Search Results (71)

Among the various brain–computer interface (BCI) modifications used in post-stroke rehabilitation, BCI systems combined with functional electrical stimulation (FES) are considered the most effective. As a preliminary step toward optimizing such systems for clinical application, it remains unclear whether using electroencephalography (EEG) alone versus a hybrid EEG and functional near-infrared spectroscopy (fNIRS) approach affects real-time three-class BCI–FES control performance in healthy individuals. In a blind randomized study, 16 healthy volunteers completed five BCI–FES training sessions across three days. In one group, FES of wrist extensor muscles was driven by a hybrid EEG–fNIRS classifier; in the other, by EEG only. Classification accuracy, sense of agency, attention, and physical comfort were assessed. No statistically significant between-group differences were found in any outcome measure (p > 0.05). Median real-time three-class classification recall was 53.5% in the hybrid group and 57.3% in the EEG-only group. The median agency score reached approximately 75% of the maximum possible value in both groups. Simulation analysis showed comparable accuracy for unimodal fNIRS-only and EEG-only classifiers. Genetic algorithm-based channel selection identified C3 and C4 as the most informative EEG channels, while optimal fNIRS placement required individual optimization. Within the constraints of the classification and fusion pipeline used here, these findings suggest that signal acquisition modality does not significantly influence BCI–FES performance or sense of agency in healthy subjects. The complete EEG–fNIRS dataset is publicly available through NITRC. Full article

This structured critical review examines wearable brain–computer interface (BCI) systems that integrate electroencephalographic (EEG) and electromyographic (EMG) signals for post-stroke motor rehabilitation. The central engineering problem is the spatio-temporal heterogeneity between cortical and muscular signals, which limits the reliability and generalizability of conventional EEG–EMG fusion. We review acquisition and synchronization methods, data-, feature-, and decision-level fusion, deep-learning architectures, wearable implementation, and clinically oriented closed-loop rehabilitation. Conventional fusion can exploit complementary information but usually treats the cross-modal relationship as fixed. By contrast, dynamic brain–muscle coupling is defined here as the explicit, time-resolved estimation of interaction strength, delay, directionality, or network topology between cortical regions and target muscles. Measurable candidates include time-resolved corticomuscular coherence, phase locking, lagged dependence, information-theoretic directionality, and dynamic graph connectivity. Coupling-aware and graph-based methods are promising, but clinical translation remains constrained by artifacts, inter-subject and cross-session variability, overfitting, limited clinical datasets, interpretability, synchronization error, and embedded-computing requirements. The review therefore proposes a transparent pathway from static signal stacking toward physiologically grounded, dynamically coupled, and adaptively controlled rehabilitation systems. Full article

Population aging and the rising prevalence of motor disorders are driving demand for assistive lower-limb robotic systems capable of decoding user intention rather than merely providing mechanical support. We present CM-FuseNet, an attention-augmented hybrid Brain–Computer–Muscle Interface (BCMI) that simultaneously fuses cortical concentration indices extracted from electroencephalography (EEG) and lower-limb intention patterns derived from electromyography (EMG) to adaptively control a 4-DOF assistive lower-limb exoskeleton. To eliminate the burden of human-subject ethics review and to ensure reproducibility of the proposed methodology, all validation is performed exclusively on (i) permissively licensed open-access biomedical datasets, (ii) high-fidelity OpenSim 4.5 and MuJoCo 3.1 musculoskeletal–exoskeleton co-simulation, and (iii) limited self-experimentation by the corresponding author with non-invasive consumer-grade devices. Three components are introduced: (i) a log-tanh normalized concentration index CI in (0, 1) derived from the $(P_{SMR}+P_{Mid-Beta})/P_{Theta}$ ratio; (ii) a bidirectional Cross-Modal Transformer (CMT) with eight-head self- and cross-attention; and (iii) a Soft Actor-Critic (SAC) reinforcement-learning controller that adaptively tunes four servo PID gains using a concentration-weighted state. Experiments on the PhysioNet EEGMMIDB, Ninapro DB2/DB7, HuMoD and WAY-EEG-GAL datasets (combining N = 162 trial sessions, 47,520 windows, and five-fold cross-validation) yield a gait-phase classification accuracy of 96.84 ± 1.18%, torque-tracking RMSE of 0.072 ± 0.008 N·m, information transfer rate of 38.6 bits/min, end-to-end latency of 9.4 ms, and a 27.4% reduction in simulated metabolic cost over an EMG-only PID baseline (one-way ANOVA: F(4, 75) = 47.83, p < 0.001; Tukey HSD: p < 0.01 against all baselines). Under high cognitive load, CM-FuseNet preserves accuracy with only a 4.63 percentage-point degradation versus 13.22 percentage points for the EMG-only baseline. Full article

