Explore the vast range of titles available.

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body’s movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively.

To enable exoskeleton wearers to walk on level ground, estimation of lower limb movement is particularly indispensable. In fact, it allows the exoskeleton to follow the human movement in real time. In this paper, the general regression neural network optimized by golden section algorithm (GS-GRNN) is used to realize prediction of the human lower limb joint angle. The human body hip joint angle and the surface electromyographic (sEMG) signals of the thigh muscles are taken as the inputs of a neural network to predict joint angles of lower limbs. To improve the prediction accuracy in different gait phases, the plantar pressure signals are also added into the input. After that, the error between the prediction result and the actual data decreases significantly. Finally, compared with the prediction result of the BP neural network, GRNN shows splendid prediction performance for its less processing time and higher prediction accuracy.

In the current study, our research group proposed an asymmetric lower extremity exoskeleton to enable above-knee amputees to walk with a load. Due to the absence of shank and foot, the knee and ankle joint at the amputation side of the exoskeleton lack tracking targets, so it is difficult to realize the function of assisted walking when going up and downstairs. Currently, the use of lower-limb electromyography to predict the angles of lower limb joints has achieved remarkable results. However, the prediction effect was poor when only using electromyography from the thigh. Therefore, this paper introduces hip-angle and plantar pressure signals for improving prediction effect and puts forward a joint prediction method of knee- and ankle-joint angles by electromyography of the thigh, hip-joint angle, and plantar pressure signals. The generalized regression neural network optimized by the golden section method is used to predict the joint angles. Finally, the parameters (the maximum error, the Root-Mean-Square error (RMSE), and correlation coefficient (γ)) were calculated to verify the feasibility of the prediction method.

Background Prosthetic restoration of reach and grasp function after a trans-humeral amputation requires control of multiple distal degrees of freedom in elbow, wrist and fingers. However, such a high level of amputation reduces the amount of available myoelectric and kinematic information from the residual limb. Methods To overcome these limits, we added contextual information about the target’s location and orientation such as can now be extracted from gaze tracking by computer vision tools. For the task of picking and placing a bottle in various positions and orientations in a 3D virtual scene, we trained artificial neural networks to predict postures of an intact subject’s elbow, forearm and wrist (4 degrees of freedom) either solely from shoulder kinematics or with additional knowledge of the movement goal. Subjects then performed the same tasks in the virtual scene with distal joints predicted from the context-aware network. Results Average movement times of 1.22s were only slightly longer than the naturally controlled movements (0.82 s). When using a kinematic-only network, movement times were much longer (2.31s) and compensatory movements from trunk and shoulder were much larger. Integrating contextual information also gave rise to motor synergies closer to natural joint coordination. Conclusions Although notable challenges remain before applying the proposed control scheme to a real-world prosthesis, our study shows that adding contextual information to command signals greatly improves prediction of distal joint angles for prosthetic control.

Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user's natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG. This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle. The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19. This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

System delay caused by mechanical transmission, control calculation and data communication are the main factor affecting the man-machine collaborative control of lower extremity exoskeleton. Improved Particle Swarm Optimization Algorithm (IPSO) was proposed to optimize BPNN (Back Propagation Neural Network) to predict the future joint angle of human lower limb. The 3d motion capture system was used to collect the Angle data of human lower limb joints, and time span was added to reconstruct the time series, which was taken as the input of the model. Compared to PSO (Particle Swarm Optimization), IPSO added a three-route competitive optimization trajectory, the training feedback of BPNN and mutation operation, which accelerated the convergence of the algorithm and avoided local optimization. Besides, we established a prediction evaluation criterion with prediction duration, iteration efficiency, Root Mean Square Error (RMSE) and Determination Coefficient (DC) as the core to analyze the prediction results of BPNN, PSO-BPNN (Support Back Propagation Neural Network by Particle Swarm Optimization) and IPSO-BPNN (Support Back Propagation Neural Network by Improved Particle Swarm Optimization). The results show that the average RMSE of IPSO-BPNN is less than 0.75 and DC is more than 98%. IPSO-BPNN can make more accurate prediction of human lower limb joint angle, which is beneficial to improve the man-machine coordination performance of exoskeleton.

