Search Results (1,246)

The practical application of Brain–Computer Interface (BCI) technology is frequently challenged by significant inter-individual variability in electroencephalogram (EEG) signals. This variability makes it extremely difficult to decode the brain activity of new subjects using pre-recorded data from previous subjects. To address these issues, this study presents an EEG decoding approach based on four-stage domain generalization. We start by preprocessing the data and then dividing it into source and target domains. The source domain data are then passed through four sequential modules: Feature Extraction, Feature Augmentation, Feature Optimization, and Domain Adaptation, where we adjust the parameters using the source domain loss function. Next, the target domain data go through the same four stages while we fine-tune the parameters together with the domain adaptation loss, ultimately obtaining the decoding results for the target domain. The proposed method achieves the highest classification accuracy of 72.61%, outperforming EEGTransferNet by 7.22% and surpassing all classical and deep learning baselines by improvements ranging from 5.97% to 23.86%. Overall, the proposed method significantly enhances cross-subject generalization in motor imagery decoding, offering practical value for plug-and-play BCI applications. Full article

Soft robotics enables inherently safe, compliant interaction, yet integrating brain–computer interfaces (BCIs) remains hindered by a fundamental mismatch: BCIs typically output low-bandwidth, discrete commands, whereas soft robots possess high-dimensional, nonlinear dynamics. In this position paper, we argue that BCI–soft robot integration must move beyond direct decoder-to-actuator mapping. We propose a unified, application-oriented compatibility framework that structurally decouples hierarchical control and formally allocates authority between human neural input and local soft robotic autonomy. Crucially, we introduce verifiable, quantitative design principles that define integration as a matching problem across neural bandwidth, update frequency, latency tolerance, and control dimensionality. Through these testable hypotheses, we demonstrate that active, reactive, and passive BCIs serve distinct, complementary roles. We conclude that shared-control strategies—where the BCI provides high-level intent, target selection, or user-state feedback, while the soft robot manages low-level physical execution and interaction—offer the most practical pathway forward. We argue that future progress depends on the co-design of paradigm, decoding, control, and embodiment for neuro-adaptive and human-centred soft robotic systems. Full article

Improving the decoding accuracy and information transfer rate (ITR) of steady-state visual evoked potential brain–computer interface (SSVEP-BCI) systems, while enhancing cross-subject generalization and reducing calibration cost, is essential for practical deployment. This study proposes an end-to-end framework that integrates adaptive filtering with semi-supervised domain adaptation. The framework incorporates a Gabor adaptive filter bank (G-AFB) to optimize time–frequency representations and extract features matched to individual neural responses. It also introduces a three-stage semi-supervised domain-adversarial neural network (TriS-DANN), which combines unsupervised pre-alignment and supervised fine-tuning to align cross-subject feature distributions and enable lightweight calibration. On the 1.0 s public benchmark dataset, G-AFB-tCNN achieved 89.13% accuracy, a 4.63 percentage-point improvement over its conventional filter-bank counterpart. On the 0.4 s in-house dataset, G-AFB-tCNN achieved 91.85% accuracy, a 3.22 percentage-point improvement over the conventional fixed filter bank. In transfer learning, TriS-DANN reached 86.60% accuracy using 0.4 s segments extracted from the stimulation period and only 23.07% of the available target-domain training/calibration trials, demonstrating higher efficiency and stability than conventional fine-tuning. These results support the proposed framework as a feasible route toward reliable, low-calibration SSVEP-BCI systems. Full article

