Search Results (624)

Surface electromyographic (sEMG) signal-driven joint-angle estimation plays a critical role in intelligent rehabilitation systems, as its accuracy directly affects both control performance and rehabilitation efficacy. This study proposes a continuous elbow joint angle estimation method based on time–frequency domain analysis. Raw sEMG signals were processed using the Short-Time Fourier Transform (STFT) to extract time–frequency features. A Scale Temporal–Channel Cross-Encoder (STCCE) network was developed, integrating temporal and channel attention mechanisms to enhance feature representation and establish the mapping from sEMG signals to elbow joint angles. The model was trained and evaluated on a dataset comprising approximately 103,000 samples collected from seven subjects. In the single-subject test set, the proposed STCCE model achieved an average Mean Absolute Error (MAE) of $2.96\pm {0.24}^{\circ }$, Root Mean Square Error (RMSE) of $4.41\pm {0.45}^{\circ }$, Coefficient of Determination ($R^2$) of $0.9924\pm 0.0020$, and Correlation Coefficient (CC) of $0.9963\pm 0.0010$. It achieved a MAE of ${3.30}^{\circ }$, RMSE of ${4.75}^{\circ }$, $R^2$ of 0.9915, and CC of 0.9962 on the multi-subject test set, and an average MAE of $15.53\pm {1.80}^{\circ }$, RMSE of $21.72\pm {2.85}^{\circ }$, $R^2$ of $0.8141\pm 0.0540$, and CC of $0.9100\pm 0.0306$ on the inter-subject test set. These results demonstrated that the STCCE model enabled accurate joint-angle estimation in the time–frequency domain, contributing to a better motion intent perception for upper-limb rehabilitation. Full article

Accurate estimation of upper-limb joint angles is essential in biomechanics, rehabilitation, and wearable robotics. While inertial measurement units (IMUs) offer portability and flexibility, systems requiring multiple inertial sensors can be intrusive and complex to deploy. In contrast, optical motion capture (MoCap) systems provide precise tracking but are constrained to controlled laboratory environments. This study presents a deep learning-based approach for estimating shoulder and elbow joint angles using only three IMU sensors positioned on the chest and both wrists, validated against reference angles obtained from a MoCap system. The input data includes Euler angles, accelerometer, and gyroscope data, synchronized and segmented into sliding windows. Two recurrent neural network architectures, Convolutional Neural Network with Long-short Term Memory (CNN-LSTM) and Bidirectional LSTM (BLSTM), were trained and evaluated using identical conditions. The CNN component enabled the LSTM to extract spatial features that enhance sequential pattern learning, improving angle reconstruction. Both models achieved accurate estimation performance: CNN-LSTM yielded lower Mean Absolute Error (MAE) in smooth trajectories, while BLSTM provided smoother predictions but underestimated some peak movements, especially in the primary axes of rotation. These findings support the development of scalable, deep learning-based wearable systems and contribute to future applications in clinical assessment, sports performance analysis, and human motion research. Full article

Stroke often leads to severe motor impairment, especially in the upper limbs, greatly reducing a patient’s ability to perform daily tasks. Effective rehabilitation is essential to restore function and improve quality of life. Traditional therapies, while useful, may lack engagement, leading to low motivation and poor adherence. Gamification—using game-like elements in non-game contexts—offers a promising way to make rehabilitation more engaging. The authors explore a gamified rehabilitation system designed in Unity 3D using a Kinect V2 camera. The game includes key features such as adjustable difficulty, real-time and predominantly positive feedback, user friendliness, and data tracking for progress. The evaluations were conducted with 18 healthy participants, most of whom had prior virtual reality experience. About 77% found the application highly motivating. While the gameplay was well received, the visual design was noted as lacking engagement. Importantly, all users agreed that the game offers a broad range of difficulty levels, making it accessible to various users. The results suggest that the system has strong potential to improve rehabilitation outcomes and encourage long-term use through enhanced motivation and interactivity. Full article

