Search Results (321)

Surface electromyography (sEMG) signals are inevitably affected by noise during acquisition, thereby degrading signal quality and analytical reliability. Most existing denoising methods combine signal decomposition with thresholding, and their performance depends on empirically set decomposition parameters and threshold estimation. However, in high-rate repetitive motions such as rapid keystrokes, sustained high-duty-cycle muscle activation biases universal-threshold noise estimation, leading to unreliable thresholds. To overcome these issues, an sEMG denoising method that integrates the Walrus Optimizer (WO) with Variational Mode Decomposition (VMD) is proposed. WO is employed to optimize key VMD parameters, including the number of modes K and the penalty factor $\alpha$. Based on this method, an improved threshold estimation strategy is developed to accommodate high-duty-cycle sEMG during rapid keystrokes. It reduces thresholding-induced over-attenuation of meaningful myoelectric components. The dataset included 18 participants with sEMG recorded from six muscles during rapid keystroke tasks (10 trials per participant; 20 keystrokes per trial). Across input signal-to-noise ratios (SNRs) of 0, 5, 10, 15 dB, the proposed method achieved a median SNR improvement (ΔSNR) ranging from 2.75 to 6.65 dB and a median root-mean-square error (RMSE) reduction rate (ΔRMSE%) ranging from 27% to 53%, while maintaining spectral fidelity with a median of median frequency variation rate (ΔMDF%) below 3.48%.These results indicate that the proposed method provides an efficient and reliable solution for sEMG signal processing in rapid keystroke analysis. Full article

Wearable sensing technologies are increasingly used to assess neuromuscular function during daily-life activities. This study presents and evaluates a multisensor wearable system integrating a textile-based surface Electromyography (sEMG) sleeve and a pressure-sensing insole for monitoring Tibialis Anterior (TA) and Gastrocnemius Lateralis (GL) activation during gait. Eleven healthy adults performed overground walking trials while synchronised sEMG and plantar pressure signals were collected and processed using a dedicated algorithm for detecting activation intervals across gait cycles. All participants completed the walking protocol without discomfort, and the system provided stable recordings suitable for further analysis. The detected activation patterns showed one to four bursts per gait cycle, with consistent TA activity in terminal swing and GL activity in mid- to terminal stance. Additional short bursts were observed in early stance, pre-swing, and mid-stance depending on the pattern. The area under the sEMG envelope and the temporal features of each burst exhibited both inter- and intra-subject variability, consistent with known physiological modulation of gait-related muscle activity. The results demonstrate the feasibility of the proposed multisensor system for characterising muscle activation during walking. Its comfort, signal quality, and ease of integration encourage further applications in clinical gait assessment and remote monitoring. Future work will focus on system optimisation, simplified donning procedures, and validation in larger cohorts and populations with gait impairments. 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

The non-invasive recording of spinal cord neuronal activity, also known as electrospinography (ESG), using high-density surface electromyography (HD-sEMG) is a promising emerging biosensing modality. However, these recordings often contain electrocardiographic (ECG) artifacts that must be removed for accurate analysis. Given the emerging nature of ESG and the lack of dedicated signal processing methods, this study assesses the performance of seven established EMG denoising algorithms for their ability to preserve the broad spectral bandwidth needed for future ESG characterization: Template Subtraction (TS), Adaptive Template Subtraction (ATS), High-Pass Filtering at 200 Hz (HP200), ATS combined with HP200, Second-Order Extended Kalman Smoother (EKS2), Stationary Wavelet Transform (SWT), and Empirical Mode Decomposition (EMD). Performance was quantified using six metrics: Relative Error (RE), Signal-to-Noise Ratio (SNR), Cross-Correlation (CC), Spectral Distortion (SD), and Kurtosis Ratio (KR2) and its variation ($\Delta$KR2). ESG data were recorded from nine healthy participants at brachial and lumbar plexus sites with various electrode configurations. ATS consistently outperformed all other methods in suppressing cardiac artifacts of varying shapes. Although it did not fully preserve low-frequency content, ATS achieved the best balance between artifact removal and signal integrity. Algorithm performance improved when ECG contamination was lower, especially in brachial plexus recordings with closer reference electrodes. Full article

