Objective: This study was to investigate alterations in contractile properties of the ankle plantar- and dorsiflexors in post-stroke individuals. The correlation between muscle architecture parameters and contractile properties was also evaluated. Methods: Eight post-stroke individuals and eight age-matched healthy subjects participated in the study. Participants were instructed to perform maximal isometric contraction (MVC) of ankle plantar- and dorsiflexors at four ankle angles, and isokinetic concentric contraction at two angular velocities. B-mode ultrasound images of gastrocnemius medialis (GM) and tibialis anterior (TA) were collected simultaneously during the MVC and isokinetic measurements. Individualized torque-angle and torque-angular velocity relations were established by fitting the experimental data using a second-order polynomial and a rectangular hyperbola function, respectively. Muscle structure parameters, such as fascicle length, muscle thickness and pennation angle of the GM and TA muscles were quantified. Results: Post-stroke subjects had significantly smaller ankle plantarflexor and dorsiflexor torques. The muscle structure parameters also showed a significant change in the stroke group, but no significant difference was observed in the TA muscle. A narrowed parabolic shape of the ankle PF torque-fiber length profile with a lower width span was also found in the stroke group. Conclusion: This study showed that the contractile properties and architecture of ankle muscles in post-stroke individuals undergo considerable changes that may directly contribute to muscle weakness, decreased range of motion, and impaired motion function in individuals after stroke.

Background: A high load on children 's feet can cause arch deformation and negatively affect their normal development. Studies have yet to document how the foot arch varied with different body mass index (BMI) increments and its influence on foot loading patterns.Methods: Barefoot walking trails were conducted using a Footscan (R) plate system. A follow-up check was per-formed after twenty-four months. Participants were selected with an initial BMI between 14.5 kg/m2 and 16.5 kg/m2. Totally 75 participants were classified into groups 0-7 according to the BMI increment levels of 0-0.49 kg/m2, 0.50-1.49 kg/m2, 1.50-2.49 kg/m2, 2.50-3.49 kg/m2, 3.50-4.49 kg/m2, 4.50-5.49 kg/m2, 5.50-6.49 kg/m2, 6.50-7.49 kg/m2, respectively. Paired t-tests and effect sizes were used to compare the data.Results: The arch index significantly decreased when the BMI reached 20.8 kg/m2. Significantly increased normalized maximum forces were found in the great toe and 1st MTPJ in groups 4-5. Meanwhile, the absence of significance showed under the 3rd-5th, midfoot, and rearfoot in those groups. The normalized maximum force increments under the 3rd-5th MTPJs, midfoot and rearfoot regions in groups 4-5 after the follow-up study were significantly decreased compared with the increments found in groups 0-3, followed by a sudden increase arising under those regions in group 6. It indicates a transition period that leads to alteration in gait pattern charac-teristics when BMI increases to 18.6-19.9 kg/m2 (between group 3 and group 4). Group 6 displayed significantly increased peak pressure amplitudes under the great toe, 1st-3rd MTPJs, midfoot, and medial rearfoot compared to other groups.Significance: There was a transition period when the BMI of normal-weighted children increased to a certain extent and failed to reach the obesity level, resulting in changes in foot arch structure and loading patterns.

Accurately predicting joint torque using wearable sensors is crucial for designing assist-as-needed exoskeleton controllers to assist muscle-generated torque and ensure successful task performance. In this paper, we estimated ankle dorsiflexion/plantarflexion, knee flexion/extension, hip flexion/extension, and hip abduction/adduction torques from electromyography (EMG) and kinematics during daily activities using neuromusculoskeletal (NMS) models and long short-term memory (LSTM) networks. The joint torque ground truth for model calibrating and training was obtained through inverse dynamics of captured motion data. A cluster approach that grouped movements based on characteristic similarity was implemented, and its ability to improve the estimation accuracy of both NMS and LSTM models was evaluated. We compared torque estimation accuracy of NMS and LSTM models in three cases: Pooled, Individual, and Clustered models. Pooled models used data from all 10 movements to calibrate or train one model, Individual models used data from each individual movement, and Clustered models used data from each cluster. Individual, Clustered and Pooled LSTM models all had relatively high joint torque estimation accuracy. Individual and Clustered NMS models had similarly good estimation performance whereas the Pooled model may be too generic to satisfy all movement patterns. While the cluster approach improved the estimation accuracy in NMS models in some movements, it made relatively little difference in the LSTM neural networks, which already had high estimation accuracy. Our study provides practical implications for designing assist-as-needed exoskeleton controllers by offering guidelines for selecting the appropriate model for different scenarios, and has potential to enhance the functionality of wearable exoskeletons and improve rehabilitation and assistance for individuals with motor disorders.

