Search Results (804)

To address the inherent limitations in the robustness of fully autonomous unmanned aerial vehicle (UAV) visual perception and the high cognitive workload associated with manual control, this paper proposes a human-in-the-loop brain–computer interface (BCI) control framework. The system integrates steady-state visual evoked potential (SSVEP) with deep learning techniques to create a spatio-temporally dynamic interaction paradigm, enabling real-time alignment between visual targets and frequency stimuli. At the perception level, an enhanced YOLOv11 network incorporating partial convolution (PConv) and shape intersection over union (Shape-IoU) loss is developed and coupled with the DeepSort multi-object tracking algorithm. This configuration ensures high-speed execution on edge computing platforms while maintaining stable stimulus coverage over dynamic targets, thus providing a robust visual induction environment for EEG decoding. At the neural decoding level, an enhanced task-discriminant component analysis (TDCA-V) algorithm is introduced to improve signal detection stability within non-stationary flight conditions. Experimental results demonstrate that within the predefined fixation task window, the system achieves 100% success in maintaining target identity (ID). The BCI system achieved an average command recognition accuracy of 91.48% within a 1.0 s time window, with the TDCA-V algorithm significantly outperforming traditional spatial filtering methods in dynamic scenarios. These findings demonstrate the system’s effectiveness in decoupling human cognitive intent from machine execution, providing a robust solution for human–machine collaborative control. Full article

Cognitive stress, also known as mental workload, constitutes a central topic within the field of psychophysiology due to its role in modulating attention, autonomic regulation, and stress reactivity. Furthermore, it bears direct relevance to practical monitoring systems that employ non-invasive sensing techniques. This study investigates whether a multimodal, non-invasive measurement setup can detect systematic physiological differences between Resting periods and short episodes of cognitive load within the same individuals. Additionally, it explores the capacity of such a system to differentiate tasks characterized by varying cognitive demands. A sequential, within-subject protocol was employed, comprising five consecutive phases (rest 1, Stroop, rest 12, subtraction, rest 3), during which five modalities were recorded concurrently: EEG, heart rate (HR), galvanic skin response (GSR), facial surface temperature, and oxygen saturation (SpO₂). Beyond phase-wise inspection of time-series data, an exploratory assessment of similarity across participants was conducted using correlation coefficients. The maximum cross-participant correlations observed were 0.88 (HR), 0.90 (GSR), 0.83 (facial temperature), and 0.77 (SpO₂); however, these correlations were used only as exploratory descriptors of inter-individual similarity and did not imply a significant phase effect. For inferential analysis, phase-wise epoch means were evaluated through one-factor repeated-measures ANOVA. The heart rate exhibited a robust main effect of phase (F(4, 32) = 10.5862, p_GG = 0.01044, ηp² = 0.5696), with higher HR observed during cognitive load epochs (e.g., 77.841 ± 11.777 bpm at rest 1 versus 83.926 ± 14.532 bpm during subtraction). The relatively large standard deviation reflects variability between subjects rather than variability within epochs. Regarding processed baseline-referenced GSR, the omnibus phase effect was not statistically significant under the conservative Greenhouse–Geisser correction; therefore, GSR was interpreted as exploratory in this dataset. Facial temperature and SpO₂ likewise did not show statistically significant omnibus phase effects under Greenhouse–Geisser correction (e.g., SpO₂: p_GG = 0.1209). EEG-derived measures provide supplementary central evidence of task engagement; entropy variations within an approximate dynamic range of 0.2 to 0.8 were observed, and the α/θ ratios demonstrated nearly a twofold distinction between rest and cognitive load epochs across different leads. Full article