Smart devices and multimodal biosignal systems, including electroencephalography (EEG/MEG), ECG-derived heart rate variability (HRV), and electromyography (EMG), increasingly supported by artificial intelligence (AI), are being explored to improve the assessment and longitudinal monitoring of mental health conditions. Despite rapid growth, the available evidence remains heterogeneous, and clinical translation is limited by variability in acquisition protocols, analytical pipelines, and validation quality. This systematic review synthesizes current applications, signal-processing approaches, and methodological limitations of biosignal-based smart systems for mental health monitoring. Methods: A PRISMA 2020-guided systematic review was conducted across PubMed/MEDLINE, Scopus, the Web of Science Core Collection, IEEE Xplore, and the ACM Digital Library for studies published between 2013 and 2026. Eligible records reported human applications of wearable/smart devices or multimodal biosignals (e.g., EEG/MEG, ECG/HRV, EMG, EDA/GSR, and sleep/activity) for the detection, monitoring, or management of mental health outcomes. The reviewed literature after predefined inclusion/exclusion criteria clustered into six themes: depression detection and monitoring (37%), stress/anxiety management (18%), post-traumatic stress disorder (PTSD)/trauma (5%), technological innovations for monitoring (25%), brain-state-dependent stimulation/interventions (3%), and socioeconomic context (7%). Across modalities, common analytical pipelines included artifact suppression, feature extraction (time/frequency/nonlinear indices such as entropy and complexity), and machine learning/deep learning models (e.g., SVM, random forests, CNNs, and transformers) for classification or prediction. However, 67% of studies involved sample sizes below 100 participants, limited ecological validity, and lacked external validation; heterogeneity in protocols and outcomes constrained comparability. Conclusions: Overall, multimodal systems demonstrate strong potential to augment conventional mental health assessment, particularly via wearable cardiac metrics and passive sensing approaches, but current evidence is dominated by proof-of-concept studies. Future work should prioritize standardized reporting, rigorous validation in diverse real-world cohorts, transparent model evaluations, and ethics-by-design principles (privacy, fairness, and clinical governance) to support translation into practice. Full article

This study focuses on classifying electromyographic (EMG) signals to identify seven specific hand movements, including complete hand closure, individual finger closures, and a pincer grip. Accurately distinguishing these movements is challenging due to overlapping muscle activation patterns. To address this, a methodology structured in five stages was developed: placement of electrodes on specific forearm muscles to capture electrical activity during movements; acquisition of EMG signals from twelve participants performing the seven types of movements; preprocessing of the signals through filtering and rectification to enhance quality, followed by the extraction of features from three distinct types of preprocessed signals—filtered, rectified, and envelope signals—to facilitate analysis in the temporal, frequency, and time–frequency domains; extraction of relevant features such as amplitude, shape, symmetry, and frequency variance; and classification of the signals using eight machine learning algorithms: support vector machine (SVM), multiclass logistic regression, k-nearest neighbors (k-NN), Bayesian classifier, artificial neural network (ANN), random forest, XGBoost, and LightGBM. The performance of each algorithm was evaluated using different sets of features derived from the preprocessed signals to identify the most effective approach for classifying hand movements. Additionally, the impact of various signal representations on classification accuracy was examined. Experimental results indicated that some algorithms, especially when an expanded set of features was utilized, achieved improved accuracy in classifying hand movements. These findings contribute to the development of more efficient control systems for myoelectric prostheses and offer insights for future research in EMG signal processing and pattern recognition. Full article