Surface electromyography (sEMG) signals directly reflect movement intention and are therefore promising for natural human–machine interaction. However, their inherent non-stationarity and high inter-subject variability remain major obstacles to robust feature extraction and model generalization. To address these challenges, this study proposes a dual-stream spatial pyramid pooling convolutional neural network (DSSCNN). In this framework, one-dimensional sEMG segments are transformed into two complementary image representations, continuous wavelet transform (CWT) spectrograms and Gramian angular difference field (GADF) images, forming a dual-channel input that jointly preserves time–frequency dynamics and temporal correlation structures. A dual-stream convolutional architecture then extracts discriminative features from each modality, after which a spatial pyramid pooling (SPP) layer aggregates multi-scale representations, enhancing the network’s capacity to capture robust spatiotemporal patterns. Extensive experiments demonstrate that DSSCNN achieves an average gesture recognition accuracy of 97.88% with low inter-subject variance under intra-subject random split, and 96.59% under leave-one-subject-out (LOSO) protocol. The practical viability of the proposed approach is further validated through real-time control of an unmanned ground vehicle (UGV). These results not only indicate that the dual-stream framework combined with SPP layer provides an effective strategy for high-precision sEMG-based gesture recognition but also provides a promising technical pathway toward next-generation natural human–machine interaction. Full article

The Brain–Computer Interface (BCI) is a system that enables communication between the brain and external devices by translating brain activity into commands. Electroencephalography (EEG) is a commonly used modality for measuring brain activity. However, its low signal-to-noise ratio (SNR) and electrode reference problems lead to poor spatial resolution. As a result, EEG signals are often contaminated with physiological artifacts such as muscle movements. Therefore, this study used novel tripolar concentric ring electrodes (TCREs) to record brain signals related to overt and covert speech. Brain signals associated with overt and covert speech were recorded using TCRE and disc electrodes. Classification algorithms, including K-Nearest Neighbors (KNN), Fully Connected Neural Networks (FCNN), and Convolutional Neural Networks (CNN), were used to classify the TCRE and conventional EEG signals. The data were collected from 16 healthy participants, consisting of 10 males and 6 females. The experimental results demonstrate that TCREs provide superior performance compared to conventional disc electrodes. In addition, the $0.5$–$1.2\mathrm{s}$ interval, corresponding to the peak stimulus window, exhibits a maximum power of $250\mathsf{\mu }\mathrm{V}$. The average accuracy achieved during this peak epoch was $86.25\%$, whereas the remaining epoch shows an accuracy of $83.5\%$ using TCREs. Full article

This study presents a computational, simulation-based investigation of the dielectric response of human hand tissues, skin, fat, muscle, and bone to radiofrequency (RF) electromagnetic fields emitted by mobile devices. The widespread adoption of handheld devices and the deployment of fifth-generation (5G) networks, including millimetre-wave (mmWave) bands, have intensified concerns regarding localized human exposure to RF radiation, particularly in the hand, which serves as the primary interface during device operation. Using validated dielectric property datasets, numerical simulations were performed across the frequency range of 0.5–40 GHz, employing the Finite-Difference Time-Domain (FDTD) method to solve Maxwell’s equations, with analytical evaluations conducted in Maple-18. A heterogeneous multilayer hand phantom was developed, and simulations were conducted under controlled exposure conditions, including a transmitted power of 1 W, antenna gain of 2 dBi, and incident power density of 5 W/m², consistent with ICNIRP and NCC safety guidelines. Tissue responses were assessed over a temperature range of 10–40 °C to account for thermal variability. The results demonstrate strong frequency- and temperature-dependent behaviour of dielectric properties, intrinsic impedance, reflection coefficient, attenuation, and specific absorption rate (SAR). At lower frequencies (<1 GHz), RF energy penetrated more deeply with distributed absorption and relatively low SAR values, whereas higher frequencies (3–40 GHz) produced highly localized absorption in superficial tissues, particularly skin and muscle. Increasing temperature led to significant increases in permittivity, conductivity, and SAR, with up to a twofold enhancement observed between 10 °C and 40 °C. These findings confirm that 5G and mmWave exposures result in predominantly surface-confined energy deposition in hand tissues. The study provides a robust computational framework for evaluating hand device electromagnetic interactions and offers quantitative insights relevant to antenna design, exposure compliance assessment, and the development of evidence-based safety guidelines. Full article

