Kinematics, Speed, and Anthropometry-Based Ankle Joint Torque Estimation: A Deep Learning Regression Approach

A Motion Capture Dataset on Human Sitting to Walking Transitions

Sit-to-walk (STW) is a crucial daily task that impacts mobility, independence, and thus quality of life. Existing repositories have limited STW data with small sample sizes (n = 10). Hence, this study presents a STW dataset obtained via the time-up-and-go test, for 65 healthy adults across three age groups - young (19-35 years), middle (36-55 years) and older (above 56 years). The dataset contains lower body motion capture, ground reaction force, surface electromyography, inertial measurement unit data, and responses for the knee injury and osteoarthritis outcome score survey. For validation, the within subjects intraclass correlation coefficients for the maximum and minimum lower body joint angles were calculated with values greater than 0.74, indicating good test-retest reliability. The joint angle trajectories and maximum voluntary contractions are comparable with existing literature, matching in overall trends and range. Accordingly, this dataset allows STW biomechanics, executions, and characteristics to be studied across age groups. Biomechanical trajectories of healthy adults serve as a benchmark in assessing neuromusculoskeletal impairments and when designing assistive technology for treatment or rehabilitation.

Exploratory analysis using machine learning algorithms to predict pinch strength by anthropometric and socio-demographic features

Objectives. This study examines the role of different machine learning (ML) algorithms to determine which socio-demographic factors and hand-forearm anthropometric dimensions can be used to accurately predict hand function. Methods. The cross-sectional study was conducted with 7119 healthy Iranian participants (3525 males and 3594 females) aged 10-89 years. Seventeen hand-forearm anthropometric dimensions were measured by JEGS digital caliper and a measuring tape. Tip-to-tip, key and three-jaw chuck pinches were measured using a calibrated pinch gauge. Subsequently, 21 features pertinent to socio-demographic factors and hand-forearm anthropometric dimensions were used for classification. Furthermore, 12 well-known classifiers were implemented and evaluated to predict pinches. Results. Among the 21 features considered in this study, hand length, stature, age, thumb length and index finger length were found to be the most relevant and effective components for each of the three pinch predictions. The k-nearest neighbor, adaptive boosting (AdaBoost) and random forest classifiers achieved the highest classification accuracy of 96.75, 86.49 and 84.66% to predict three pinches, respectively. Conclusions. Predicting pinch strength and determining the predictive hand-forearm anthropometric and socio-demographic characteristics using ML may pave the way to designing an enhanced tool handle and reduce common musculoskeletal disorders of the hand.

Prediction of Gait Kinematics and Kinetics: A Systematic Review of EMG and EEG Signal Use and Their Contribution to Prediction Accuracy

Human-machine interfaces hold promise in enhancing rehabilitation by predicting and responding to subjects' movement intent. In gait rehabilitation, neural network architectures utilize lower-limb muscle and brain activity to predict continuous kinematics and kinetics during stepping and walking. This systematic review, spanning five databases, assessed 16 papers meeting inclusion criteria. Studies predicted lower-limb kinematics and kinetics using electroencephalograms (EEGs), electromyograms (EMGs), or a combination with kinematic data and anthropological parameters. Long short-term memory (LSTM) and convolutional neural network (CNN) tools demonstrated highest accuracies. EEG focused on joint angles, while EMG predicted moments and torque joints. Useful EEG electrode locations included C3, C4, Cz, P3, F4, and F8. Vastus Lateralis, Rectus Femoris, and Gastrocnemius were the most commonly accessed muscles for kinematic and kinetic prediction using EMGs. No studies combining EEGs and EMGs to predict lower-limb kinematics and kinetics during stepping or walking were found, suggesting a potential avenue for future development in this technology.

Sit-to-walk strategy classification in healthy adults using hip and knee joint angles at gait initiation

Forward continuation, balance, and sit-to-stand-and-walk (STSW) are three common movement strategies during sit-to-walk (STW) executions. Literature identifies these strategies through biomechanical parameters using gold standard laboratory equipment, which is expensive, bulky, and requires significant post-processing. STW strategy becomes apparent at gait-initiation (GI) and the hip/knee are primary contributors in STW, therefore, this study proposes to use the hip/knee joint angles at GI as an alternate method of strategy classification. To achieve this, K-means clustering was implemented using three clusters corresponding to the three STW strategies; and two feature sets corresponding to the hip/knee angles (derived from motion capture data); from an open access online database (age: 21-80 years; n = 10). The results identified forward continuation with the lowest hip/knee extension, followed by balance and then STSW, at GI. Using this classification, strategy biomechanics were investigated by deriving the established biomechanical quantities from literature. The biomechanical parameters that significantly varied between strategies (P < 0.05) were time, horizontal centre of mass (COM) momentum, braking impulse, centre of pressure (COP) range and velocities, COP-COM separation, hip/knee torque and movement fluency. This alternate method of strategy classification forms a generalized framework for describing STW executions and is consistent with literature, thus validating the joint angle classification method.