Background/Objectives: Peripheral artery disease (PAD) impacts more than 200 million individuals globally and leads to mortality and morbidity secondary to progressive limb dysfunction and amputation. However, clinical management of PAD remains suboptimal, in part because of the lack of standardized biomarkers to predict patient outcomes. Growth differentiation factor 15 (GDF15) is a stress-responsive cytokine that has been studied extensively in cardiovascular disease, but its investigation in PAD remains limited. This study aimed to use explainable statistical and machine learning methods to assess the prognostic value of GDF15 for limb outcomes in patients with PAD. Methods: This prognostic investigation was carried out using a prospectively enrolled cohort comprising 454 patients diagnosed with PAD. At baseline, plasma GDF15 levels were measured using a validated multiplex immunoassay. Participants were monitored over a two-year period to assess the occurrence of major adverse limb events (MALE), a composite outcome encompassing major lower extremity amputation, need for open/endovascular revascularization, or acute limb ischemia. An Extreme Gradient Boosting (XGBoost) model was trained to predict 2-year MALE using 10-fold cross-validation, incorporating GDF15 levels along with baseline variables. Model performance was primarily evaluated using the area under the receiver operating characteristic curve (AUROC). Secondary model evaluation metrics were accuracy, sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Prediction histogram plots were generated to assess the ability of the model to discriminate between patients who develop vs. do not develop 2-year MALE. For model interpretability, SHapley Additive exPlanations (SHAP) analysis was performed to evaluate the relative contribution of each predictor to model outputs. Results: The mean age of the cohort was 71 (SD 10) years, with 31% (n = 139) being female. Over the two-year follow-up period, 157 patients (34.6%) experienced MALE. The XGBoost model incorporating plasma GDF15 levels and demographic/clinical features achieved excellent performance for predicting 2-year MALE in PAD patients: AUROC 0.84, accuracy 83.5%, sensitivity 83.6%, specificity 83.7%, PPV 87.3%, and NPV 86.2%. The prediction probability histogram for the XGBoost model demonstrated clear separation for patients who developed vs. did not develop 2-year MALE, indicating strong discrimination ability. SHAP analysis showed that GDF15 was the strongest predictive feature for 2-year MALE, followed by age, smoking status, and other cardiovascular comorbidities, highlighting its clinical relevance. Conclusions: Using explainable statistical and machine learning methods, we demonstrated that plasma GDF15 levels have important prognostic value for 2-year MALE in patients with PAD. By integrating clinical variables with GDF15 levels, our machine learning model can support early identification of PAD patients at elevated risk for adverse limb events, facilitating timely referral to vascular specialists and aiding in decisions regarding the aggressiveness of medical/surgical treatment. This precision medicine approach based on a biomarker-guided prognostication algorithm offers a promising strategy for improving limb outcomes in individuals with PAD. Full article

SGLT2 inhibitors have become increasingly used due to their effectiveness in improving not only type 2 diabetes but also cardiovascular, renal and hepatic diseases, as well as the obesity found in metabolic syndrome. Starting from the structure of gliflozins, modifications of the carbohydrate part, aglycone, and also the glycosidic bond between them can determine variations in pharmacokinetic and pharmacodynamic properties. SGLT2 inhibitors, in addition to reducing blood glucose levels, improve alterations in lipid metabolism by diverting excessively accumulated lipids in tissues towards mobilization, lipolysis, β-oxidation, ketogenesis and the utilization of ketone bodies. This enhances anti-inflammatory properties by decreasing the levels of some proinflammatory mediators and by modulating some cell signaling pathways. Thus, in this review, the intimate mechanisms by which SGLT2 inhibitors achieve these therapeutic effects in the various conditions belonging to metabolic syndrome and beyond were described, along with the structure–effect relationship with some specific features of each gliflozin. Starting from these findings, further modeling of these molecules may lead to the creation of new therapeutic uses. Further research is needed to broaden the range of indications and also eliminate adverse effects, such as phenomena leading to lower limb amputations. Full article