Steady-state visual evoked potentials (SSVEPs) are one of the key paradigms used in brain–computer interface (BCI) systems. Their performance, however, is substantially degraded by EEG artifacts of muscular, motion-related, and ocular origin. This issue is particularly pronounced in individuals exhibiting increased facial muscle tension or involuntary eye movements. The aim of this study was to develop and evaluate an EEG artifact reduction method based on auxiliary channels, including central (Cz), frontal (Fp1), electrooculographic (HEOG), and muscular electrodes (neck, cheek, jaw). Signals from these channels were used to model the physical sources of interference recorded concurrently with occipital brain activity (O1, O2, Oz). EEG signal cleaning was performed using linear regression in 1-s windows, followed by frequency-domain analysis to extract features related to stimulation frequencies and SSVEP classification using SVM and CNN algorithms. The experiment involved three visual stimulation frequencies (7, 8, and 9 Hz) generated by LEDs and the recording of controlled facial and jaw-related artifacts. Experiments conducted on 12 participants demonstrated a 9% increase in classification accuracy after artifact removal. Further analysis indicated that the Cz and jaw channels contributed most significantly to effective artifact suppression. The results confirm that the use of auxiliary channels substantially improves EEG signal quality and enhances the reliability of BCI systems under real-world conditions. Full article

Electromyography (EMG) has become essential in biomedical engineering, rehabilitation, and human–machine interfacing due to its ability to capture neuromuscular activation for control, monitoring, and diagnosis. Recent advances in sensing hardware, high-density and flexible electrodes, and embedded acquisition modules combined with modern signal processing and machine learning have significantly enhanced the robustness and applicability of EMG-based systems. This review provides an integrated overview of EMG generation, acquisition standards, and preprocessing techniques, including adaptive filtering, wavelet denoising, and empirical mode decomposition. Feature extraction methods across the time, frequency, time–frequency, and nonlinear domains are compared with respect to computational efficiency and suitability for real-time systems. The review synthesizes classical and contemporary pattern-recognition approaches, from statistical classifiers to deep architectures such as CNNs, RNNs, hybrid CNN–RNN models, transformer-based networks, and graph neural networks. Key challenges, including signal non-stationarity, electrode displacement, muscle fatigue, and poor cross-user or cross-session generalization, are examined alongside emerging strategies such as transfer learning, domain adaptation, and multimodal fusion with IMU or FMG signals. Finally, the paper surveys rapidly growing EMG applications in prosthetics, rehabilitation robotics, human–machine interfaces, clinical diagnostics, and sports analytics. The review highlights ongoing limitations and outlines future pathways toward robust, adaptive, and deployable EMG-driven intelligent systems. Full article

Microproteins are small polypeptides translated from short open reading frames (sORFs) that typically encode < 100 amino acids. Advances in ribosome profiling, mass spectrometry, and computational prediction have revealed a growing number of microproteins that play important roles in cellular metabolism, organelle function, and stress adaptation; however, these were considered non-coding or functionally insignificant. At the mitochondrial level, microproteins, such as MTLN (also known as mitoregulin/MOXI) and BRAWNIN, contribute to lipid oxidation, oxidative phosphorylation efficiency, and respiratory chain assembly. Other microproteins at the endoplasmic reticulum–mitochondria interface, including PIGBOS and several muscle-resident regulators of calcium cycling, show diverse biological contexts in which these microproteins act. A subset of microproteins responds to nutrient availability. For example, SMIM26 modulates mitochondrial complex I translation under serine limitation, and non-coding RNA expressed in mesoderm-inducing cells encoded with peptides facilitates glucose uptake during differentiation, indicating that some microproteins can affect metabolic adaptation through localized translational- or organelle-level mechanisms. Rather than functioning as primary nutrient sensors, these microproteins complement classical nutrient-responsive pathways such as AMP-activated protein kinase-, peroxisome proliferator-activated receptor-, and carbohydrate response element binding protein-mediated signaling. As the catalog of microproteins continues to expand, integrating proteogenomics, nutrient biology, and functional studies will be central to defining their physiological relevance; these integrative approaches will also help reveal their potential applications in metabolic health. Full article

