paradigms need to detect pre-movement EEG to activate robotics or electrical stimulation nearly simultaneously with movement to promote neuroplasticity. We present a novel detection method commonly used in time-series forecasting (e.g., stock market trends), identifying crosses in fast (short) and slow (long) moving average windows to identify negative deflections in slow movement-related cortical potentials (MRCPs) or event-related desynchronization (ERD) within −400–+100 ms of movement onset. We recorded EEG data from the Cz electrode during our cued ankle dorsiflexion BCI-NFT paradigm in four adult participants, two neurotypical and two with cerebral palsy. Simulated real-time offline analyses demonstrated an 85.9% mean true positive rate and 14.1% false positive rate of detecting motor intent at a mean −182 ms from movement onset. We further evaluated whether the detection indicated a MRCP and/or ERD, with MRCP detected in 70–80% of trials in three participants, but high ERD detection (87%) instead in the other. Preliminary results indicate that this approach offers a straightforward, accurate, and well-timed method for real-time EEG detection during neurofeedback training and as a control signal for brain–computer interfaces. Full article

Electroencephalography (EEG)-based brain–computer interface (BCI) systems pose significant privacy risks, as EEG data remain vulnerable to inference and reconstruction attacks. Conventional privacy-preserving techniques, including data anonymization, encryption, and perturbation, frequently compromise data utility or prove ineffective against advanced adversaries. To address these limitations and balance utility and privacy, we propose a quantum-inspired, differential privacy-based generative adversarial network (Q-DP-GAN). Unlike classical GANs, which lack adaptive privacy mechanisms during training, our method uses quantum-inspired stochasticity to dynamically calibrate noise and the privacy budget. The experimental results demonstrate that Q-DP-GAN is more robust to membership inference and reconstruction attacks than existing approaches. Evaluation on the widely used BCI Competition IV Datasets 2A and 2B indicates that our framework produces high-quality synthetic EEG data while maintaining utility and data confidentiality for BCI classification tasks. Full article

Motor imagery (MI)-based brain–computer interfaces (BCIs) provide an intuitive pathway for neural interaction and rehabilitation, yet their practical deployment remains constrained by long calibration requirements, substantial inter-subject variability, and the non-stationary nature of EEG signals. These challenges are amplified when using dry-electrode EEG, which offers superior convenience for real-world systems but produces noisier and less stable recordings than traditional wet electrodes. As a result, online or real-time four-class MI detection—especially with dry electrodes—has been explored only in a limited number of studies, underscoring an important gap in the field and the need for adaptive, intelligent models capable of coping with continuous signal drift. In this study, we propose a real-time MI-BCI framework that integrates immersive action observation (AO) in virtual reality with a continual learning strategy to manage the evolving nature of dry-EEG features. A CNN–Transformer hybrid model is first initialized through AO-enhanced pre-training and subsequently refined via online continual adaptation during user interaction. This continual learning mechanism enables the classifier to incrementally assimilate new MI patterns while preserving previously acquired knowledge, thereby mitigating the performance degradation that typically arises in extended MI-BCI sessions. Experimental results across four motor classes demonstrate improved decoding accuracy and strengthened sensorimotor activation over time, confirming the system’s capacity for user-specific and session-to-session adaptation. By addressing the rarely studied combination of dry electrodes, online four-class MI decoding, and continual learning, the proposed approach enhances MI-BCI robustness, reduces calibration burden, and supports sustainable long-term deployment in intelligent neurotechnology applications. Full article

