Search Results (48)

To comprehensively leverage the temporal, static, and dynamic information features of multi-channel surface electromyography (sEMG) signals for gesture recognition, considering the sensitive temporal characteristics of sEMG signals to action amplitude and muscle recruitment patterns, an sEMG-based gesture recognition algorithm is innovatively proposed using Sigimg-GADF-MTF and multi-stream convolutional neural network (MSCNN) by introducing the Sigimg, GADF, and MTF data processing methods and combining them with a multi-stream fusion strategy. Firstly, a sliding window is used to rearrange the multi-channel original sEMG signals through channels to generate a two-dimensional image (named Sigimg method). Meanwhile, each channel signal is respectively transformed into two-dimensional subimages using Gram angular difference field (GADF) and Markov transition field (MTF) methods. Then, the GADF and MTF images are obtained using a horizontal stitching method to splice these subimages, respectively. The Sigimg, GADF, and MTF images are used to construct a training and testing dataset, which is then imported into the constructed MSCNN model for experimental testing. The fully connected layer fusion method is utilized for multi-stream feature fusion, and the gesture recognition results are output. Through comparative experiments, an average accuracy of 88.4% is achieved using the Sigimg-GADF-MTF-MSCNN algorithm on the Ninapro DBl dataset, higher than most mainstream models. At the same time, the effectiveness of the proposed algorithm is fully verified through generalization testing of data obtained from the self-developed sEMG signal acquisition platform with an average accuracy of 82.4%. Full article

Accurate and reliable human pose estimation (HPE) is essential in interactive systems, particularly for applications requiring personalized adaptation, such as controlling cooperative robots and wearable exoskeletons, especially for healthcare monitoring equipment. However, continuously maintaining diverse datasets and frequently updating models for individual adaptation are both resource intensive and time-consuming. To address these challenges, we propose a meta-transfer learning framework that integrates multimodal inputs, including high-frequency surface electromyography (sEMG), visual-inertial odometry (VIO), and high-precision image data. This framework improves both accuracy and stability through a knowledge fusion strategy, resolving the data alignment issue, ensuring seamless integration of different modalities. To further enhance adaptability, we introduce a training and adaptation framework with few-shot learning, facilitating efficient updating of encoders and decoders for dynamic feature adjustment in real-time applications. Experimental results demonstrate that our framework provides accurate, high-frequency pose estimations, particularly for intra-subject adaptation. Our approach enables efficient adaptation to new individuals with only a few new samples, providing an effective solution for personalized motion analysis with minimal data. Full article

Gait is a complex motor process that involves the coordination and synchronization of various body parts through continuous interaction with the environment. Monitoring gait is crucial for the early detection of abnormalities, such as toe walking, which is characterized by limited or absent heel contact with the floor during walking. Persistent toe walking can cause severe foot, ankle, and musculature conditions; poor balance; increased risk of falling or tripping; and can affect overall quality of life, making it difficult, for example, to participate in sports or social activities. This study proposes a new approach to detect toe walking using surface Electromyography (sEMG) on lower limbs. sEMG sensors, by measuring the electrical activity of muscles, can see signals before the movement corresponding to muscle activation, contributing to an early detection of a possible problem. The sEMG signal presents significant complexity due to its noisy nature and the challenge of extracting meaningful features for classification. To address this issue and enhance the model’s robustness across different devices and configurations, a Transfer Learning (TL) approach is introduced. This method leverages pre-trained models to effectively handle the variability of sEMG data and improve classification accuracy. In particular, Continuous Wavelet Transform (CWT) is applied to sEMG-filtered signals (with time windows of 1 s) to convert them into 2D images (scalograms). Preliminary tests were performed on a public dataset using some of the most well-known pre-trained architectures, obtaining an accuracy of about 95% on InceptionResNetV2. Full article