Maintaining body symmetry in sports characterized by high lateralization is crucial for optimizing long-term athletic performance and mitigating injury risk. This study aimed to evaluate the extent of morphological asymmetry in anthropometric features among elite professional fencers. Additionally, the presence of functional asymmetry and its associations with morphological asymmetry were assessed. Thirty-two Polish adult female fencers, aged 18–33 yrs, were examined. Data collection involved a questionnaire survey, anthropometric measurements, calculation of anthropological indices, and assessment of functional asymmetry. For the 24 bilateral anthropometric features, small differences were found in seven characteristics: foot length, subscapular skinfold thickness, upper arm circumference, minimum and maximum forearm circumference, upper limb length, and arm circumference in tension. Morphological asymmetry index did not exceed 5%. Left-sided lateralization of either the upper or lower limbs was associated with significantly high asymmetry, specifically indicating larger minimum forearm circumferences in the right limb. Continuous, individualized monitoring of morphological asymmetry and its direction in athletes is essential, demanding concurrent consideration of functional lateralization. This ongoing assessment establishes a critical baseline for evaluating training adaptations, reducing injury susceptibility, and optimizing rehabilitation strategies. Deeper investigation of symmetry within non-dominant limbs is warranted to enhance our understanding. Full article

Accurate detection of fractures in X-ray images is important to initiate appropriate medical treatment in time—in this study, an advanced combined attention CNN model with multiple attention mechanisms was developed to improve fracture detection by deeply representing features. Specifically, our model incorporates squeeze blocks and convolutional block attention module (CBAM) blocks to improve the model’s ability to focus on relevant features in X-ray images. Using computed tomography X-ray images, this study assesses the diagnostic efficacy of the artificial intelligence (AI) model before and after optimization and compares its performance in detecting fractures or not. The training and evaluation dataset consists of fractured and non-fractured X-rays from various anatomical locations, including the hips, knees, lumbar region, lower limb, and upper limb. This gives an extremely high training accuracy of 99.98 and a validation accuracy 96.72. The attention-based CNN thus showcases its role in medical image analysis. This aspect further complements a point we highlighted through our research to establish the role of attention in CNN architecture-based models to achieve the desired score for fracture in a medical image, allowing the model to generalize. This study represents the first steps to improve fracture detection automatically. It also brings solid support to doctors addressing the continued time to examination, which also increases accuracy in diagnosing fractures, improving patients’ outcomes significantly. Full article

Series elastic actuators (SEAs) represent a key technological solution to enhance safety, performance, and adaptability in robotic devices for physical training. Their ability to decouple the rigid actuator’s mechanical impedance from the load, combined with passive absorption of external disturbances, makes them particularly suitable for pediatric applications. In children aged 2 to 5 years—where motor control is still developing and movements can be unpredictable or unstructured—SEAs provide a compliant mechanical response that ensures user protection and enables safe physical interaction. This study explores the role of SEAs as a central component for imparting compliance and backdrivability in robotic systems designed for upper-limb training. A dynamic model is proposed, incorporating interaction with the user’s limb, along with a computed torque control strategy featuring integral action. The system’s performance is validated through simulations and experimental tests, demonstrating stable trajectory tracking, disturbance absorption, and effective impedance decoupling. The results support the use of SEAs as a foundational technology for developing safe adaptive robotic solutions in pediatric contexts capable of responding flexibly to user variability and promoting secure interaction in early motor development environments. Full article

Background/Objectives: The co-existence of multiple compression sites on the same nerve can pose a clinical and diagnostic challenge, warranting a different treatment strategy. This so-called double crush syndrome (DCS) has mainly been investigated in the upper limb. Only a few studies have investigated DCS for the lower limb. In this article, a single-center illustrative clinical case series is presented, and current literature on L5 nerve root (NR) and concomitant common peroneal nerve (CPN) is reviewed. Methods: All patients presenting between 2019 and 2022 with L5 nerve root (NR) compression and, along their clinical courses, concomitant compression of the common peroneal nerve (CPN) at the fibular head were included. Information on clinical features, diagnostics and surgeries was obtained. The outcome was assessed at the last outpatient follow-up appointment. In addition, an extensive literature review has been conducted. Results: Fourteen patients were included with a mean follow-up of 6.8 months. The majority had pain (71%) or motor deficits (71%). Seven patients were referred for clinical and radiological L5 NR compression but were also found to have CPN compression; the other seven patients had persisting or recurrent symptoms after surgically or conservatively treated L5 NR compression, suggestive of additional peroneal neuropathy. All patients had CPN decompression at the fibular head, with successful results obtained in 93% of the patients. Pain of the lower leg improved in all patients, and dorsiflexion function improved in 78%. Conclusions: Concomitant L5 NR and CPN appear to occur more frequently than expected. Peroneal neuropathy can present simultaneously with L5 nerve radiculopathy or after surgically or conservatively treated L5 NR compression. Overlapping symptoms and variation in clinical presentations make it difficult to diagnose and, therefore, underrecognized. More awareness among treating physicians of this specific double crush syndrome is important to prevent any delay in treatment, in this case, a less invasive common peroneal nerve release at the fibular head, and to avoid unnecessary (additional) spinal surgery. Full article

