This study investigated classification of six types of head motions using mechanomyography (MMG) signals. An unequal segmenting algorithm was adopted to segment the MMG signals generated by head motions. Three types of features (time domain, time-frequency domain and nonlinear dynamics) were extracted to construct five feature sets as candidate datasets for classification analysis. Genetic algorithm optimized support vector machine (GA-SVM) was used to classify the MMG signals. Three different kernel functions, different combinations of feature sets, different number of signal channels and training samples were selected for comparative analysis to evaluate the classification accuracy. Experimental results showed that the classifier had the best overall classification accuracy when using the radial basis function (RBF). Any combination of three different types of feature sets guaranteed an average accuracy of over 80%. In the case of the best combination (feature set 2 + 3 + 5), the classification accuracy was up to 88.2%. Using four channels to acquire MMG signal and no less than 60 training samples can assure a satisfactory classification accuracy.
Pattern recognition of lower-limb movements based on mechanomyography (MMG) signals has a certain application value in the study of wearable rehabilitation-training devices. In this paper, MMG feature selection methods based on a chameleon swarm algorithm (CSA) and a grasshopper optimization algorithm (GOA) are proposed for the pattern recognition of knee and ankle movements in the sitting and standing positions. Wireless multichannel MMG acquisition systems were designed and used to collect MMG movements from four sites on the subjects thighs. The relationship between the threshold values and classification accuracy was analyzed, and comparatively high recognition rates were obtained after redundant information was eliminated. When the threshold value rose, the recognition rates from the CSA fluctuated within a small range: up to 88.17% (sitting position) and 90.07% (standing position). However, the recognition rates from the GOA drop dramatically when increasing the threshold value. The comparison results demonstrated that using a GOA consumes less time and selects fewer features, while a CSA gives higher recognition rates of knee and ankle movements.
Mechanomyography (MMG) is a non-invasive technique for assessing muscle activity by measuring mechanical signals, offering high sensitivity and real-time monitoring capabilities, and it has many applications in rehabilitation training. Traditional MMG-based motion recognition relies on feature extraction and classifier training, which require segmenting continuous actions, leading to challenges in real-time performance and segmentation accuracy. Therefore, this paper proposes an innovative method for the real-time segmentation and classification of upper limb rehabilitation actions based on the You Only Look Once (YOLO) algorithm, integrating the Squeeze-and-Excitation (SE) attention mechanism to enhance the model’s performance. In this paper, the collected MMG signals were transformed into one-dimensional time-series images. After image processing, the training set and test set were divided for the training and testing of the YOLOv5s-SE model. The results demonstrated that the proposed model effectively segmented isolated and continuous MMG motions while simultaneously performing real-time motion category prediction and outputting results. In segmentation tasks, the base YOLOv5s model achieved 97.9% precision and 98.0% recall, while the improved YOLOv5s-SE model increased precision to 98.7% (+0.8%) and recall to 98.3% (+0.3%). Additionally, the model demonstrated exceptional accuracy in predicting motion categories, achieving an accuracy of 98.9%. This method realizes the automatic segmentation of time-domain motions, avoids the limitations of manual parameter adjustment in traditional methods, and simultaneously enhances the real-time performance of MMG motion recognition through image processing, providing an effective solution for motion analysis in wearable devices.
24 September 2026 in Journal of Intelligent & Robotic Systems
Wheel-legged robots combine the efficiency of wheeled locomotion with the ter- rain adaptability of legged systems, but many existing mechanisms exhibit strong kinematic nonlinearity during body lifting, which complicates control and lim- its recovery capability. To address this issue, this paper proposes a symmetric five-bar wheel-leg mechanism that supports two motion modes within a uni- fied architecture: quasi-linear vertical lifting under synchronous actuation and body reorientation under differential actuation. A closed-loop kinematic model is established, and a reduced lifting model is derived under symmetry constraints. Based on this model, a boundary-constrained dimensional synthesis method with numerical optimization is developed to improve lifting linearity, enlarge the usable stroke, and avoid unfavorable kinematic regions. The optimized mechanism is implemented on a prototype robot with quasi-direct-drive actuation and slip-ring-based wiring. Simulation and experimental results show that the prototype preserves a quasi-linear angle–height relationship, with limited lateral drift, bounded joint torque, and small pitch variation during synchronous lifting. Workspace, Jacobian, and Monte Carlo sensitivity analyses further indicate that the selected design remains away from the prescribed singularity threshold under the tested perturbations. Self-recovery experiments under several tested conditions demonstrate that the differential mode provides repeatable posture-reconfiguration capability. These results support the feasibility of using the proposed mechanism for combined height adjustment and recovery-oriented reconfiguration in wheel-legged robots.