Background: This study aimed to explore the effects of neuromuscular electrical stimulation (NMES) combined with water-based resistance training on muscle activation and coordination during freestyle kicking. Methods: Thirty National Level male freestyle swimmers were randomly assigned to an experimental group (NMES + water-based training) or a control group (water-based training only) for a 12-week intervention. The experimental group received NMES pretreatment before each session. Underwater surface electromyography (sEMG) synchronized with high-speed video was used to collect muscle activation data and corresponding kinematic information during the freestyle kick. The sEMG signals were then processed using time-domain analysis, including integrated electromyography (iEMG), which reflects the cumulative electrical activity of muscles, and root mean square amplitude (RMS), which indicates the intensity of muscle activation. Non-negative matrix factorization (NMF) was further applied to extract and characterize muscle synergy patterns. Results: The experimental group showed significantly higher iEMG and RMS values in key muscles during both kicking phases. Within the core propulsion synergy, muscle weighting of vastus medialis and biceps femoris increased significantly, while activation duration of the postural adjustment synergy was shortened. The number of synergies showed no significant difference. Conclusions: NMES combined with water-based resistance training enhances muscle activation and optimizes neuromuscular coordination strategies, offering a novel approach to improving sport-specific performance. Full article

Objective: to clarify differences in the intermuscular coherence of core muscles during side kicks among male Sanda athletes at varying skill levels, particularly in critical frequency bands; to reveal the association between neuromuscular coordination mechanisms and technical proficiency; and to provide methodological references for quantitative analysis of combat sports techniques. Methods: Thirty-six male Sanda athletes were divided into professional (n = 18) and amateur (n = 18) groups based on athletic ranking and training duration. Surface electromyographic (EMG) signals from 15 core muscles and kinematic data were synchronously recorded using a wireless EMG system and a high-speed camera. Signal processing extracted root mean square amplitude (RMS) and integral EMG (iEMG). Muscle coordination was quantified via time-frequency coherence analysis across alpha (8–15 Hz), beta (15–30 Hz), and gamma (30–50 Hz) bands. Results: The professional group exhibited significantly higher RMS and iEMG values in most core muscles (e.g., rectus femoris RMS: 0.298 ± 0.072 vs. 0.214 ± 0.077 mV, p < 0.001). Regarding intermuscular coherence, the professional group demonstrated significantly superior coherence in the α, β, and γ bands for key muscle pairs, including upper limb–swing leg, support leg–swing leg, and upper limb–support leg. Notable differences were observed in pairs such as external oblique–rectus femoris (alpha band: 0.039 ± 0.012 vs. 0.032 ± 0.011, p < 0.01) and right rectus femoris–biceps femoris (beta band: 0.033 ± 0.010 vs. 0.023 ± 0.007, p < 0.01). Conclusions: The fundamental difference in side kick technique among Sanda athletes lies in neuromuscular control strategies and muscle coordination efficiency. Sensor-based intermuscular coherence analysis provides an objective quantitative indicator for distinguishing technical proficiency, offering a scientific basis for optimizing training and extending the methodological framework for technique assessment in combat sports. Full article

Bio-electric fields—manifested as Electroencephalogram (EEG), Electrocardiogram (ECG), Electromyogram (EMG), and Electrooculogram (EOG)—are fundamental to modern medical diagnostics but often suffer from severe data imbalance, scarcity, and environmental noise. Generative Adversarial Networks (GANs) offer a powerful, nonlinear solution to these modeling hurdles. This review presents a comprehensive survey of GAN methodologies specifically tailored for bio-electric signal processing. We first establish a theoretical foundation by detailing GAN principles, training mechanisms, and critical structural variants, including advancements in loss functions and conditional architectures. Subsequently, the paper extensively analyzes applications ranging from high-fidelity signal synthesis and noise reduction to multi-class classification. Special attention is given to clinical anomaly detection, specifically covering epilepsy, arrhythmia, depression, and sleep apnea. Furthermore, we explore emerging applications such as modal transformation, Brain–Computer Interfaces (BCI), de-identification for privacy, and signal reconstruction. Finally, we critically evaluate the computational trade-offs and stability issues inherent in current models. The study concludes by delineating prospective research avenues, emphasizing the necessity of interdisciplinary synergy to advance personalized medicine and intelligent diagnostic systems. Full article