Motor Imagery (MI)-based brain–computer interfaces (BCIs) offer promising solutions for enhancing communication and motor functions in individuals with neurological impairments. However, decoding EEG signals accurately is difficult because of their poor signal-to-noise ratio and variability across subjects and sessions. In addition, EEG signals are sensitive to noise. Moreover, the low spatial resolution of EEG signals makes model generalization unreliable due to differences between signals across subjects. While several deep learning models have been developed, a fair comparison remains difficult due to differences in pre-processing, training procedures, and evaluation protocols. This study provides a systematic, controlled comparison of five deep learning approaches for subject-specific classification—EEGNet, EEG-TCNet, ShallowConvNet, DeepConvNet, and CTNet—using the BCI Competition IV datasets 2a and 2b. To enable an unbiased comparison, all models are trained using the same pipeline, with uniform pre-processing and training. Apart from classical accuracy scores, the effect of a constant set of hyper-parameters on the training dynamics, generalization capacity, and the susceptibility to overfitting is evaluated. The performance of the above-stated models is evaluated based on training dynamics, computational efficiency, accuracy, and the quality of the features learned by the models. Using the five-dimensional analysis framework consisting of quantitative performance metrics, training curves, confusion matrix analysis, ROC analysis, and t-SNE visualization techniques, the performance of the brain–computer interfaces is comprehensively analyzed. The experimental analysis confirms that CTNet outperforms other models, with accuracy values of 82.56% and 86.42% on the BCI competition IV datasets 2a and 2b, respectively. The EEGNet model is recognized as having the most potential in the field of real-time applications, owing to its light structure; meanwhile, the DeepConvNet model shows signs of overfitting, despite showing good accuracy. These findings highlight that model training characteristics and sensitivity to the hyper-parameters are important factors in evaluating deep learning models for MI-EEG classification problems. Full article

The deployment of Motor Imagery Brain–Computer Interfaces (MI-BCI) is constrained by the inherent physiological variabilities of Electroencephalography (EEG) and parametric opacity. This paper presents a targeted technical audit of ten high-density MI-BCI computational pipelines, evaluating how existing literature addresses low Signal-to-Noise Ratio (SNR), intra-subject variability, and session-to-session instability. The investigation focuses on the contamination of data by ocular and muscular artifacts that overlap with the spectral components of Mu and Beta rhythms, often leading to algorithmic overfitting. Furthermore, the paper evaluates the impact of manifold drift where fluctuations in user state necessitate frequent recalibration as a primary hurdle for BCI portability. By applying a forensic evaluation framework to standardize the analysis across the ten selected studies, this paper identifies a high-performance landscape within standardized benchmarks, with classification accuracies reaching peak values of 95.42%. The audit specifically identifies a performance-reporting gap; while hybrid architectures demonstrate superior noise-rejection, they are frequently characterized by undocumented computational overhead. Additionally, while Neighborhood Component Analysis (NCA) emerges as a stable feature selection algorithm across the sampled literature, the systemic absence of reported execution times prevents a verified assessment of its low-latency viability. A critical technical finding is the widespread issue of Parametric Opacity, particularly regarding the omission of essential deterministic variables such as filter orders, windowing constants, and the final dimensionality of feature vectors. The audit reveals that the frequent failure to report the exact number of features utilized for classification masks potential overfitting and prevents an accurate assessment of the system’s generalization capabilities. Furthermore, only a specialized subset of the reviewed literature validates performance through formal statistical testing, such as Friedman ANOVA or Wilcoxon Signed-Rank tests, with most studies relying on peak accuracy metrics that may disguise filtered artifact residuals. This lack of granular documentation disguises the computational complexity of proposed methods and complicates their feasibility for hardware-in-the-loop validation. The findings establish that standardizing the reporting of preprocessing variables and feature-space dimensions is a prerequisite for overcoming current performance plateaus in universal BCI architectures. Full article

This study quantitatively evaluates the performance of a non-invasive hybrid brain–computer interface (BCI) compared to a conventional mouse in pointing (point-and-click) tasks. A commercial wearable BCI (Brainfingers), based on electromyography (EMG) and electrooculography (EOG) signals with low-level electroencephalography (EEG) components, was assessed against a Microsoft Optical Mouse using ISO/TS 9241-411-based one-dimensional (1D) and two-dimensional (2D) target acquisition tasks. Pointer coordinates were recorded and analyzed using Fitts’ law metrics. A total of 48 non-disabled participants completed the experiments. The results reveal significant performance differences between the two input devices. The BCI device exhibits substantially lower performance than the mouse across the reported Fitts’ law measures. Mean throughput was 0.35 bits/s for the BCI and 6.03 bits/s for the mouse in the 1D tests and 0.43 bits/s for the BCI and 5.17 bits/s for the mouse in the 2D tests. Despite the BCI’s low performance and although the present experiments involved non-disabled participants, the findings, considered alongside the prior literature on Brainfingers and non-invasive BCIs for computer access, suggest that the device may still have assistive technology value for users with severe motor impairments. Full article

