A preliminary study of classification of upper limb motions and forces based on mechanomyography

A HYBRID RECOGNITION METHOD VIA KELM WITH CPSO FOR MMG-BASED UPPER-LIMB MOVEMENTS CLASSIFICATION

Mechanomyography (MMG) is a low-frequency signal emitted during muscle contraction; it can overcome the inherently unreliable defects of electromyography (EMG) and electroencephalography (EEG). For MMG-based movement pattern recognition, this paper proposes an innovative kernel extreme learning machine (KELM) based on the chaotic particle swarm optimization (CPSO), namely CPSO–KELM. By using CPSO–KELM in MMG-based movement pattern recognition, the classification accuracy of upper-limb movement has been improved, and the results can be better applied to the control of passive rehabilitation training of the upper-limb exoskeleton, which can provide help for the upper extremity rehabilitation of stroke patients. In this paper, MMG which is used for pattern recognition research, is collected by accelerometers when the subjects performed seven types of upper-limb rehabilitation movements. After filtering and segmentation, six time-domain features are extracted for the MMG of each channel, then kernel principal component analysis (KPCA) and principal component analysis (PCA) are used to reduce the feature dimensions. By using different classifiers to build classification models, the average recognition accuracies of movement classification under different processing methods are obtained; it is found that for most classifiers, the recognition rate of MMG after KPCA dimensionality reduction is better than that of PCA, and the overall recognition rate of upper-limb movements using the CPSO–KELM classifier can reach 97.1%, which is better than support vector machine (SVM), back-propagation neural network (BPNN), linear discriminant algorithm (LDA) and other MMG common classifiers in recognition accuracy. Moreover, the experimental analysis shows that compared with genetic algorithm (GA) and particle swarm optimization (PSO), CPSO has faster convergence and smaller training error, and the final recognition accuracy proves that the performance of CPSO–KELM is better than those of GA–KELM and PSO–KELM.

BiLSTM-Based Joint Torque Prediction From Mechanomyogram During Isometric Contractions: A Proof of Concept Study

Quantifying muscle strength is an important measure in clinical settings; however, there is a lack of practical tools that can be deployed for routine assessment. The purpose of this study is to propose a deep learning model for ankle plantar flexion torque prediction from time-series mechanomyogram (MMG) signals recorded during isometric contractions (i.e., a similar form to manual muscle testing procedure in clinical practice) and to evaluate its performance. Four different deep learning models in terms of model architecture (based on a stacked bidirectional long short-term memory and dense layers) were designed with different combinations of the number of units (from 32 to 512) and dropout ratio (from 0.0 to 0.8), and then evaluated for prediction performance by conducting the leave-one-subject-out cross-validation method from the 10-subject dataset. As a result, the models explained more variance in the untrained test dataset as the error metrics (e.g., root-mean-square error) decreased and as the slope of the relationship between the measured and predicted joint torques became closer to 1.0. Although the slope estimates appear to be sensitive to an individual dataset, >70% of the variance in nine out of 10 datasets was explained by the optimal model. These results demonstrated the feasibility of the proposed model as a potential tool to quantify average joint torque during a sustained isometric contraction.

Classification of hand and wrist movements via surface electromyogram using the random convolutional kernels transform

Prosthetic devices are vital for enhancing personal autonomy and the quality of life for amputees. However, the rejection rate for electric upper-limb prostheses remains high at around 30%, often due to issues like functionality, control, reliability, and cost. Thus, developing reliable, robust, and cost-effective human-machine interfaces is crucial for user acceptance. Machine learning algorithms using Surface Electromyography (sEMG) signal classification hold promise for natural prosthetic control. This study aims to enhance hand and wrist movement classification using sEMG signals, treated as time series data. A novel approach is employed, combining a variation of the Random Convolutional Kernel Transform (ROCKET) for feature extraction with a cross-validation ridge classifier. Traditionally, achieving high accuracy in time series classification required complex, computationally intensive methods. However, recent advances show that simple linear classifiers combined with ROCKET can achieve state-of-the-art accuracy with reduced computational complexity. The algorithm was tested on the UCI sEMG hand movement dataset, as well as on the Ninapro DB5 and DB7 datasets. We demonstrate how the proposed approach delivers high discrimination accuracy with minimal parameter tuning requirements, offering a promising solution to improve prosthetic control and user satisfaction.

Mechanomyography signals pattern recognition in hand movements using swarm intelligence algorithm optimized support vector machine based on acceleration sensors

On the basis of extracting mechanomyography (MMG) signal features, the classification of hand movements has certain application values in human-machine interaction systems and wearable devices. In this paper, pattern recognition of hand movements based on MMG signal is studied with swarm intelligence algorithms introduced to optimize support vector machine (SVM). Time domain (TD) features, wavelet packet node energy (WPNE) features, frequency domain (FD) features, convolution neural network (CNN) features were extracted from each channel to constitute different feature sets. Three novel swarm intelligence algorithms (i.e., bald eagle search (BES), sparrow search algorithm (SSA), grey wolf optimization (GWO)) optimized SVM is proposed to train the models and recognition of hand movements are tested for each MMG feature extraction method. Using GWO as the optimization algorithm, time consumption is less than using the other two swarm algorithms. Using GWO with TD+FD features can obtain the classification accuracy of 93.55 %, which is higher than other methods while using CNN to extract features can be independent of domain knowledge. The results confirm GWO-SVM with TD + FD features is superior to some other methods in the classification problem for tiny samples based on MMG.

Mechanomyography Signal Pattern Recognition of Knee and Ankle Movements Using Swarm Intelligence Algorithm-Based Feature Selection Methods

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.

A PILOT STUDY OF MECHANOMYOGRAPHY-BASED HAND MOVEMENTS RECOGNITION EMPHASIZING ON THE INFLUENCE OF FABRICS BETWEEN SENSOR AND SKIN

Multi-channel mechanomyography (MMG) signals were acquired from the forearm when the subjects were performing eight classes of hand movements related to rehabilitation training. Ten time domain (TD) features and wavelet packet node energy (WPNE) features were extracted from each channel of MMG, and the hand movements were classified by support vector machine (SVM), extreme learning machine (ELM), linear discriminant analysis (LDA) and [Formula: see text]-nearest neighborhood (KNN) and the classifying results of three methods of collecting MMG (sensors directly on skin, sensors on cotton fabric and sensors on acrylic fiber) were compared. When all TD features were selected and SVM was adopted as the classifier, the total recognition rates of hand movements were 94.0%, 93.9% and 93.6%, respectively, of three collection methods. Using ELM can obtain similar results as SVM, with the recognition rates of 94.3%, 94.3% and 94.1%, respectively, better than using LDA (88.5%, 88.6% and 88.0%) or KNN (88.9%, 89.4% and 89.0%). For each algorithm, using TD features can acquire the highest recognition rates. Once the feature set and the classifier were selected, the total recognition rates were almost equally among three collection methods (especially for some feature sets, the differences are smaller than 1%). The results confirmed that satisfactory effects could be acquired even when the MMG was collected from sensors on fabrics with specific material, thus indicating that MMG has a unique potential value for developing wearable devices.