Steady-state visual evoked potential-based brain–computer interfaces (SSVEP-BCIs) are widely applied in non-invasive brain–computer interaction, yet traditional single-frequency coding suffers from scarce frequency resources and degraded accuracy in multi-target tasks. The partitioned backlight mode (PB-M) supports SSVEP spatial coding, while systematic investigations on its inherent backlight crosstalk are still lacking. This study develops a PB-M-based SSVEP-BCI system to explore crosstalk mechanisms. Each participant completed 90 valid trials with 18 stimuli and five repetitions each. The results verify inter-partition crosstalk, which can reduce recognition accuracy under narrow frequency intervals and non-isolated layouts, and gaze position can modulate non-target SSVEP responses. Classification accuracy was calculated by valid correct trial ratios, and the information transfer rate (ITR) was computed using standard BCI formulas, yielding 87.50% accuracy and 48.75 bits/min ITR. Full exhaustive classification testing across all 18 stimulus targets was not implemented, where core classification validation was performed on partially selected targets. The proposed frequency reuse strategy shows promising potential to improve SSVEP-BCI performance based on empirical experimental data, providing valid references for multi-target BCI design. Full article

Emotion recognition through electroencephalogram (EEG) signals is crucial for brain–computer interfaces (BCIs), yet existing methods often struggle with heterogeneous feature fusion and capturing long-range temporal dependencies. To address these challenges, we propose MAF-TransNet, a novel unified spatiotemporal framework. Specifically, parallel Fully Connected Neural Network (FCNN) modules first non-linearly align heterogeneous differential entropy (DE) and power spectral density (PSD) features. Subsequently, an Adaptive Channel-wise Feature Encoder (ACFE) recalibrates spatial–spectral responses to highlight emotion-relevant cortical activations. Finally, a Transformer encoder dynamically models the global temporal evolution of emotional states. Evaluated on the SEED-IV and DEAP datasets, MAF-TransNet achieves superior subject-dependent (SD) accuracies of 88.80% and 96.58%, respectively, alongside robust subject-independent (SI) performance. Furthermore, Granger causality analysis reveals distinct emotion-dependent prefrontal asymmetry, while t-SNE visualizations confirm the formation of a highly discriminative, linearly separable feature manifold. Ultimately, MAF-TransNet effectively unifies local spatial–spectral extraction with global temporal modeling, providing an accurate and robust approach, while offering preliminary insights into the spatiotemporal dynamics of emotion for future affective BCI applications. Full article

Real-time physiological state awareness is central to next-generation wearable computing, yet most existing electrophysiological signal acquisition platforms remain limited to single-modality sensing, high component cost, or bulky form factors that hinder everyday deployment. Here, we present a compact, low-cost wearable platform for simultaneous electroencephalography (EEG), electromyography (EMG), and electrocardiography (ECG) acquisition. The system integrates an analog front-end, a microcontroller, and a Bluetooth wireless link on a compact single-board platform (5.6 × 3.8 cm, approximately 12.8 g with the selected lithium-polymer battery installed), with an estimated bill-of-materials cost of 67.40 USD. Experimental validation across three healthy subjects, with the ECG channel additionally benchmarked against a commercial clinical-grade ambulatory ECG recorder, demonstrates that the platform captures ECG waveforms with recognizable P-QRS-T morphology under controlled recording conditions, supports reliable R-peak detection and heart rate estimation, records stable resting-state EEG spectral features, and distinguishes EMG activation from resting baseline in both time-domain amplitude and time-frequency structure. Leveraging the real-time wireless data link between the wearable hardware and a PC-hosted MATLAB environment, we further explore application-oriented signal processing scenarios. As an offline algorithm-pipeline compatibility demonstration, a CNN-based seizure detection pipeline is applied to the Bonn EEG benchmark for five-class epileptic state classification, achieving 86.60% mean classification accuracy. The proposed system offers a scalable and affordable foundation for wearable human-state-aware interaction, with potential applications in clinical monitoring, rehabilitation, and brain–computer interfaces. Full article

A brain–computer interface (BCI) is a complex system that allows humans to interact with physical devices by analysing and interpreting brain signals obtained from neuroimaging modalities (electroencephalography, electrocorticography, magnetoencephalography, intracortical neuron recording, functional magnetic resonance imaging, etc.). BCI applications in robotics and medicine have demonstrated invaluable benefits. The rise of BCI technology and neuroergonomics techniques could also provide promising solutions in transportation systems, particularly in smart roads, vehicles, and traffic regulation systems. This narrative literature review examines how, in the age of smart transportation systems and self-driving vehicles, different far-future applications of BCI systems could be integrated to enhance the safety and capacity of transportation systems. Full article