Gesture recognition technology has emerged as a transformative solution for natural and intuitive human–computer interaction (HCI), offering touch-free operation across diverse fields such as healthcare, gaming, and smart home systems. In mobile contexts, where hygiene, convenience, and the ability to operate under resource constraints are critical, hand gesture recognition provides a compelling alternative to traditional touch-based interfaces. However, implementing effective gesture recognition in real-world mobile settings involves challenges such as limited computational power, varying environmental conditions, and the requirement for robust offline–online data management. In this study, we introduce ThumbsUp, which is a gesture-driven system, and employ a partially systematic literature review approach (inspired by core PRISMA guidelines) to identify the key research gaps in mobile gesture recognition. By incorporating insights from deep learning–based methods (e.g., CNNs and Transformers) while focusing on low resource consumption, we leverage Google’s MediaPipe in our framework for real-time detection of 21 hand landmarks and adaptive lighting pre-processing, enabling accurate recognition of a “thumbs-up” gesture. The system features a secure queue-based offline–cloud synchronization model, which ensures that the captured images and metadata (encrypted with AES-GCM) remain consistent and accessible even with intermittent connectivity. Experimental results under dynamic lighting, distance variations, and partially cluttered environments confirm the system’s superior low-light performance and decreased resource consumption compared to baseline camera applications. Additionally, we highlight the feasibility of extending ThumbsUp to incorporate AI-driven enhancements for abrupt lighting changes and, in the future, electromyographic (EMG) signals for users with motor impairments. Our comprehensive evaluation demonstrates that ThumbsUp maintains robust performance on typical mobile hardware, showing resilience to unstable network conditions and minimal reliance on high-end GPUs. These findings offer new perspectives for deploying gesture-based interfaces in the broader IoT ecosystem, thus paving the way toward secure, efficient, and inclusive mobile HCI solutions. Full article

The accurate, repeatable, and cost-effective quantitative characterization of mild traumatic brain injuries (mTBIs) is crucial for safeguarding the long-term health and performance of high-risk groups, including athletes, emergency responders, and military personnel. However, gaps remain in optimizing mTBI assessment methods, especially regarding the integration of neuromechanical metrics such as reaction time (RT) in predictive models. Background/Objectives: This review synthesizes existing research on the use of neuromechanical probabilistic models as tools for assessing mTBI, with an emphasis on RT’s role in predictive diagnostics. Methods: We examined 57 published studies on recent sensing technologies such as advanced electromyographic (EMG) systems that contribute data for probabilistic neural imaging, and we also consider measurement models for real-time RT tracking as a diagnostic measure. Results: The analysis identifies three primary contributions: (1) a comprehensive survey of probabilistic approaches for mTBI characterization based on RT, (2) a technical examination of these probabilistic algorithms in terms of reliability and clinical utility, and (3) a detailed outline of experimental requirements for using RT-based metrics in psychomotor tasks to advance mTBI diagnostics. Conclusions: This review provides insights into implementing RT-based neuromechanical metrics within experimental frameworks for mTBI diagnosis, suggesting that such metrics may enhance the sensitivity and utility of assessment and rehabilitation protocols. Further validation studies are recommended to refine RT-based probabilistic models for mTBI applications. Full article

Ankle-foot orthoses (AFOs) have been commonly prescribed for stroke survivors with foot drop, but their impact on the contractions of paretic tibialis anterior (TA) and medial gastrocnemius (MG) has remained inconclusive. This study thus investigated the effect of AFOs on these muscle contractions in stroke survivors. The contractions of paretic TA and MG muscles were assessed in twenty stroke patients and compared between walking with and without AFOs, using a novel wearable dynamic ultrasound imaging and sensing system. The study found an increase in TA muscle thickness throughout a gait cycle (p > 0.05) and a significant increase in TA muscle surface mechanomyography (sMMG) signals during the pre- and initial swing phases (p < 0.05) when using an AFO. MG muscle thickness generally decreased with the AFO (p > 0.05), aligning more closely with trends seen in healthy adults. The MG surface electromyography (sEMG) signal significantly decreased during the initial and mid-swing phases when wearing an AFO (p < 0.05). The TA-MG co-contraction index significantly decreased during initial and mid-swing phases with the AFO (p < 0.05). These results suggest that AFOs positively influenced the contraction patterns of paretic ankle muscles during walking in stroke patients, but further research is needed to understand their long-term effects. Full article

