Search

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 K -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. [ABSTRACT FROM AUTHOR]

• A new experiment that involves upper limb motions and muscle forces is designed. • The classification of upper limb motions and muscle forces based on mechanomyography is proposed. • This study provide a basis for further research in which rehabilitation training is evaluated based on MMG. • This study has potential advantages in development on the human-computer interaction system that assist rehabilitation training. Rehabilitation training is essential for patients who have a history of certain illnesses, such as stroke. As a crucial part of rehabilitation training, upper limb training involves such key factors as upper limb motions and forces. This study investigated three upper limb motions (elbow flexion of 135°, Motion 1; shoulder flexion of 90°, Motion 2; and shoulder abduction of 90°, Motion 3) and various forces (muscle Force 0, no force; holding one 1.4 kg dumbbell, muscle Force 1; holding one 2.4 kg dumbbell, muscle Force 2) in combination to evaluate nine motion patterns. These patterns were completed by twelve healthy volunteers. Mechanomyography (MMG) measurements of the biceps brachii (Channel 1), triceps (Channel 2), and deltoid (Channel 3) muscles were collected. These were subsequently divided into signal segments corresponding to each of the motions using a segmentation method based on average energy. After extracting time-domain features and wavelet packet energy features, support vector machine analysis (SVM) was used for the classification of the upper limb motions and forces based on the MMG measurements. Channel 2 and Channel 3 were shown to play an important role in the classification of upper limb motions, and Channel 1 played a role in the classification of the forces. These results demonstrate that collection of MMG measurements from the three muscles is feasible and suggest a foundation for further studies in which rehabilitation training is evaluated based on MMG measurements. [ABSTRACT FROM AUTHOR]

The study of lower limb movements plays an important role in many fields, such as rehabilitation and treatment of disabled patients, detection, and monitoring of daily life, as well as the interaction between people and machine, like the application of intelligent prosthetics. In this paper, the wireless device was used to collect the mechanomyography (MMG) signals of four thigh muscles (rectus femoris, vastus lateralis, vastus medialis, and semitendinosus) and the attitude angle of rectus femoris. High precision was achieved in 11 gait movements, including 3 static activities, 4 dynamic transition activities, and 4 dynamic activities. It has been verified that the hidden Markov model (HMM) could not only be applied to the MMG-based gait recognition with high veracity but also support comparative analysis between support vector machine (SVM) and quadratic discriminant analysis (QDA). In addition, the experiment was conducted from the perspectives of feature selections, channel combinations, and muscle contribution rates. The results show that the average classification accuracy of dynamic motions based on MMG is 98.27%, while based on attitude angle, the average recognition rate of static motions and dynamic transition motions could achieve 98.33% and 100%, respectively. Generally, the average recognition rate of 11 gait motions is 98.91%. [ABSTRACT FROM AUTHOR]

• Repetitive wear and multiple collection will cause non-identical distribution. • The traditional model has poor recognition effect on non-identical signals. • Incremental learning has a good recognition effect on non-identical signals. • Deep learning can construct sample incremental learning well. • Incremental learning can be used to build real-time evaluation training systems. Aiming at the problem that the traditional mechanomyography (MMG) pattern recognition model for upper limb rehabilitation action has poor recognition effect on non-identical distribution test data, this research proposes an incremental learning method for deep learning based on MMG. By collecting 8-channels of MMG of 4 types of hand movements (wrist flexion, wrist extension, wrist ulnar flexion, and wrist radial flexion), after signal preprocessing, feature extraction and dimensionality reduction, 12 groups of non-identical distributed data were obtained. The model was trained by using deep neural network (DNN), and five commonly used machine learning algorithms were used as comparison for incremental training. Finally, the recognition rate of DNN was 88.25%, and the final recognition rates of Passive Aggressive (PA), Incremental Support Vector Machine (ISVM), Perceptron, Bernoulli Naive Bayes (BNB) and Multinomial Naive Bayes (MNB) were 85.94%, 84.82%, 81.01%, 73.07% and 61.20% respectively. Among them, both DNN and PA had better upward trends, and DNN had the highest final recognition rate. By comparing the confusion matrices before and after DNN incremental learning, it could be seen that DNN incremental training can significantly improve the accuracy and precision in confusion matrix. The experimental results demonstrate that the method of incremental learning can not only achieve the recognition of non-identically distributed test data, but also improve the recognition rates and the generalization performance of the model. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

• In MMG-based hand movement recognition, novel swarm intelligence algorithms (BES, GWO, SSA) were introduced to optimize SVM. • Based on hand-crafted feature extraction methods and a deep learning method, the performances of classification methods are compared in accuracy and time consumption. • Adopting GWO-SVM with TD + FD features can obtain good classification accuracy of eight classes of hand movements, up to 93.55 %, and take relatively less training time. 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. [ABSTRACT FROM AUTHOR]