Gesture recognition via surface electromyography (sEMG) has drawn significant attention in the field of human–computer interaction. An important factor limiting the performance of sEMG-based pattern recognition (PR) is the generalization ability which sEMG changes for the identical movements when conducted at various positions or by different persons. Thus, this study aims to explore the generalization of classifier to develop a stable classification model that does not require relearning, even if it is used by other people. We propose a new feature extraction method to diminish the influence of limb position on sEMG-based PR. Specifically, the sEMG features are extracted directly from time domain. This condition is accomplished by using Fourier transform properties, difference, and the sum of squares differences. The best offline cross-validation accuracy (CVA) results are 88.775% training data from the tenth subject and testing data from the fifth subject in the NinaPro dataset. The best online CVA is 99%, and the movement selection time is 47.036 ± 1.028 ms. In comparison with the well-known sEMG feature, the CVA and the generalization of the proposed features improved substantially. These improvements aim to facilitate the practical implementation of myoelectric interfaces.

Background. The efficacy of robotic‐assisted gait training (RAGT) should be considered versatilely; among which, gait assessment is one of the most important measures; observational gait assessment is the most commonly used method in clinical practice, but it has certain limitations due to the deviation of subjectivity; instrumental assessments such as three‐dimensional gait analysis (3DGA) and surface electromyography (sEMG) can be used to obtain gait data and muscle activation during walking in stroke patients with hemiplegia, so as to better evaluate the rehabilitation effect of RAGT. Objective. This single‐blind randomized controlled trial is aimed at analyzing the impact of RAGT on the 3DGA parameters and muscle activation in patients with subacute stroke and evaluating the clinical effect of improving walking function of RAGT. Methods. This randomized controlled trial evaluated the improvement of 4‐week RAGT on patients with subacute stroke by 3DGA and surface electromyography (sEMG), combined with clinical scales: experimental group (n = 18, 20 sessions of RAGT) or control group (n = 16, 20 sessions of conventional gait training). Gait performance was evaluated by the 3DGA, and clinical evaluations based on Fugl‐Meyer assessment for lower extremity (FMA‐LE), functional ambulation category (FAC), and 6‐minute walk test (6MWT) were used. Of these patients, 30 patients underwent sEMG measurement synchronized with 3DGA; the cocontraction index in swing phase of the knee and ankle of the affected side was calculated. Results. After 4 weeks of intervention, intragroup comparison showed that walking speed, temporal symmetry, bilateral stride length, range of motion (ROM) of the bilateral hip, flexion angle of the affected knee, ROM of the affected ankle, FMA‐LE, FAC, and 6MWT in the experimental group were significantly improved (p < 0.05), and in the control group, significant improvements were observed in walking speed, temporal symmetry, stride length of the affected side, ROM of the affected hip, FMA‐LE, FAC, and 6MWT (p < 0.05). Intergroup comparison showed that the experimental group significantly outperformed the control group in walking speed, temporal symmetry of the spatiotemporal parameters, ROM of the affected hip and peak flexion of the knee in the kinematic parameters, and the FMA‐LE and FAC in the clinical scale (p < 0.05). In patients evaluated by sEMG, the experimental group showed a noticeable improvement in the cocontraction index of the knee (p = 0.042), while no significant improvement was observed in the control group (p = 0.196), and the experimental group was better than the control group (p = 0.020). No noticeable changes were observed in the cocontraction index of the ankle in both groups (p > 0.05). Conclusions. Compared with conventional gait training, RAGT successfully improved part of the spatiotemporal parameters of patients and optimized the motion of the affected lower limb joints and muscle activation patterns during walking, which is crucial for further rehabilitation of walking ability in patients with subacute stroke. This trial is registered with ChiCTR2200066402.

The existing surface electromyography-based pattern recognition system (sEMG-PRS) exhibits limited generalizability in practical applications. In this paper, we propose a stacked weighted random forest (SWRF) algorithm to enhance the long-term usability and user adaptability of sEMG-PRS. First, the weighted random forest (WRF) is proposed to address the issue of imbalanced performance in standard random forests (RF) caused by randomness in sampling and feature selection. Then, the stacking is employed to further enhance the generalizability of WRF. Specifically, RF is utilized as the base learner, while WRF serves as the meta-leaning layer algorithm. The SWRF is evaluated against classical classification algorithms in both online experiments and offline datasets. The offline experiments indicate that the SWRF achieves an average classification accuracy of 89.06%, outperforming RF, WRF, long short-term memory (LSTM), and support vector machine (SVM). The online experiments indicate that SWRF outperforms the aforementioned algorithms regarding long-term usability and user adaptability. We believe that our method has significant potential for practical application in sEMG-PRS.

Human arm exhibits superb maneuverability in performing various tasks by utilizing its ability to actively adjust impedance parameters and interaction forces. Therefore, how to identify the joint stiffness of the arm during motion and transmit them to the exoskeleton robots is the key to achieving flexible rehabilitation motion. In this paper, we propose a stiffness estimation method for elbow joint, termed stiffness and torque mapping index (STMI), which establishes the relationship between joint torque, joint angle and joint stiffness based on surface electromyography (sEMG). To improve joint angle identification accuracy, we propose a regression algorithm (RA), termed improved ant colony optimization generalized regression neural network (IACO-GRNN), and propose a time-domain descriptor (TDD) sEMG feature. Feature comparison experiment show that the TDD features (RMSE: 7.9792±0.0721; R2: 0.9257±0.0020) are superior among the popular features such as mean absolute value (MAV), root mean square (RMS) and waveform length (WL). The combination of TDD and IACO-GRNN achieves more impressive regression performance (RMSE: 8.6839 ± 0.0084, R2: 0.9109 ± 0.0002) than RA in joint angle recognition experiments, such as support vector regression (SVR), random forest regression (RFR), Particle swarm optimization-GRNN (PSO-GRNN) and Genetic algorithm-GRNN (GA-GRNN). The average RMSE of the joint stiffness estimated using STMI was 1.0146 Nm/rad. The proposed method can offer satisfactory dynamic elbow joint stiffness estimation only using sEMG signals, avoiding complex calibration of physiological data and additional sensing devices.