Background/Objectives: Pelvic floor muscles (PFM) play a vital role in the proper functioning of the pelvic and abdominal organs. The PFM are structurally connected to other areas of the body, forming part of the deep front line. Due to its course, this line connects the PFM with the temporomandibular joint (TMJ). The aim of the study was to evaluate the impact of a single 15-minute soft tissue therapy session in the TMJ on the activity of the PFM. Methods: A total of 47 nulliparous women aged 20–29 years old diagnosed with myofascial pain in the TMJ area were included in the study. PFM were assessed using the Noraxon Ultium device and a vaginal probe, utilizing the surface electromyography (sEMG) method. The sEMG signal was processed with MyoResearch XP software version 1.0. Additionally, bladder floor displacement during PFM contractions was evaluated using an ultrasound imaging device set in B-mode (LOGIQ P7/P9). Results: In the experimental group, following the applied soft tissue therapy, a significant decrease in resting PFM activity between maximal contractions was observed (p < 0.05). The resting PFM activity assessed in the final phase of the measurement protocol was also significantly lower (p < 0.05). During endurance contractions in the experimental group, after the therapy, an 18.05% increase in PFM tension amplitude was noted, although this change was not statistically significant. In the control group, a decrease in amplitude was observed during the second assessment in this phase of the test. Conclusions: A single session of soft tissue therapy in the TMJ area may enhance the ability of the pelvic floor muscles to relax and contribute to improved muscle function by increasing their activation levels during submaximal contractions Full article

Estimating human joint angles is a crucial task in motion analysis, gesture recognition, and motion intention prediction. This paper presents a novel model-based approach for generating reliable and accurate human joint angle estimation using a dual-branch network. The proposed network leverages combined features derived from encoded sEMG signals and RGB-D image data. To ensure the accuracy and reliability of the estimation algorithm, the proposed network employs a convolutional autoencoder to generate a high-level compression of sEMG features aimed at motion prediction. Considering the variability in the distribution of sEMG signals, the proposed network introduces a vision-based joint regression network to maintain the stability of combined features. Taking into account latency, occlusion, and shading issues with vision data acquisition, the feature fusion network utilizes high-frequency sEMG features as weights for specific features extracted from image data. The proposed method achieves effective human body joint angle estimation for motion analysis and motion intention prediction by mitigating the effects of non-stationary sEMG signals. Full article

Emotions are dynamic processes; their variability relates to psychological well-being and psychopathology. Affective alterations have been linked to mental diseases like depression, although little is known about how similar patterns occur in healthy individuals. This study investigates the psychophysiological correlations of emotional processing in healthy subjects, specifically exploring the relationship between depressive traits, cognitive distortions, and facial electromyographic (f-EMG) responses during affective transitions. A cohort of 44 healthy participants underwent f-EMG recording while viewing emotional images from the International Affective Picture System (IAPS). Self-report measures included the Beck Depression Inventory (BDI) and the Cognitive Distortion Scale (CDS). Higher BDI scores were associated with increased EMG activity in the corrugator muscle during transitions between positive and negative emotional states. Cognitive distortions such as Catastrophizing, All-or-Nothing Thinking, and Minimization showed significant positive correlations with EMG activity, indicating that individuals with higher levels of these distortions experienced greater facial muscle activation during emotional transitions. This study’s results indicate that there is a bidirectional correlation between depressed features and cognitive distortions and alterations in facial emotional processing, even in healthy subjects. Facial EMG in the context of dynamic affective transitions has the potential to be used as a non-invasive method for detecting abnormal emotional reactions at an early stage. This might help in identifying individuals who are at risk of developing depression and guide therapies to prevent its advancement. Full article