Infantile Epileptic Spasms Syndrome (IESS) is a devastating epileptic encephalopathy of infancy that carries a high risk of lifelong neurodevelopmental disability. Timely diagnosis is critical, as every week of delay in effective treatment is associated with worse cognitive outcomes. Although synchronized electroencephalogram (EEG) and surface electromyography (EMG) recordings capture both the electrophysiological and motor signatures of spasms, accurate automated detection remains challenging due to the non-stationary nature of the signals and the absence of physiologically plausible inter-modal fusion in current deep learning approaches. We introduce IESS-FusionNet, an end-to-end dual-stream framework specifically designed for accurate, real-time IESS detection from simultaneous EEG and EMG. Each modality is processed by a dedicated Unimodal Encoder that hierarchically integrates Continuous Wavelet Transform, Spatio-Temporal Convolution, and Bidirectional Mamba to efficiently extract frequency-specific, spatially structured, local and long-range temporal features within a compact module. A novel Cross Time-Mixing module, built upon the linear recurrent attention of the Receptance Weighted Key Value (RWKV) architecture, subsequently performs efficient, time-decaying, bidirectional cross-modal integration that explicitly respects the causal and physiological properties of cortico-muscular coupling during spasms. Evaluated on an in-house clinical dataset of synchronized EEG-EMG recordings from infants with confirmed IESS, IESS-FusionNet achieves 89.5% accuracy, 90.7% specificity, and 88.3% sensitivity, significantly outperforming recent unimodal and multimodal baselines. Comprehensive ablation studies validate the contribution of each component, while the proposed cross-modal fusion requires approximately 60% fewer parameters than equivalent quadratic cross-attention mechanisms, making it suitable for real-time clinical deployment. IESS-FusionNet delivers an accurate, computationally efficient solution with physiologically inspired cross-modal fusion for the automated detection of infantile epileptic spasms, offering promise for future clinical applications in reducing diagnostic delay. Full article

Electroencephalography (EEG) signal acquisition is often affected by artifacts, challenging applications such as brain disease diagnosis and Brain-Computer Interfaces (BCIs). This paper proposes TF-Denoiser, a deep learning model using a joint time-frequency optimisation strategy for artifact removal. The proposed method first employs a position embedding module to process EEG data, enhancing temporal feature representation. Then, the EEG signals are transformed from the time domain to the complex frequency domain via Fourier transform, and the real and imaginary parts are denoised separately. The multi-attention denoising module (MA-denoise) is used to extract both local and global features of EEG signals. Finally, joint optimisation of time-frequency features is performed to improve artifact removal performance. Experimental results demonstrate that TF-Denoiser outperforms the compared methods in terms of correlation coefficient (CC), relative root mean square error (RRMSE), and signal-to-noise ratio (SNR) on electromyography (EMG) and electrooculography (EOG) datasets. It effectively reduces ocular and muscular artifacts and improves EEG denoising robustness and system stability. Full article

Objective quantification of tremor remains a challenge in Parkinson’s disease (PD) assessment, with current clinical assessments relying largely on subjective scale ratings. This study evaluates the feasibility and signal behaviour of integrating surface electromyography (sEMG) with MDS-UPDRS-aligned tasks in a healthy adult cohort, with the aim of establishing normative low-frequency muscle activation profiles. Thirty-two healthy participants (mean age 27.6 ± 5.3 years) completed seven upper-limb tasks derived from the MDS-UPDRS while sEMG data were recorded from antagonistic forearm muscles. Signals were normalised using maximum voluntary contraction, filtered at 14 Hz, and analysed using frequency-domain (FFT) and time-frequency (STFT) methods. Significant task-dependent differences were observed in both frequency occurrence and magnitude (p < 0.05), particularly within the 3.5–9 Hz range. Finger tapping elicited increased low-frequency activity compared to baseline, while pronation–supination produced the most stable and consistent muscle activation across participants. Frequencies above 12 Hz showed minimal task discrimination. These findings demonstrate that low-frequency tremor-like activity can occur during specific MDS-UPDRS tasks in healthy individuals and may require further validation before being considered suitable for PD staging. This work establishes normative sEMG benchmarks to support future clinical validation and PD cohort comparisons. Full article