Our study introduces a surface electromyography (sEMG)-based Cheonjiin speller system developed to assist individuals with restricted hand mobility. The interface incorporates a directional control framework—comprising up, down, left, right, and select commands—integrated with a Korean keyboard layout to enable efficient and accessible text input. Two-channel surface EMG signals were recorded from the rectus femoris and gastrocnemius muscles at a sampling rate of 200 Hz using an EMG acquisition module. The signals were processed in real time using notch and bandpass filtering, followed by full-wave rectification. To decode user intent, three physiologically interpretable time-domain features—root mean square (RMS), slope sign change (SSC), and peak amplitude—were extracted and subsequently used for classification. The Cheonjiin speller was implemented in Python 3.10.8 and operated through directional cursor navigation. System performance was quantitatively evaluated in two experiments: in Experiment 1, recognition accuracy for five discrete commands reached an average of 90.0%, while Experiment 2, involving continuous Korean word and sentence input, achieved an average accuracy of 88.65%. Across both experimental conditions, the system attained an average information transfer rate (ITR) of 96.19 bits/min, confirming efficient real-time communication capability. The results demonstrate that high recognition performance can be achieved using simple, low-computation features without deep learning models, confirming the feasibility of real-time implementation in resource-limited environments. Overall, the proposed speller system exhibits high operability, accessibility, and practical usability in constrained conditions and holds potential for integration into augmentative and alternative communication (AAC) systems for users with motor impairments. Moreover, its lightweight architecture, minimal computational load, and flexible directional control structure make it adaptable to a wide range of assistive and wearable technology applications. Full article

High-performance musical instrument training is a demanding discipline that engages cognitive, neurological, and physical skills. Professional musicians invest substantial time and effort into mastering their repertoire and developing the muscle memory and reflexes required to perform complex works in high-stakes settings. While existing surveys have explored the use of music in therapeutic and general training contexts, there is a notable lack of work focused specifically on the needs of professional musicians and advanced instrumental practice. This topical review explores the potential of EEG-based brain–computer interface (BCI) technologies to integrate real-time feedback of biomechanic and cognitive features in advanced musical practice. Building on a conceptual framework of technology-enhanced musical practice (TEMP), we review empirical studies of broad contexts, addressing the EEG signal decoding of biomechanic and cognitive tasks that closely relates to the specified TEMP features (movement and muscle activity, posture and balance, fine motor movements and dexterity, breathing control, head and facial movement, movement intention, tempo processing, ptich recognition, and cognitive engagement), assessing their feasibility and limitations. Our analysis highlights current gaps and provides a foundation for future development of BCI-supported musical training systems to support high-performance instrumental practice. Full article

Sophisticated voluntary movements are essential for everyday functioning, making the study of how the brain controls muscle activity a central challenge in neuroscience. Investigating corticomuscular control through non-invasive electrophysiological recordings is particularly complex due to the intricate nature of neuronal signals. To address this challenge, we present a novel experimental methodology designed to study corticomuscular control using electroencephalography (EEG) and electromyography (EMG). Our approach integrates a serious gaming biofeedback system with a specialized experimental protocol for simultaneous EEG-EMG data acquisition, optimized for corticomuscular studies. This work introduces, for the first time, a method for assessing brain–muscle functional connectivity during the execution of a demanding motor task. By identifying neuronal sources linked to muscular activity, this methodology has the potential to advance our understanding of motor control mechanisms. These insights could contribute to improving clinical practices and fostering the development of novel brain–computer interface technologies. Full article