Background: This study aims to characterize the clinical impact of endovascular treatment in Chronic Pelvic Pain (CPP) patients due to Pelvic Congestion Syndrome (PCS) and to assess the diagnostic value of surface electromyography (sEMG) studies of pelvic floor musculature (PFM) in PCS patients pre- and post-endovascular treatment. Between January 2019 and July 2023, we studied consecutive patients who were referred for interventional radiology assessment and treatment to a tertiary trauma care hospital, had evidence of non-obstructive PCS from Magnetic Resonance Imaging (MRI), had sEMG of PFM and who had undergone endovascular treatment. The primary outcome was clinical, defined as a change in symptom severity after endovascular treatment. The secondary outcome was a difference in the sEMG values pre- and post-endovascular therapy. Results: We included 32 women (mean age 38 years). CPP was the leading symptom in 100% patients, followed by dysmenorrhea (75%) and post-coital pain (68.7%). Endovascular therapy included ovarian vein embolization in 28 patients (87.5%) and internal iliac vein embolization in only 2 patients (6.2%). After a median of 8 (range 6–10) months from endovascular treatment, 29 (90%) of patients reported an improvement of the main symptoms, and 15 (46%) were symptom-free. The sEMG values did not show a statistical difference pre- and post-PCS endovascular treatment. Conclusions: Endovascular treatment appeared to be highly effective in CPP due to PCS and was associated with a low rate of complication. sEMG study could be useful in revealing alterations of PFM electrophysiology, but a difference pre- and post-embolization in PCS patients was not demonstrated. Full article

Introduction: Upper-limb loss results in significant functional impairment and a reduced quality of life. A human–machine interface (HMI) using surface electromyography (sEMG) establishes a link between the user and a hand prosthesis to recognize hand gestures and motions. Bio-impedance analysis (BIA) is a non-invasive way of assessing body composition and is adapted for hand motion interpretation with promising results. However, an optimized BIA recording strategy has not yet been achieved due to various parameters (e.g., the large scale of the neuromodulator settings and variations in the tissue dielectric properties). This paper investigates the impact of the dielectric properties of the tissue layers on the bio-impedance variation based on different simulation frequency spectra using the transient modeling method. The model can provide helpful insight into the effect of dielectric properties on the impedance variation of the upper limbs, which is otherwise challenging to investigate in practical studies. Method: The 3D realistic human upper arm model was developed based on the image data set. The dielectric properties of each tissue layer were attained based on each frequency level and the time-based current pulse was applied. The electrical potential variation for each frequency level was recorded to calculate impedance variation based on the applied current level. The unseen current distribution across the upper arm’s fat, muscle, and bone layers under the skin was also simulated to aid in selecting the most responsive area for BIA towards an optimal simulation frequency level. The results were obtained based on 10 Hz, 1 kHz, 10 kHz, 100 kHz, 500 kHz, and 1 MHz levels. Results: The results show that the frequency-based dielectric properties of the tissue layer have a significant impact on impedance variation. Conclusion: In this study, a 3D bio-computational model of the human arm was developed to investigate the impact of dielectric properties on impedance. The results of the study may provide helpful insight into an optimized BIA recording strategy. Full article

Background: Surface electromyography (sEMG) can provide an objective and quantitative image of the functional state of neuromuscular balance in the stomatognathic system. The objective of this systematic review is to examine current scientific evidence regarding the effects of orthodontic treatment on muscle electromyographic (EMG) activity in children. Methods: The search strategy included the PubMed, PubMed Central, Web of Science, Scopus, and Embase databases. The inclusion criteria were studies assessing EMG muscle activity in children undergoing orthodontic treatment compared with untreated children. The Cochrane risk-of-bias tool (RoB2) and the Newcastle–Ottawa Scale (NOS) were used to evaluate the quality of the studies. The quality of evidence assessment was performed using GRADE analysis. The PRISMA diagram visually represented the search strategy, as well as screening and inclusion process. Results: The search strategy identified 540 potential articles. Fourteen papers met the inclusion criteria. Six studies were judged at a low risk of bias. The certainty of evidence was rated as moderate to low, according to the GRADE criteria. Studies showed alterations in EMG muscle activity in children undergoing orthodontic treatment. Conclusions: Orthodontic treatment appears to affect muscle activity in children undergoing orthodontic treatment. However, the quality of evidence is low and, therefore, it is not possible to definitively state this effect. Further long-term studies are needed to confirm the findings of this review. Study protocol number in PROSPERO database: CRD42023491005. Full article