This paper presents the development and cloud deployment of a system for the segmentation of electromyographic (EMG) signals oriented toward muscle fatigue monitoring in the biceps and triceps. A dataset of 30 subjects was used, resulting in 120 EMG and gyroscope files containing between four and six strength exercise series each. After a quality assessment, approximately 80% of the signals (95 files) were classified as level 1 or 2 and considered suitable for segmentation and subsequent analysis. A near real-time segmentation algorithm was designed based on signal envelopes, sliding windows, and quantile thresholds, complemented with discrete wavelet transform (DWT) filtering. Using EMG alone, segmentation accuracy reached 83% for biceps and 54% for triceps; after incorporating DWT preprocessing, accuracy increased to 87.5% and 71%, respectively. By exploiting the gyroscope’s X-axis signal as a low-noise reference, the optimal configuration achieved an overall accuracy of 80%, with 83.3% for biceps and 76.2% for triceps. The prototype was deployed on Amazon Web Services (AWS) using EC2 instances and SQS queues, and its computational cost was evaluated across four server types. On a t2.micro instance, the maximum memory usage was approximately 219 MB with a dedicated CPU and a maximum processing time of 0.98 s per signal, demonstrating the feasibility of near real-time operation under conditions with limited resources. Full article

In response to the personalized and precise rehabilitation needs for motor injuries and stroke associated with population aging, this study proposes a design method for an intelligent rehabilitation trainer that integrates Bayesian information gain (BIG) and axis matching techniques. Grounded in the biomechanical characteristics of the human ankle joint, the design fully draws upon biomimetic principles, constructing a 3-PUU-R hybrid serial–parallel bionic mechanism. By mimicking the dynamic variation of the ankle’s instantaneous motion axis and its balance between stiffness and compliance, a three-dimensional digital model was developed, and multi-posture human factor simulations were conducted, thereby achieving a rehabilitation process more consistent with natural human movement patterns. Natural randomized disability grade experimental data were collected for 100 people to verify the validity of the design results. On this basis, a Bayesian information gain framework was established by quantifying the reduction of uncertainty in rehabilitation outcomes through characteristic parameters, enabling the dynamic optimization of training strategies for personalized and precise ankle rehabilitation. The rehabilitation process was modeled as a problem of uncertainty quantification and information gain optimization. Prior distributions were constructed using surface EMG (electromyography) signals and motion trajectory errors, and mutual information was used to drive the dynamic adjustment of training strategies, ultimately forming a closed-loop control architecture of “demand perception–strategy optimization–execution adaptation.” This innovative integration of probabilistic modeling and cross-joint bionic design overcomes the limitations of single-joint rehabilitation and provides a new paradigm for the development of intelligent rehabilitation devices. The deep integration mechanism-based dynamic axis matching and Bayesian information gain holds significant theoretical value and engineering application prospects for enhancing the effectiveness of neural plasticity training. Full article

Background: Haptic technology has long been integrated into simulated (sim) environments to create a sense of realism and improve performance. In sim racing, force and vibrotactile feedback have been implemented into steering wheels to create a more realistic experience. However, little is understood about how these types of feedback convey information to the sim racer. This study aimed to decode the vibration frequencies transferred through the steering wheel to the user and investigate how these frequencies vary as the strength of each feedback channel is manipulated. Methods: Using a Noraxon Ultium EMG accelerometer, the movements of a Logitech G Pro sim racing wheel were recorded whilst four participants completed five clean laps across nine different conditions. During each condition, a combination of force feedback (0 nm, 6 nm, or 11 nm) and vibrotactile feedback (0%, 50%, or 100%) settings were altered. Accelerometer data were pre-processed and Fast Fourier Transforms were performed to allow examination of signal power at frequencies of up to 200 Hz. Two-way repeated measures ANOVAs were performed to investigate differences in power at relevant frequencies across conditions and laps. Results: Wheel motion was predominantly contained within the 0–5 Hz (force feedback and racer input) and 25–30 Hz ranges. No significant differences were seen in 0–5 Hz power between conditions, but the 25–30 Hz range was observed to exponentially increase as vibrotactile feedback was linearly increased. Finally, 25–30 Hz power at a fixed vibrotactile feedback intensity significantly decreased when the force feedback intensity was increased. Discussion and Conclusions: This study decodes the haptic feedback relayed to the user through a sim racing wheel and highlights atypical changes to signal amplitude across various frequency bands when altering force and vibrotactile feedback intensity. Full article