This study proposes a hybrid approach combining threshold-based algorithm and deep learning to detect four major gait events—initial contact (IC), toe-off (TO), opposite initial contact (OIC), and opposite toe-off (OTO)—using only a smartphone’s built-in inertial sensor placed in the user’s pocket. The algorithm enables estimation of spatiotemporal gait parameters such as cadence, stride length, loading response (LR), pre-swing (PSw), single limb support (SLS), double limb support (DLS), and swing phase and symmetry. Gait data were collected from 20 healthy individuals and 13 hemiparetic stroke patients. To reduce sensitivity to sensor orientation and suppress noise, sum vector magnitude (SVM) features were extracted and filtered using a second-order Butterworth low-pass filter at 3 Hz. A deep learning model was further compressed using knowledge distillation, reducing model size by 96% while preserving accuracy. The proposed method achieved error rates in event detection below 2% of the gait cycle for healthy gait and a maximum of 4.4% for patient gait in event detection, with corresponding parameter estimation errors also within 4%. These results demonstrated the feasibility of accurate and real-time gait monitoring using a smartphone. In addition, statistical analysis of gait parameters such as symmetry and DLS revealed significant differences between the normal and patient groups. While this study is not intended to provide or guide rehabilitation treatment, it offers a practical means to regularly monitor patients’ gait status and observe gait recovery trends over time. Full article

Sign language is a complex and dynamic visual language that requires the coordinated movement of various body parts, such as the hands, arms, and limbs—making it an ideal application domain for sensor networks to capture and interpret human gestures accurately. To address the intricate task of precise and expedient SLR from raw videos, this study introduces a novel deep learning approach by devising a multimodal framework for SLR. Specifically, feature extraction models are built based on two modalities: skeleton and RGB images. In this paper, we firstly propose a Multi-Stream Spatio-Temporal Graph Convolutional Network (MSGCN) that relies on three modules: a decoupling graph convolutional network, a self-emphasizing temporal convolutional network, and a spatio-temporal joint attention module. These modules are combined to capture the spatio-temporal information in multi-stream skeleton features. Secondly, we propose a 3D ResNet model based on deformable convolution (D-ResNet) to model complex spatial and temporal sequences in the original raw images. Finally, a gating mechanism-based Multi-Stream Fusion Module (MFM) is employed to merge the results of the two modalities. Extensive experiments are conducted on the public datasets AUTSL and WLASL, achieving competitive results compared to state-of-the-art systems. Full article

Extraterrestrial exploration presents unique challenges for robotic systems, as traditional rigid rovers face limitations in stowage volume, traction on unpredictable terrain, and susceptibility to damage. Soft robotics offers promising solutions through bio-inspired designs that can mimic natural locomotion mechanisms. Here, we present an optimised, spider-inspired soft jumping robot for extraterrestrial exploration that addresses key challenges in soft robotics: actuation efficiency, controllability, and deployment. Drawing inspiration from spider physiology—particularly their hydraulic extension mechanism—we develop a lightweight limb capable of multi-modal behaviour with significantly reduced energy requirements. Our 3D-printed soft actuator leverages pressure-driven collapse for efficient retraction and pressure-enhanced rapid extension, achieving a power-to-weight ratio of 249 W/kg. The integration of a non-backdriveable clutch mechanism enables the system to hold positions with zero energy expenditure—a critical feature for space applications. Experimental characterisation and a subsequent optimisation methodology across various materials, dimensions, and pressures reveal that the robot can achieve jumping heights of up to 1.86 times its body length. The collapsible nature of the soft limb enables efficient stowage during spacecraft transit, while the integrated pumping system facilitates self-deployment upon arrival. This work demonstrates how biologically inspired design principles can be effectively applied to develop versatile robotic systems optimised for the unique constraints of extraterrestrial exploration. Full article