Exoskeleton robots have been increasingly applied in mountaineering, rescue, and military scenarios to alleviate physical burden and enhance mobility. This study proposes a novel approach for continuous knee joint angle prediction based on surface electromyography (sEMG), integrating an Improved Zebra Optimization Algorithm (IZOA) with an attention-enhanced Gated Recurrent Unit (GRU) network. The IZOA leverages Tent and Logistic chaotic mappings for improved population diversity and convergence, along with a memory-based strategy to enhance global search capabilities. Experimental evaluations across three motion tasks—level walking, stair ascent, and stair descent—demonstrated that the proposed method achieved a minimum root mean square error (RMSE) of 1.31°, with over 50% reduction in feature dimensionality, significantly outperforming Genetic Algorithm (GA), Zebra Optimization Algorithm (ZOA), Liver Cancer Algorithm (LCA), and Pied Kingfisher Optimizer (PKO). In addition, normalization based on maximal voluntary contraction (MVC) improved model robustness across subjects. The attention-based GRU further enhanced dynamic feature extraction, leading to an average RMSE reduction of 27.2% compared to baseline GRU and Long Short-Term Memory (LSTM) models. These results confirm the effectiveness of the proposed method in achieving accurate, stable, and continuous sEMG-driven knee joint angle prediction, offering strong potential for intelligent control in wearable exoskeleton systems.

In biomechanics, accurate prediction of joint angles under varying conditions is critical for the advancement of rehabilitation protocols, improvement of orthopedic design, and optimization of athletic performance. The complexity of joint movements, influenced by factors such as external conditions and the specific joint being analyzed, presents a significant challenge for predictive modeling. This study explores the application of Support Vector Regression (SVR) and Random Forest (RF) models to predict joint angles across three distinct conditions: unbraced, knee braced, and ankle braced. These conditions were chosen to reflect variations in external support, which can significantly affect joint kinematics and dynamics. Both models were rigorously optimized through hyperparameter tuning to enhance their performance and evaluated using key metrics, which include Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-squared (R2). The RF model emerged as the superior method, which achieves an R2 value of 0.9947, an MSE of 0.0001, and an MAE of 0.0034, which demonstrates exceptional accuracy in the capture of complex movement patterns. In contrast, the SVR model achieved an R2 value of 0.9571, an MSE of 0.0012, and an MAE of 0.0285, which indicates solid predictive performance but with less robustness compared to RF. These findings underscore the effectiveness of Random Forest in modeling intricate joint movements under varying conditions. The study highlights the potential of machine learning techniques to address challenges in joint angle prediction. Future work should focus on incorporation of larger and more diverse datasets, exploration of advanced algorithms, and improvement in real-time applicability to broaden the scope of these models in clinical and athletic settings.

Electromyography (EMG) is commonly used to measure electrical activity of the skeletal muscles. As exoskeleton technology advances, these signals may be used to predict human intent for control purposes. This study used an artificial neural network trained and tested with knee flexion angles and knee muscle EMG signals to predict knee flexion angles during gait at 50, 100, 150, and 200 ms into the future. The hypothesis of this study was that the algorithm’s prediction accuracy would only be affected by time into the future, not subject, gender or side, and that as time into the future increased, the prediction accuracy would decrease. A secondary hypothesis was that as the number of algorithm training trials increased, the prediction accuracy of the artificial neural network (ANN) would increase. The results of this study indicate that only time into the future affected the accuracy of knee flexion angle prediction (p < 0.001), whereby greater time resulted in reduced accuracy (0.68 to 4.62 degrees root mean square error (RMSE) from 50 to 200 ms). Additionally, increased number of training trials resulted in increased angle prediction accuracy.