Functional near-infrared spectroscopy (fNIRS) is a valuable non-invasive modality for brain-computer interfaces (BCIs), but robust signal interpretation is challenged by the significant temporal variability of the hemodynamic response. Standard linear methods, such as Pearson correlation, often fail to capture functional connectivity when signals exhibit temporal jitter. This study validates an unsupervised Dynamic Time Warping (DTW) clustering framework to robustly identify motor networks from fNIRS data by accommodating non-linear temporal shifts. We analyzed a public fNIRS dataset (N = 30) across right-hand (RHT), left-hand (LHT), and foot tapping (FT) tasks. A robust preprocessing pipeline was implemented, including Wavelet Motion Correction and Common Average Referencing (CAR) to remove artifacts and global systemic noise. The core method involved computing Z-score normalized DTW distance matrices, followed by hierarchical clustering. To validate the framework, we benchmarked it against a standard Pearson Correlation method. Results show that the unsupervised DTW framework achieved a network identification accuracy of 53.17%, significantly outperforming the standard Pearson correlation benchmark (48.06%) with a statistically significant difference (p < 0.05). The framework successfully detected distinct, somatotopically correct modulations: superior-medial activation during foot tapping and lateralized activation during hand tapping. These findings demonstrate that unsupervised DTW clustering is a robust, data-driven approach that outperforms conventional linear methods in capturing functional networks during motor tasks, showing significant potential for next-generation asynchronous BCIs. Full article

Brain–computer interfaces (BCIs) have great potential for consumer electronics, as they enable the decoding of brain activity to control external devices and assist human–computer interaction. However, current decoding methods for BCIs face several challenges, such as low accuracy, poor stability under electrode shift, and slow processing for real-time use. In this paper, we propose a hybrid decoding framework designed to address the challenges of current EEG decoding methods. Our method combines manifold learning with contrastive learning. The core of our method lies in a dual-manifold model that uses non-negative matrix factorization (NMF) and a contrastive manifold learning framework to extract clear and useful features from brain signals. To improve decoding stability, we introduce a joint training strategy that enhances feature learning. Furthermore, the system is optimized for real-time interaction, reducing the system latency to 100 ms. We collect EEG signals from 15 subjects performing motor execution tasks and 10 subjects performing motor imagery tasks to construct a motor EEG dataset. On this dataset, the proposed method achieves superior decoding performance, reaching F1-scores of 0.7382 for the motor imagery tasks and 0.8361 for the motor execution tasks. Furthermore, the method maintains robustness even with reduced electrode counts and altered spatial distributions, highlighting its potential as a decoding solution for reliable and portable BCI systems. Full article

Auditory Brain–Computer Interfaces (BCIs) constitute the vital intervention for profound sensorineural hearing loss where the auditory nerve is compromised, yet their clinical efficacy remains restricted by substantial biological bottlenecks and limited spectral resolution. This review critically examines the evolutionary paradigm of auditory restoration, tracing the transition from static physical replacement to dynamic biological symbiosis. We systematically analyze physiological barriers across cochlear, brainstem, and cortical levels, elucidating how rigid interfaces provoke chronic tissue responses and why linear encoding protocols fail in distorted central tonotopy. The article synthesizes emerging methodologies in material science, demonstrating how soft, bio-integrated electronics and biomimetic topologies effectively address mechanical impedance mismatches. Furthermore, the trajectory of neural encoding is evaluated, highlighting the paradigm shift from traditional envelope extraction to deep learning-driven non-linear mapping and adaptive closed-loop neuromodulation. Finally, the potential of high-resolution modulation techniques, including optogenetics and sonogenetics, alongside AI-facilitated intent perception for active listening, is assessed. It is concluded that future neuroprostheses must evolve into symbiotic systems capable of seamlessly integrating with neural plasticity to enable high-fidelity cognitive reconstruction. Full article

We classified essential motor actions, dorsal and plantar flexion (lower limb), and arm movement (upper limb) from electroencephalography (EEG)-based brain–computer interface (BCI) signals, using a convolutional neural network (CNN). Different from previous research on upper or lower limb motor imagery in isolation, we integrated both categories in a unified framework to explore a broader range of movements for broader applications. These motor actions are fundamental to daily activities such as walking, running, maintaining balance, lifting, reaching, and exercising. Upper limb EEG data were provided by INTI International University, whereas lower limb data were obtained from a publicly available dataset, recorded using 16-channel Emotiv and OpenBCI systems, respectively, each with distinct sampling rates and signal formats. To improve signal quality and facilitate joint model training, all signals were downsampled to 125 Hz, standardized to 16 channels, segmented using sliding windows, normalized via StandardScaler, and labelled according to action class. The processed data were used to train a CNN model configured with a kernel size of 3 and rectified linear unit activation functions. Training was terminated early at epoch 11 using an early stopping strategy, resulting in approximately 67% accuracy for both training and validation sets. Although this accuracy was moderate for deep learning, a promising outcome for EEG-based multi-class motor imagery classification was obtained, with the challenges posed by limited data availability, low inter-class feature discriminability, and the inherently noisy nature of non-invasive EEG signals. The results of this study underscore the potential of CNN-based models for future real-time BCI applications. By expanding the dataset, deep learning architectures can be refined to improve signal preprocessing techniques. Prosthetic devices need to be integrated to validate the system in practical scenarios. Full article