Analysis of technical characteristics of typical lower limb balance movements in Tai Chi: a cross-sectional study based on AnyBody bone muscle modeling

BACKGROUND

Tai Chi is an excellent traditional Chinese physical fitness exercise, and its unique balancing movements are very important for improving human balance. In this study, the two most representative Tai Chi balance movements, "knee lift balance" and "leg stirrup balance", were selected to establish the lower limb bone muscle model of Tai Chi balance movements by using computer simulation modeling technology, aiming to analyze the characteristics of the lower limb movement mechanisms of typical balance movements, to provide a quantitative theoretical basis for improving the scientific level of Tai Chi.

METHOD

A total of 16 subjects were recruited for this study. the BTS three-dimensional motion capture system and three-dimensional force platform were used for motion data acquisition, the physiological electromyographic signals were collected using BTS surface electromyography, and the lower limb bone muscle model of Tai Chi balance movements was established by AnyBody human simulation.

RESULT

In the knee lift balancing movement, the balance leg hip abduction/adduction angle, hip flexion/extension moment, and the strength of the rectus femoris muscle, biceps femoris short capitis, and iliacus muscle of the amateur group was significantly smaller than that of the professional group (P < 0.01). In the leg stirrup balance movement, the knee flexion/extension angle of the balancing leg in the amateur group was significantly greater than that in the professional group (P < 0.01), and the hip flexion/extension angle, hip inversion/abduction angle, knee flexion/extension moment, hip flexion/extension moment, the strength iliacus, gluteus maximus, and obturator internus were significantly smaller than those in the professional group (P < 0.01). The integral EMG of the biceps femoris of the support leg in the amateur group was significantly smaller than that of the professional group (P < 0.01). The integral EMG of the lateral femoral muscle of the balance leg was significantly smaller than that of the professional group (P < 0.01).

CONCLUSION

In this study, we found that the balancing leg of the balancing movement has a larger hip joint angle, the stirrup balancing knee joint angle is smaller, and the hip and knee joint moments are larger. This is related to joint activity and muscle activation, and amateurs should pay attention to increasing the range of motion of the hip joint and decreasing the range of motion of the knee joint when practicing to better stimulate exercise of the lower limb joints. In addition, the practice of balancing movements should strengthen the iliacus muscle, which plays an important role in maintaining the stable balance of the lower limbs, and strengthen the knee flexor and extensor muscles and hip adductor/abductor muscles of the balancing leg, thus promoting the stability of the balancing leg movements.

A Two-Degree-of-Freedom Knee Model Predicts Full Three-Dimensional Tibiofemoral and Patellofemoral Joint Motion During Functional Activity

Six kinematic parameters are needed to fully describe three-dimensional (3D) bone motion at a joint. At the knee, the relative movements of the femur and tibia are often represented by a 1-degree-of-freedom (1-DOF) model with a single flexion-extension axis or a 2-DOF model comprising a flexion-extension axis and an internal-external rotation axis. The primary aim of this study was to determine the accuracy with which 1-DOF and 2-DOF models predict the 3D movements of the femur, tibia and patella during daily activities. Each model was created by fitting polynomial functions to 3D tibiofemoral (TF) and patellofemoral (PF) kinematic data recorded from 10 healthy individuals performing 6 functional activities. Model cross-validation analyses showed that the 2-DOF model predicted 3D knee kinematics more accurately than the 1-DOF model. At the TF joint, mean root-mean-square (RMS) errors across all activities and all participants were 3.4°|mm (deg or mm) for the 1-DOF model and 2.4°|mm for the 2-DOF model. At the PF joint, mean RMS errors were 4.0°|mm and 3.9°|mm for the 1-DOF and 2-DOF models, respectively. These results indicate that a 2-DOF model with two rotations as inputs may be used with confidence to predict the full 3D motion of the knee-joint complex.

A Review on Locomotion Mode Recognition and Prediction When Using Active Orthoses and Exoskeletons

Understanding how to seamlessly adapt the assistance of lower-limb wearable assistive devices (active orthosis (AOs) and exoskeletons) to human locomotion modes (LMs) is challenging. Several algorithms and sensors have been explored to recognize and predict the users' LMs. Nevertheless, it is not yet clear which are the most used and effective sensor and classifier configurations in AOs/exoskeletons and how these devices' control is adapted according to the decoded LMs. To explore these aspects, we performed a systematic review by electronic search in Scopus and Web of Science databases, including published studies from 1 January 2010 to 31 August 2022. Sixteen studies were included and scored with 84.7 ± 8.7% quality. Decoding focused on level-ground walking along with ascent/descent stairs tasks performed by healthy subjects. Time-domain raw data from inertial measurement unit sensors were the most used data. Different classifiers were employed considering the LMs to decode (accuracy above 90% for all tasks). Five studies have adapted the assistance of AOs/exoskeletons attending to the decoded LM, in which only one study predicted the new LM before its occurrence. Future research is encouraged to develop decoding tools considering data from people with lower-limb impairments walking at self-selected speeds while performing daily LMs with AOs/exoskeletons.