Background: Although model personalization is critical when assessing individuals with morphological or neurological abnormalities, or even non-disabled subjects, its translation into routine clinical settings is hampered by the cumbersomeness of experimental data acquisition and lack of resources, which are linked to high costs and long processing pipelines. Quantifying the impact of neglecting subject-specific information in simulations that aim to estimate muscle forces with surface electromyography informed modeling approaches, can address their potential in relevant clinical questions. The present study investigates how different methods to fine-tune subject-specific neuromuscular parameters, reducing the number of electromyography input data, could affect the estimation of the unmeasured excitations and the musculotendon forces. Methods: Three-dimensional motion analysis was performed on 8 non-disabled adult subjects and 13 electromyographic signals captured. Four neuromusculoskeletal models were created for 8 participants: a reference model driven by a large set of sEMG signals; two models informed by four electromyographic signals but calibrated in different fashions; a model based on static optimization. Findings: The electromyography-informed models better predicted experimental excitations, including the unmeasured ones. The model based on static optimization obtained less reliable predictions of the experimental data. When comparing the different reduced models, no major differences were observed, suggesting that the less complex model may suffice for predicting muscle forces with a small set of input in clinical gait analysis tasks. Interpretation: Quantitative model performance evaluation in different conditions provides an objective indication of which method yields the most accurate prediction when a small set of electromyographic recordings is available.

Research interest in exoskeleton assistance strategies that incorporate the user's torque capacity is rapidly growing, yet uncertainty in predicted torque capacity can significantly impact the user-exoskeleton interface safety. In this paper, we estimated knee flexion/extension torques by using a neuromusculoskeletal (NMS) solver-informed Gaussian process (NMS-GP) model with muscle electromyography signals and joint kinematics as model inputs. The NMS-GP model combined the NMS and GP models by integrating valuable features from an NMS solver into a GP model. The NMSGP model was used to predict knee joint torque in daily activities with uncertainty quantification. The activities included slow walking, self-selected speed walking, fast walking, sit-to-stand, and stand-to-sit. Model performance, defined as low prediction error between the model's predicted torque and measured torques from inverse dynamics computations, of both the NMS-GP and NMS models was analyzed. We found that prediction error was significantly lower in NMS-GP models than in NMS models. We observed relatively high uncertainties in the predicted knee torque at the beginning of each movement, particularly in self-selected speed walking. High uncertainties were also found during terminal stance and swing in self-selected speed walking. Compared to other torque prediction methods, the proposed NMS-GP model not only provides an accurate joint torque prediction but also a measure of the uncertainty. Our study showed that the NMS-GP model has a large potential in control strategy design for rehabilitation exoskeletons and to enhance the overall user experience.

Introduction: Research interest in exoskeleton assistance strategies that incorporate the user's torque capacity is growing rapidly. However, the predicted torque capacity from users often includes uncertainty from various sources, which can have a significant impact on the safety of the exoskeleton-user interface. Methods: To address this challenge, this paper proposes an adaptive control framework for a knee exoskeleton that uses muscle electromyography (EMG) signals and joint kinematics. The framework predicted the user's knee flexion/extension torque with confidence bounds to quantify the uncertainty based on a neuromusculoskeletal (NMS) solver-informed Bayesian Neural Network (NMS-BNN). The predicted torque, with a specified confidence level, controlled the assistive torque provided by the exoskeleton through a TCP/IP stream. The performance of the NMS-BNN model was also compared to that of the Gaussian process (NMS-GP) model. Results: Our findings showed that both the NMS-BNN and NMS-GP models accurately predicted knee joint torque with low error, surpassing traditional NMS models. High uncertainties were observed at the beginning of each movement, and at terminal stance and terminal swing in self-selected speed walking in both NMS-BNN and NMS-GP models. The knee exoskeleton provided the desired assistive torque with a low error, although lower torque was observed during terminal stance of fast walking compared to self-selected walking speed. Discussion: The framework developed in this study was able to predict knee flexion/extension torque with quantifiable uncertainty and to provide adaptive assistive torque to the user. This holds significant potential for the development of exoskeletons that provide assistance as needed, with a focus on the safety of the exoskeleton-user interface.