Nanobiosensors, with their unique physicochemical properties, are transformative tools for diagnosing and monitoring neurodegenerative diseases and mental disorders. This article systematically reviews the latest progress of nanomaterial systems and integrated sensing modalities in neurological disease diagnosis. First, we clarify the multiple functional roles of nanomaterials in biosensors, including signal amplification, interface optimization, and spatial positioning, and compare the applicable scenarios of various sensing principles based on different nanomaterials. Second, we evaluate the design and integration strategies of molecular recognition elements (antibodies, nucleic acid aptamers, molecularly imprinted polymers, and CRISPR-Cas systems) and discuss their synergistic integration mechanisms for improving detection performance. In terms of detection targets, we focus on three applications: high-sensitivity quantification of established protein biomarkers, real-time monitoring of dynamic neurochemicals (dopamine, serotonin, glutamate), and emerging liquid biopsy targets such as exosomal cargo and circulating microRNAs. Finally, to address the core challenges of biofouling, sensitivity–selectivity trade-offs, and multiplex detection in complex matrices, we propose three breakthrough directions for next-generation diagnostics: deep integration of multimodal and multiplexing platforms, closed-loop chemical brain–computer interfaces (cBCIs), and AI-driven predictive diagnostic models, collectively enabling a transition from passive detection to active sensing and intervention for precise, rapid, and non-invasive neurological disease management. Full article

Electroencephalography (EEG) offers a noninvasive, high-temporal-resolution modality for estimating mental workload. However, session-to-session variability limits the generalizability of workload classifiers, and few systematic cross-session evaluations are reported in the literature. This study systematically evaluates domain adaptation methods for cross-session mental workload classification using the publicly available COG-BCI dataset within an evaluation framework that may guide future studies on EEG-based classification models. We make four contributions: (i) integration of Optimal Transport (OT) with Graph Neural Networks (GNNs) to model spatial relationships and align feature distributions under strict session-wise separation; (ii) a data-centric evaluation pipeline incorporating Self-Organizing Map (SOM) visualizations for data exploration and a heuristic loss function for model selection; (iii) a strict cross-session protocol examining the effects of graph construction, feature selection, and data splits; and (iv) comparison of OT with CORrelation ALignment (CORAL) and GNN with EEGNet. Incorporating OT improved test accuracies across all experimental configurations. SOM visualizations confirmed enhanced feature alignment after OT. Our results highlight the potential of OT for mitigating session-to-session variability and underscore the importance of a data-centric approach and rigorous cross-session evaluation when developing classifiers for complex cognitive state estimation. Future work should explore semi-supervised OT strategies and scalable implementations for real-time applications. Full article