Motor imagery (MI) EEG classification is a key component of noninvasive brain–computer interfaces (BCIs) and often must satisfy strict latency constraints in online or edge deployments. Although ensembling can reliably improve MI decoding accuracy, its inference cost grows linearly with the number of ensemble members, making it impractical for low-latency applications. To address these issues, we propose an entropy-based dual-teacher distillation framework that transfers ensemble teacher knowledge to a single deployable backbone. From an information theoretic perspective, two failure modes are common in small and noisy MI datasets: elevated predictive entropy (noisy decisions) and large fluctuation across late training epochs (unstable convergence and unreliable checkpoint selection). Thus, we introduce an exponential moving average (EMA) teacher with entropy-gated activation as a low-pass filter in parameter space to reduce the student’s prediction noise. In addition, a two-stage cosine annealing schedule is employed to suppress late-stage oscillations and improve the robustness of final checkpoint selection. Experiments on two public MI benchmarks (BCI Competition IV-2a and IV-2b) with three representative backbones (EEGNet, ShallowConvNet, and ATCNet) under the subject dependent protocol show consistent accuracy gains over the ensemble teacher and strong distillation baselines. On IV-2a, our method achieves an average accuracy of 0.7713 across the backbones, surpassing both the original models (0.7222) and the corresponding ensembles (0.7482); on IV-2b, it achieves 0.8583 versus 0.8432 (original) and 0.8529 (ensemble). Full article

This study investigates whether inter-channel similarity, quantified using Pearson’s correlation, can be used as an indicator of electrode relevance in electroencephalography (EEG)-based motor imagery (MI) classification and compares this approach with a genetic algorithm (GA)-based electrode selection strategy. Electrode subsets were obtained using Pearson correlation ranking, a GA optimizing classification accuracy, and the reference-study electrode subset reported in prior work. All subsets were evaluated on the BCI Competition IV Dataset 2a using a unified classifier architecture, and the sensitivity to classifier hyperparameter configuration was analyzed. Pearson-based selection achieved accuracies of 75.8% (8 channels), 78.1% (10 channels), and 81.5% (12 channels), while the GA achieved 75.9% (8 channels), 78.8% (10 channels), and 80.0% (13 channels). The reference-study electrode subset reached 75.0% (8 channels) and 76.7% (10 channels). Although correlation-based selection yielded competitive performance, no consistent relationship was observed between inter-channel similarity and discriminative relevance, and classification performance showed notable sensitivity to hyperparameter settings. These findings indicate that inter-channel similarity alone is not sufficient to determine electrode importance in MI classification and support the use of data-driven, model-aware selection strategies for the design of efficient low-channel-count brain–computer interface systems. Full article

Spontaneous intracerebral hemorrhage (ICH) is associated with substantial mortality and morbidity. Current management paradigms rely heavily on the rapid interpretation of neuroimaging and clinical data, yet are frequently constrained by limitations in processing speed, diagnostic accuracy, and prognostic precision. Artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), offers transformative potential to circumvent these challenges across the entire continuum of ICH care. This comprehensive review synthesizes the rapidly evolving landscape of AI applications in ICH management. Through a systematic evaluation of recent literature, we examine studies focused on the development, validation, or critical appraisal of AI-driven technologies for ICH care. Our analysis encompasses automated neuroimaging, computer-assisted surgical navigation, brain–computer interfaces (BCIs), prognostic modeling, and fundamental research into disease mechanisms. AI has demonstrated performance comparable to that of clinical experts in automating hematoma segmentation, predicting complications such as hematoma expansion, and refining surgical planning via augmented reality. Furthermore, BCIs present innovative therapeutic avenues for motor rehabilitation. However, the translation of these technological advances into routine clinical practice is impeded by substantial challenges, including data heterogeneity, model opacity (“black-box” issues), workflow integration barriers, regulatory ambiguities, and ethical concerns surrounding accountability and algorithmic bias. The integration of AI into ICH care signifies a paradigm shift from standardized treatment protocols toward dynamic, precision medicine. Realizing this vision necessitates interdisciplinary collaboration to engineer robust, generalizable, and interpretable AI systems. Key priorities include the establishment of large-scale multimodal data repositories, the advancement of explainable AI (XAI) frameworks, the execution of rigorous prospective clinical trials to validate efficacy, and the implementation of adaptive regulatory and ethical guidelines. By systematically addressing these barriers, AI can evolve from a mere analytical tool into an indispensable clinical partner, ultimately optimizing patient outcomes. Full article