In this work, we predicted ankle joint torque by combining a neuromusculoskeletal (NMS) solver-informed artificial neural network (hybrid-ANN) model with transfer learning based on joint angle and muscle electromyography signals. The hybrid-ANN is an ANN augmented with two kinds of features: 1) experimental measurements - muscle signals and joint angles, and 2) informative physical features extracted from the underlying NMS solver, such as individual muscle force and joint torque. The hybrid-ANN model accuracy in torque prediction was studied in both intra- and inter-subject tests, and compared to the baseline models (NMS and standard-ANN). For each prediction model, seven different cases were studied using data from gait at different speeds and from isokinetic ankle dorsi/plantarflexion motion. Additionally, we integrated a transfer learning method in inter-subject models to improve joint torque prediction accuracy by transferring the learned knowledge from previous participants to a new participant, which could be useful when training data is limited. Our results indicated that better accuracy could be obtained by integrating informative NMS features into a standard ANN model, especially in inter-subject cases; overall, the hybrid-ANN model predicted joint torque with higher accuracy than the baseline models, most notably in inter-subject prediction after adopting the transfer learning technique. We demonstrated the potential of combining physics-based NMS and standard-ANN models with a transfer learning technique in different prediction scenarios. This procedure holds great promise in applications such as assistance-as-needed exoskeleton control strategy design by incorporating the physiological joint torque of the users.

Estimation of joint torque during movement provides important information in several settings, such as effect of athletes' training or of a medical intervention, or analysis of the remaining muscle strength in a wearer of an assistive device. The ability to estimate joint torque during daily activities using wearable sensors is increasingly relevant in such settings. In this study, lower limb joint torques during ten daily activities were predicted by long short-term memory (LSTM) neural networks and transfer learning. LSTM models were trained with muscle electromyography signals and lower limb joint angles. Hip flexion/extension, hip abduction/adduction, knee flexion/extension and ankle dorsiflexion/plantarflexion torques were predicted. The LSTM models' performance in predicting torque was investigated in both intra-subject and inter-subject scenarios. Each scenario was further divided into intra-task and inter-task tests. We observed that LSTM models could predict lower limb joint torques during various activities accurately with relatively low error (root mean square error <= 0.14 Nm/kg, normalized root mean square error <= 8.7%) either through a uniform model or through ten separate models in intra-subject tests. Furthermore, a transfer learning technique was adopted in the inter-task and inter-subject tests to further improve the generalizability of LSTM models by pre-training a model on multiple subjects and/or tasks and transferring the learned knowledge to a target task/subject. Particularly in the inter-subject tests, we could predict joint torques accurately in several movements after training from only a few movements from new subjects.

The generous application of robot-assisted minimally invasive surgery (RAMIS) promotes human-machine interaction (HMI). Identifying various behaviors of doctors can enhance the RAMIS procedure for the redundant robot. It bridges intelligent robot control and activity recognition strategies in the operating room, including hand gestures and human activities. In this paper, to enhance identification in a dynamic situation, we propose a multimodal data fusion framework to provide multiple information for accuracy enhancement. Firstly, a multi-sensors based hardware structure is designed to capture varied data from various devices, including depth camera and smartphone. Furthermore, in different surgical tasks, the robot control mechanism can shift automatically. The experimental results evaluate the efficiency of developing the multimodal framework for RAMIS by comparing it with a single sensor system. Implementing the KUKA LWR4+ in a surgical robot environment indicates that the surgical robot systems can work with medical staff in the future.