Electroencephalogram (EEG)-based brain–computer interfaces (BCIs) offer a promising pathway for restoring communication. Decoding tonal languages like Mandarin from EEG remains challenging due to homophones and complex temporal dynamics. This study investigates the decoding of six high-frequency Mandarin action verbs—Chi (eat), He (drink), Chuan (wear), Na (take), Kan (look), and Dai (put on)—from EEG signals. We designed a visual-cue-based overt speech production experiment and collected EEG data from 30 participants during visually guided verb reading aloud. A recurrent neural network framework incorporating dual Long Short-Term Memory (LSTM) layers was implemented to model the long-range temporal dependencies in EEG patterns. The proposed model was compared against a traditional Common Spatial Pattern combined with Support Vector Machine (CSP-SVM) baseline. Our LSTM-based model achieved an average classification accuracy of 69.93% ± 3.07% for the six-class task, significantly outperforming the CSP-SVM baseline (36.53% ± 3.17%). Accuracy exceeded 75% under specific training conditions, including more than 15 training repetitions and a training-data proportion of 38%. Furthermore, the model attained this performance level utilizing approximately 38% of the available trial data for training, demonstrating data efficiency. The results indicate that the LSTM architecture can effectively capture the neural signatures associated with Mandarin verb processing, providing a foundation for developing practical EEG-based assistive communication technologies. The inference latency of the trained model, quantified as the post-training per-trial testing time, was under 2 s, supporting near-real-time applications. Full article

As a common brain-computer interface (BCI) paradigm, electroencephalogram (EEG)-based motor imagery provides a critical pathway for both assistive technology to (restoring communication and control) and active rehabilitation (promoting neural plasticity and functional recovery). Domain adaptation has been shown to effectively enhance the decoding performance of motor intentions for target subjects by leveraging labeled data from source subjects. However, EEG data from source subjects often contains extensive personal privacy, and the direct access to source EEG data easily leads to privacy leakage issues. An important research topic is to achieve domain adaptation without directly accessing the source subjects’ raw data. To address this challenge, a privacy-preserving source-free domain adaptation framework, termed Transformer-based SFDA with Class-balanced Multicentric Dynamic Pseudo-labeling (T-CMDP), is proposed for cross-subject motor-imagery EEG classification. This framework consists of three coupled stages. In the source model training stage, a Transformer-based encoder combined with Riemannian manifold-aware feature extraction is employed to learn transferable and discriminative EEG feature representations. In the source-free target adaptation stage, only the pretrained source model is transferred to the target domain and adapted through knowledge distillation and information maximization, without accessing raw source EEG data. In the self-supervised learning stage, class-balanced multicentric prototypes and high-confidence pseudo-label updates are introduced to progressively refine the target-domain decision boundaries. Extensive experiments on three motor-imagery EEG datasets demonstrate that the proposed T-CMDP framework consistently outperforms eleven representative baselines from traditional machine learning, deep learning, and source-free transfer approaches, achieving average accuracies of 56.85%, 76.34%, and 74.49%, respectively. These results indicate that T-CMDP effectively alleviates inter-subject EEG distribution discrepancies and ensures the privacy preserving of source subjects, thereby facilitating more reliable and practical deployment of EEG-based BCI systems. Full article