Conventional P300-based brain–computer interfaces (BCIs) commonly rely on two-dimensional (2D) visual flashing, which may induce visual fatigue and limit immersion, thereby restricting long-term usability and system performance. To address these limitations, this study proposes an immersive P300-BCI framework integrating a three-dimensional morphological stimulation paradigm, termed 3D-Morph, with self-adaptive Bayesian linear discriminant analysis (SA-BLDA). Instead of using color or luminance flickering, the proposed paradigm employs dynamic 2D-to-3D morphological transformations of virtual objects in a virtual reality environment to enhance target-related event-related potentials while preserving visual immersion. SA-BLDA further adjusts the number of stimulation rounds according to classification confidence to balance accuracy and interaction efficiency. Experiments with 24 participants showed that the proposed system outperformed the conventional 2D paradigm. In offline analysis, the proposed method achieved an average classification accuracy of 94.17% and an information transfer rate (ITR) of 25.50 bits/min, significantly outperforming the 2D paradigm (87.29% accuracy, 22.75 bits/min ITR, both $p<0.001$, Cohen’s $d\ge 1.22$). In online experiments, the 3D-Morph paradigm achieved an average accuracy of 91.46% and an ITR of 37.23 bits/min, compared with 83.96% and 28.74 bits/min for the conventional 2D paradigm (both $p<0.01$, Cohen’s $d\ge 1.14$). The average response time was reduced by 0.46 s ($p<0.01$, Cohen’s $d=0.78$), and the processing time per stimulation round (PT) of SA-BLDA was significantly reduced from $48.54\pm 10.47$ ms in the 2D paradigm to $26.40\pm 9.41$ ms in the 3D-Morph paradigm ($p<0.01$, Cohen’s $d=2.34$), corresponding to a 45.61% reduction in computational time per round. NASA-TLX evaluations indicated a significantly lower subjective workload across all dimensions (all $p<0.05$, Cohen’s $d\ge 0.76$). These results demonstrate that combining 3D-Morph stimulation with SA-BLDA can significantly improve classification performance, interaction efficiency, and user experience, providing a feasible framework for immersive and practical P300-BCI applications. Full article

Fatigue monitoring and detection are crucial for improving efficiency and safety due to their influence on reducing cognitive and physical performance that may result in safety-related incidents. This paper proposes a filter bank-based approach that decomposes electroencephalography (EEG) signals into delta, theta, alpha, beta, and gamma sub-bands for feature extraction to enhance fatigue detection using a wearable EEG-based brain–computer interface (BCI). The study utilized a publicly available EEG dataset from 40 participants collected with a dry-EEG headband while performing two cognitive tasks: a Cognitive Vigilance Task (CVT) and a Multi-Modal Integration Task (MMIT). The data was previously investigated for stress detection on the MMIT. In this study, we investigate fatigue detection on the CVT. Subjects who were not fatigued post-CVT were iteratively removed. Two models were trained with five models to classify the fatigued state from the non-fatigued state, one using features extracted from a broadband filter approach and the other from the proposed filter bank approach. Leave-one-subject-out cross-validation yielded accuracies of 75.8% $\pm$10.4% (95% confidence interval) from the broadband filter approach, and 86.4% $\pm$8.3% (95% confidence interval) from the proposed filter bank approach, yielding an overall increase of 10.6%. These results demonstrate the potential of filter bank-based feature extraction for fatigue detection in wearable EEG-based BCI systems. Full article

Motor imagery brain–computer interfaces (MI-BCIs) have important applications in neurorehabilitation, assistive communication, and non-muscular human–machine interaction. From a bionic neural-interfacing perspective, MI-BCI decoding provides a computational bridge between biological motor intention and external machine control. However, reliable motor imagery electroencephalography (MI-EEG) classification remains challenging due to the highly non-stationary features of MI-EEG and limited interpretability. In this work, we propose PG-MCTFormer, a prior-guided multi-scale convolutional Transformer for MI-EEG classification that integrates rhythm-aware temporal filtering, dual-scale spatial modeling, and contextual decoding within a unified architecture. We evaluated the model on the publicly available BCI Competition IV 2a dataset, achieving 85.08% average accuracy and a Cohen’s kappa of 0.80, with significant performance improvement over the traditional methods. Comprehensive multi-view interpretability analyses in the frequency, temporal, and spatial domains further show that the learned filters remain aligned with canonical MI-related bands, discriminative evidence concentrates in the middle-to-late imagery interval, and the spatial prior is refined into subject-adaptive sensorimotor topographic patterns. These results indicate that explicit neurophysiological priors can improve both the robustness and the interpretability of MI-EEG decoders for biomimetic neural-interface applications. Full article