Gesture recognition based on conventional machine learning is the main control approach for advanced prosthetic hand systems. Its primary limitation is the need for feature extraction, which must meet real-time control requirements. On the other hand, deep learning models could potentially overfit when trained on small datasets. For these reasons, we propose a hybrid Linear Discriminant Analysis–convolutional neural network (LDA-CNN) framework to improve the gesture recognition performance of sEMG-based prosthetic hand control systems. Within this framework, 1D-CNN filters are trained to generate latent representation that closely approximates Fisher’s (LDA’s) discriminant subspace, constructed from handcrafted features. Under the train-one-test-all evaluation scheme, our proposed hybrid framework consistently outperformed the 1D-CNN trained with cross-entropy loss only, showing improvements from 4% to 11% across two public datasets featuring hand gestures recorded under various limb positions and arm muscle contraction levels. Furthermore, our framework exhibited advantages in terms of induced spectral regularization, which led to a state-of-the-art recognition error of 22.79% with the extended 23 feature set when tested on the multi-limb position dataset. The main novelty of our hybrid framework is that it decouples feature extraction in regard to the inference time, enabling the future incorporation of a more extensive set of features, while keeping the inference computation time minimal. Full article

Background and Objectives: Brain-computer interface (BCI) technology is revolutionizing stroke rehabilitation by offering innovative neuroengineering solutions to address neurological deficits. By bypassing peripheral nerves and muscles, BCIs enable individuals with severe motor impairments to communicate their intentions directly through control signals derived from brain activity, opening new pathways for recovery and improving the quality of life. The aim of this study was to explore the beneficial effects of BCI system-based interventions on upper limb motor function and performance of activities of daily living (ADL) in stroke patients. We hypothesized that integrating BCI into occupational therapy would result in measurable improvements in hand strength, dexterity, independence in daily activities, and cognitive function compared to baseline. Materials and Methods: An observational study was conducted on 56 patients with subacute stroke. All patients received standard medical care and rehabilitation for 54 days, as part of the comprehensive treatment protocol. Patients underwent BCI training 2–3 times a week instead of some occupational therapy sessions, with each patient completing 15 sessions of BCI-based recoveriX treatment during rehabilitation. The occupational therapy program included bilateral exercises, grip-strengthening activities, fine motor/coordination tasks, tactile discrimination exercises, proprioceptive training, and mirror therapy to enhance motor recovery through visual feedback. Participants received ADL-related training aimed at improving their functional independence in everyday activities. Routine occupational therapy was provided five times a week for 50 min per session. Upper extremity function was evaluated using the Box and Block Test (BBT), Nine-Hole Peg Test (9HPT), and dynamometry to assess gross manual dexterity, fine motor skills, and grip strength. Independence in daily living was assessed using the Functional Independence Measure (FIM). Results: Statistically significant improvements were observed across all the outcome measures (p < 0.001). The strength of the stroke-affected hand improved from 5.0 kg to 6.7 kg, and that of the unaffected hand improved from 29.7 kg to 40.0 kg. Functional independence increased notably, with the FIM scores rising from 43.0 to 83.5. Cognitive function also improved, with MMSE scores increasing from 22.0 to 26.0. The effect sizes ranged from moderate to large, indicating clinically meaningful benefits. Conclusions: This study suggests that BCI-based occupational therapy interventions effectively improve upper extremity motor function and daily functions and have a positive impact on the cognition of patients with subacute stroke. Full article

Motor imagery (MI) is a crucial research field within the brain–computer interface (BCI) domain. It enables patients with muscle or neural damage to control external devices and achieve movement functions by simply imagining bodily motions. Despite the significant clinical and application value of MI-BCI technology, accurately decoding high-dimensional and low signal-to-noise ratio (SNR) electroencephalography (EEG) signals remains challenging. Moreover, traditional deep learning approaches exhibit limitations in processing EEG signals, particularly in capturing the intrinsic correlations between electrode channels and long-distance temporal dependencies. To address these challenges, this research introduces a novel end-to-end decoding network that integrates convolutional neural networks (CNNs) and a Swin Transformer, aiming at enhancing the classification accuracy of the MI paradigm in EEG signals. This approach transforms EEG signals into a three-dimensional data structure, utilizing one-dimensional convolutions along the temporal dimension and two-dimensional convolutions across the EEG electrode distribution for initial spatio-temporal feature extraction, followed by deep feature exploration using a 3D Swin Transformer module. Experimental results show that on the BCI Competition IV-2a dataset, the proposed method achieves 83.99% classification accuracy, which is significantly better than the existing deep learning methods. This finding underscores the efficacy of combining a CNN and Swin Transformer in a 3D data space for processing high-dimensional, low-SNR EEG signals, offering a new perspective for the future development of MI-BCI. Future research could further explore the applicability of this method across various BCI tasks and its potential clinical implementations. Full article