Flexible factories and adaptive fabrication lines offer a testbed for advanced multimodal interaction concepts that can support the inclusion of disabled workers in Industry 5.0 manufacturing systems. The study synthesizes interdisciplinary data from ergonomics, industrial automation, and EU regulatory frameworks to establish a conceptual model for human-machine interaction. Building on conceptual modeling and a structured literature analysis, the study proposes a six-step integration framework that links task demands, worker capabilities, and interaction modalities within human-in-the-loop manufacturing environments. Although no empirical case study was conducted in this phase, an exemplary application is presented for a semi-automated bike wheel manufacturing process. Detailed machine-based assembly line flows and simulated process data were utilized for illustrative purposes to depict the process and validate the proposed Capability–Task Matching Matrix. The results operationalize the human-centric vision of Industry 5.0 by providing a structured methodology for the inclusion of disabled workers within fabrication environments. The findings are organized into two primary components: the conceptual development of the Integration Approach and its practical application to a semi-automated industrial use-case. Finally, a particular focus is placed on Brain–Computer Interfaces (BCIs) as an emerging interaction channel that enables non-muscular control, attention monitoring, and neuroadaptive feedback, complementing conventional interfaces rather than replacing them. The framework is illustrated through application to the same semi-automated bicycle wheel assembly line, where BCI-supported interaction, augmented interfaces, and robotic assistance are mapped to specific production tasks and assessed in terms of feasibility and technological maturity. Drawing on the paper’s results, an explanatory 10-year roadmap outlines the feasibility and phased deployment of BCI solutions. It aligns technological advances with European regulations and a vision for a fully inclusive manufacturing enterprise. Full article

Electroencephalogram (EEG) signals serve as the core information carrier for brain–computer interfaces (BCIs); however, their highly non-stationary nature, extremely low signal-to-noise ratio, and significant inter-individual variability pose considerable challenges for signal decoding. Existing deep learning methods struggle to strike a balance between multi-scale, fine-grained feature extraction and efficient long-range temporal modeling. To overcome this limitation, this study proposes a novel deep cascaded architecture, MSResBiMamba, which deeply integrates multi-scale spatiotemporal feature learning with cutting-edge long-sequence modeling techniques. The model first utilizes an enhanced multi-scale spatiotemporal convolutional network (MS-CNN) combined with a SE-channel attention mechanism to adaptively extract local multi-band features and dynamically suppress redundant artefacts. Subsequently, it innovatively introduces an enhanced bidirectional Mamba (Bi-Mamba) module to efficiently capture non-causal long-range temporal dependencies with linear computational complexity, whilst cascading multi-head self-attention mechanisms to establish global higher-order feature interactions. Extensive experiments on the BCI Competition IV-2a dataset demonstrate that MSResBiMamba achieves outstanding classification performance in multi-class motor imagery tasks, significantly outperforming traditional methods and existing state-of-the-art neural networks. Ablation studies and t-SNE visualisations further confirm the model’s robustness in feature decoupling and cross-subject applications, providing a high-precision, high-efficiency decoding solution for BCI systems. Full article

Imaginary handwriting is an important research paradigm in the field of brain-controlled typing. Neural signals exhibit high complexity, low signal-to-noise ratio, and strong temporal and environmental variability, leading to significant inter-trial differences in the temporal dynamics of character-related signals. These factors pose significant challenges for segmenting character-related signals and accurately decoding imaginary handwriting. To address these issues, this study proposes a Dynamic Time Warping Independent Component Analysis (DTWICA) framework. This framework employs FastDTW to construct individualized warping functions for each trial, followed by FastICA-based decomposition to separate the signal into distinct temporal and neuronal factors. The decomposed temporal factors are then mapped and transformed using the warping function and subsequently merged with the neuronal factors to reconstruct the signal. A sliding time window is then applied for adaptive processing, yielding the transformed signal. Finally, the transformed signals from multiple trials are averaged to generate a template for each character. Results based on a publicly available neural signals dataset for imaginary handwriting indicate that, compared with mainstream time warping models such as Shift, Linear, Piecewise, and TWPCA, the proposed model improves the character decoding accuracy for 31 characters by 14%, 13%, 7%, and 2%, respectively. This study not only constructs effective character signal templates but also facilitates accurate character segmentation during unlabeled imagined typing in an offline setting, providing a promising methodological basis for future real-time imagined typing decoding systems. Full article