Background: The coordination between the upper and lower limbs is essential for athletic performance. However, the structural features that influence coordination difficulty remain insufficiently understood. Few studies have systematically analyzed how task components such as the directional congruence or rhythm structure affect inter-limb coordination. Objective: This study aimed to clarify the structural factors that influence the difficulty of upper–lower limb coordination tasks under rhythmic constraints and to explore the feasibility of applying such tasks in future coordination assessments. Methods: Eighty-six male high school baseball players performed six Rhythm Jump tasks combining fixed upper limb movements with varying lower limb patterns. The task performance was analyzed using three indices: full task success, partial success, and average successful series. One year later, a follow-up test involving 27 participants was conducted to evaluate the reproducibility and sensitivity to the performance change. Results: The task difficulty was significantly affected by structural features, including directional incongruence, upper limb static holding, and rhythmic asynchrony. The tasks that exhibited these features had lower success rates. Some tasks demonstrated moderate reproducibility and captured subtle longitudinal changes in the performance. Conclusions: The results highlight the key structural factors contributing to coordination difficulty and support the potential applicability of Rhythm Jump tasks as a basis for future assessment tools. Although further validation is necessary, this study provides foundational evidence for the development of practical methods for evaluating inter-limb coordination. Full article

Parkinson’s disease (PD) is a neurodegenerative disorder commonly marked by upper limb tremors that interfere with daily activities. Wearable devices, such as smartwatches, represent a promising solution for continuous and objective monitoring in PD. This study aimed to develop and validate a tremor-detection algorithm using smartwatch sensors. Data were collected from 21 individuals with PD and 27 healthy controls using both a commercial inertial measurement unit (G-Sensor, BTS Bioengineering, Italy) and a smartwatch (Apple Watch Series 3). Participants performed standardized arm movements while sensor signals were synchronized and processed to extract relevant features. Statistical analyses assessed discriminant and concurrent validity, reliability, and accuracy. The algorithm demonstrated moderate to strong correlations between smartwatch and commercial IMU data, effectively distinguishing individuals with PD from healthy controls showing associations with clinical measures, such as the MDS-UPDRS III. Reliability analysis demonstrated agreement between repeated measurements, although a proportional bias was noted. Power spectral density (PSD) analysis of accelerometer and gyroscope data along the x-axis successfully detected the presence of tremors. These findings support the use of smartwatches as a tool for detecting tremors in PD. However, further studies involving larger and more clinically impaired samples are needed to confirm the robustness and generalizability of these results. Full article

Brain–Computer Interfaces (BCIs) enable direct communication between the brain and external devices by decoding motor intentions from EEG signals. However, the existing multi-class classification methods for motor imagery EEG (MI-EEG) signals are hindered by low signal quality and limited accuracy, restricting their practical application. This study focuses on rehabilitation training scenarios, aiming to capture the motor intentions of patients with partial or complete motor impairments (such as stroke survivors) and provide feedforward control commands for exoskeletons. This study developed an EEG acquisition protocol specifically for use with lower-limb rehabilitation motor imagery (MI). It systematically explored preprocessing techniques, feature extraction strategies, and multi-classification algorithms for multi-task MI-EEG signals. A novel 3D EEG convolutional neural network (3D EEG-CNN) that integrates time/frequency features is proposed. Evaluations on a self-collected dataset demonstrated that the proposed model achieved a peak classification accuracy of 66.32%, substantially outperforming conventional approaches and demonstrating notable progress in the multi-class classification of lower-limb motor imagery tasks. Full article