High-resolution, multi-modal neural interfaces are essential for advancing systems neuroscience and brain–computer interface technologies. This study designed and fabricated a 128-channel comb-shaped flexible micro-electrode array. The device integrates a biocompatible Parylene substrate with a flexible thin-film microprobe array, enabling simultaneous recording of electrocorticography (ECoG), intracortical local field potentials (LFP), and neuronal action potentials (spikes) from the cortical surface and superficial layers. Microelectrode sites were modified with platinum black nanoparticles, significantly reducing impedance. In vivo experiments in rats demonstrated the array’s ability to capture high-fidelity signals across different recording depths. Key findings included the acquisition of opposing LFP trends and polarity reversals between adjacent channels, reflecting local microcircuit dynamics. The array also reliably recorded neural activity during audiovisual cross-modal sensory stimulation. These results validate the device as an effective tool for multi-scale electrophysiology, successfully balancing high spatial resolution and signal quality with minimal tissue invasiveness, thereby offering significant potential for fundamental research and neural engineering applications. Full article

Background and Objectives: Attention-Deficit Hyperactivity Disorder (ADHD) is a neurological condition characterized by cognitive task difficulty, impulsivity, hyperactivity and loss of attention. This study compared four approaches for improving attention and related skills in school-age children: COGO Brain–Computer Interface (BCI)-based attention training, methylphenidate, citicoline, and their combined use. Materials and Methods: A quasi-experimental pre–post design was used with four groups: COGO + methylphenidate (n = 44), COGO + citicoline (n = 44), COGO-only (n = 44), and citicoline-only (n = 42). Children completed baseline and post-treatment assessments, including the CPT-3 and several behavioral and emotional rating scales. Analyses included paired t-tests, ANCOVA, and repeated-measures ANOVA, adjusting for age. Results: The strongest improvements appeared in the COGO + methylphenidate group, especially in measures of sustained attention and reaction time consistency. The COGO + citicoline group showed clearer gains in inhibitory control (fewer commission errors) and reductions in anxiety/emotional symptoms. The COGO-only and citicoline-only groups showed little to no measurable change. Despite these within-group patterns, there were no significant differences between groups on CPT-3 outcomes or behavioral/emotional scales. Conclusions: This trial showed that combining COGO-based attention training with medication is both feasible and well-tolerated in children with attention and executive function difficulties. Moreover, the integrated approach produced measurable improvements across attentional performance and behavioral regulation domains. Full article

Stroke-induced hand motor dysfunction severely limits activities of daily living (ADL). While conventional systems face challenges in portability and sustained actuation accuracy, this work addresses these limitations through an integrated adaptive control framework and a lightweight 10-degrees-of-freedom (DoFs) tendon-driven exoskeleton. The system employs a rigid–flexible coupling design with a wearable mass under 300 g, ensuring compatibility across various finger lengths. The system is implemented via a motor imagery-based brain–computer interface (MI-BCI); by processing 64-channel electroencephalogram (EEG) signals, the system adaptively maps motor intent into three discrete grasp intensity levels (20%, 50%, and 80% maximum voluntary contraction). To reduce cognitive load and enhance system stability during rehabilitation, we propose a novel “Force–Topology Coupling” control paradigm. This paradigm functions as a synergistic filter, leveraging the correlation between intended effort level (IEL) and grasp taxonomy to map intensity levels to ADL-specific grasps (lateral, precision, and power). Validation with healthy subjects demonstrated 0° to 90° joint mobility and the successful execution of 9 ADL tasks. The results verify the efficacy of utilizing adaptive MI-BCI modulation to trigger biomechanically precise assistance, establishing a foundational computational paradigm with significant potential for clinical stroke rehabilitation. Full article