Background: Spiking neural networks (SNNs) have attracted significant attention in the field of brain–computer interfaces owing to their distinctive biological plausibility and energy efficiency advantages. However, the discrete nature of spikes renders gradient-based differentiation infeasible, making it difficult to directly obtain well-trained SNNs. A common approach is to transfer the weights from artificial neural networks (ANNs) to SNNs. However, this process introduces conversion errors that pose significant challenges. Methods: To address these challenges, we propose the self-rectifying integrate-and-fire (SRIF) neuron, which employs negative spikes to reduce asynchronism error and rectification spikes to diminish clipping error. Concomitantly, we propose a collaborative trim (CT) training framework that introduces a quantized network to perceive the weights and results of SNNs, which can further improve performance. Result: The proposed training methodology enables SNNs to achieve performance metrics comparable to those of ANNs in EEG-based motor imagery (MI) classification. Conclusions: Experimental results demonstrate that our method not only preserves the superior classification performance of ANNs but also leverages the superior energy efficiency and lower computational complexity of SNNs. Full article

Background: Vascular cognitive impairment (VCI) is a common consequence of cerebrovascular diseases and significantly affects multiple cognitive domains. Brain–computer interface (BCI) technology has emerged as a promising tool for cognitive assessment and rehabilitation in patients with VCI. This systematic review examined the current applications of BCI technology for cognitive function in patients with VCI. Methods: In accordance with the PRISMA 2020 guidelines, we searched Medline, PubMed, Web of Science, Embase, and the Cochrane Central Register of Controlled Trials. We included studies published between January 2000 and March 2026 that evaluate BCI for cognitive function in patients with VCI. Results: A total of 30 studies were included in the review. The participants comprised 696 stroke patients, 71 patients with early cerebral microangiopathy and 128 patients with VCI and no dementia. In patients with VCI, BCI interventions combined with other technologies (e.g., exoskeleton, virtual reality, functional electrical stimulation, acupuncture, or game-based cognitive training) appeared more effective for cognitive rehabilitation than BCI alone. Attention was the most consistently improved domain among the studies reviewed. Global cognitive function also improved in many studies, though not uniformly. Memory, executive function, and language outcomes varied depending on factors such as intervention protocols, training duration, and assessment tools. Conclusions: BCI is a promising tool for cognitive assessment and rehabilitation in patients with VCI. However, substantial heterogeneity across studies limits the conclusions. Future large-scale, well-designed randomized controlled trials with standardized outcome measures are needed to validate the efficacy of BCI technology and to explore its underlying mechanisms. Full article

Brain–computer interface (BCI) systems aim to establish direct communication pathways between neural activity and external devices, enabling interaction without relying on conventional neuromuscular mechanisms. This study investigates the feasibility of decoding binary decisions (“Yes”/”No”) from self-generated cognitive–emotional modulation patterns using a single-channel low-cost EEG device. The proposed approach evaluates whether internally generated modulation strategies can produce distinguishable neural activity suitable for BCI applications under constrained acquisition conditions. EEG signals were recorded from two participants using a consumer-grade headset while they responded to questions through intentional internal modulation associated with affirmative and negative responses. The recorded signals were preprocessed, and multiple feature representations were extracted, including raw temporal data, cepstral coefficients, spectral power, and continuous wavelet transform (CWT) features. Several machine learning and deep learning models, including convolutional neural networks (CNN), long short-term memory networks (LSTM), and support vector machines (SVM), were trained and evaluated using hold-out and stratified k-fold validation strategies. The best performance was achieved by a CWT-based CNN model, reaching an average accuracy of 80.5%, significantly above chance level. Additional models, including CEP-CNN and RAW-LSTM, achieved competitive results, highlighting the relevance of feature representation in EEG-based classification tasks. The results demonstrate that internally generated modulation patterns can produce distinguishable EEG responses, even when using low-cost single-channel hardware. Although the limited number of participants constrains statistical generalization, this work serves as a proof-of-concept and provides a reproducible experimental pipeline for future studies. Overall, the findings support the development of accessible, scalable, and user-centered BCI systems based on internally generated neural modulation strategies, contributing to more natural interaction paradigms in EEG-based communication systems. Full article