Exercise therapy as part of the clinical management of patients with neuromuscular diseases (NMDs) is complicated by the limited insights into its efficacy. There is an urgent need for sensitive and non-invasive quantitative muscle biomarkers to monitor the effects of exercise training. Therefore, the objective of this systematic review was to critically appraise and summarize the current evidence for the sensitivity of quantitative, non-invasive biomarkers, based on imaging and electrophysiological techniques, for measuring the effects of physical exercise training. We identified a wide variety of biomarkers, including imaging techniques, i.e., magnetic resonance imaging (MRI) and ultrasound, surface electromyography (sEMG), magnetic resonance spectroscopy (MRS), and near-infrared spectroscopy (NIRS). Imaging biomarkers, such as muscle maximum area and muscle thickness, and EMG biomarkers, such as compound muscle action potential (CMAP) amplitude, detected significant changes in muscle morphology and neural adaptations following resistance training. MRS and NIRS biomarkers, such as initial phosphocreatine recovery rate (V), mitochondrial capacity (Q_max), adenosine phosphate recovery half-time (ADP t_1/2), and micromolar changes in deoxygenated hemoglobin and myoglobin concentrations (Δ[deoxy(Hb + Mb)]), detected significant adaptations in oxidative metabolism after endurance training. We also identified biomarkers whose clinical relevance has not yet been assessed due to lack of sufficient study. Full article

The relationship between asymmetrical occlusion and surface electromyographic activity (sEMG) in people with different chewing preferences is not clear. In this study, the 5 s sEMG changes in the masseter muscle (MM), sternocleidomastoid (SCM), lateral (LGA), and medial (MGA) gastrocnemius muscles were recorded in controls, and subjects with chewing side preference (CSP) during clench with bilateral (BCR), left (LCR), and right (RCR) posterior teeth placement of cotton rolls. The images of the middle 3 s were selected and expressed as the root mean square (unit: μV/s). The EMG waves of bilateral muscles were compared by computing the percentage overlapping coefficient (POC). Only the POCMM of the CSP showed gender differences at BCR and RCR. Between the control group and the CSP group, there were significant differences in the POCMM and the POCLGA at BCR. In addition, there was a significant difference in POCMM and POCSCM between the two populations in different occlusal positions. The change in the POCSCM correlated with the change in the POCMM (r = 0.415, p = 0.018). The experiment-induced asymmetrical occlusion showed that the altered symmetry of the MM correlated with the altered symmetry of the SCM. Long-term asymmetrical occlusion (i.e., CSP) not only affects MM but also has potential effects on other superficial muscles (e.g., LGA). Full article

Wearable surface electromyography (sEMG) signal-acquisition devices have considerable potential for medical applications. Signals obtained from sEMG armbands can be used to identify a person’s intentions using machine learning. However, the performance and recognition capabilities of commercially available sEMG armbands are generally limited. This paper presents the design of a wireless high-performance sEMG armband (hereinafter referred to as the α Armband), which has 16 channels and a 16-bit analog-to-digital converter and can reach 2000 samples per second per channel (adjustable) with a bandwidth of 0.1–20 kHz (adjustable). The α Armband can configure parameters and interact with sEMG data through low-power Bluetooth. We collected sEMG data from the forearms of 30 subjects using the α Armband and extracted three different image samples from the time–frequency domain for training and testing convolutional neural networks. The average recognition accuracy for 10 hand gestures was as high as 98.6%, indicating that the α Armband is highly practical and robust, with excellent development potential. Full article