Performance of Deep Learning Models in Forecasting Gait Trajectories of Children with Neurological Disorders

Forecasted gait trajectories of children could be used as feedforward input to control lower limb robotic devices, such as exoskeletons and actuated orthotic devices (e.g., Powered Ankle Foot Orthosis—PAFO). Several studies have forecasted healthy gait trajectories, but, to the best of our knowledge, none have forecasted gait trajectories of children with pathological gait yet. These exhibit higher inter- and intra-subject variability compared to typically developing gait of healthy subjects. Pathological trajectories represent the typical gait patterns that rehabilitative exoskeletons and actuated orthoses would target. In this study, we implemented two deep learning models, a Long-Term Short Memory (LSTM) and a Convolutional Neural Network (CNN), to forecast hip, knee, and ankle trajectories in terms of corresponding Euler angles in the pitch, roll, and yaw form for children with neurological disorders, up to 200 ms in the future. The deep learning models implemented in our study are trained on data (available online) from children with neurological disorders collected by Gillette Children’s Speciality Healthcare over the years 1994–2017. The children’s ages range from 4 to 19 years old and the majority of them had cerebral palsy (73%), while the rest were a combination of neurological, developmental, orthopaedic, and genetic disorders (27%). Data were recorded with a motion capture system (VICON) with a sampling frequency of 120 Hz while walking for 15 m. We investigated a total of 35 combinations of input and output time-frames, with window sizes for input vectors ranging from 50–1000 ms, and output vectors from 8.33–200 ms. Results show that LSTMs outperform CNNs, and the gap in performance becomes greater the larger the input and output window sizes are. The maximum difference between the Mean Absolute Errors (MAEs) of the CNN and LSTM networks was 0.91 degrees. Results also show that the input size has no significant influence on mean prediction errors when the output window is 50 ms or smaller. For output window sizes greater than 50 ms, the larger the input window, the lower the error. Overall, we obtained MAEs ranging from 0.095–2.531 degrees for the LSTM network, and from 0.129–2.840 degrees for the CNN. This study establishes the feasibility of forecasting pathological gait trajectories of children which could be integrated with exoskeleton control systems and experimentally explores the characteristics of such intelligent systems under varying input and output window time-frames.

Assist-As-Needed Control Strategy of Bilateral Upper Limb Rehabilitation Robot Based on GMM

Robotic-assisted rehabilitation therapy has been shown to be effective in improving upper limb motor function and the daily behavior of patients with motor dysfunction. At present, the majority of upper limb rehabilitation robots can only move in the two-dimensional plane, and cannot adjust the assistance mode in real-time according to the patient’s rehabilitation needs. In this paper, according to the shortcomings of the current rehabilitation robot only moving in the two-dimensional plane, a type of bilateral mirror upper limb rehabilitation robot structure with the healthy side assisting the affected side is proposed. This can move in three-dimensional space. Additionally, an assist-as-needed (AAN) control strategy for upper limb rehabilitation training is proposed based on the bilateral upper limb rehabilitation robot. The control strategy adopts Gaussian Mixture Model (GMM) and impedance controller to maximize the patient’s rehabilitation effect. In the task’s design, there is no need to rely on the assistance of the therapist, only the patients who completed the task independently. GMM guides the rehabilitation robot to provide different assistance for the patients at different task stages and induces the patients to complete the rehabilitation training independently by judging the extent to which the patients can complete the task. Furthermore, in this paper, the effectiveness of the proposed control strategy was verified by three volunteers participating in a two-dimensional task. The experimental results show that the proposed AAN control strategy can effectively provide appropriate assistance according to the classification stage of the interaction between the patients and the rehabilitation robot, and thus, patients can better achieve the rehabilitation effect during the rehabilitation task as much as possible.

PMSM Speed Control Based on Particle Swarm Optimization and Deep Deterministic Policy Gradient under Load Disturbance

Proportional integral-based particle swarm optimization (PSO) and deep deterministic policy gradient (DDPG) algorithms are applied to a permanent-magnet synchronous motor to track speed control. The proposed methods, based on notebooks, can deal with time delay challenges, imprecise mathematical models, and unknown disturbance loads. First, a system identification method is used to obtain an approximate model of the motor. The load and speed estimation equations can be determined using the model. By adding the estimation equations, the PSO algorithm can determine the sub-optimized parameters of the proportional-integral controller using the predicted speed response; however, the computational time and consistency challenges of the PSO algorithm are extremely dependent on the number of particles and iterations. Hence, an online-learning method, DDPG, combined with the PSO algorithm is proposed to improve the speed control performance. Finally, the proposed methods are implemented on a real platform, and the experimental results are presented and discussed.