Electromyography Pattern Recognition Research Articles

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

Enhancing Robustness of Surface Electromyography Pattern Recognition at Different Arm Positions for Transhumeral Amputees Using Deep Adversarial Inception Domain Adaptation

Removal of Interference from Electromyogram based on Empirical Mode Decomposition and Correlation Coefficient Thresholding

Introduction:: Electromyography (EMG) signals are contaminated by various noise components. These noises directly degrade the EMG processing performance, thereby affecting the classification accuracy of the EMG signals for implementing various hand movements of the prosthetic arm from the amputee’s residual muscle. Methods:: This study mainly aims to denoise the EMG signals using the empirical mode decomposition (EMD) and correlation coefficient thresholding (CCT) methods. The noisy EMG signal is obtained from NinaPro Database 2. Then, EMD is used to decompose it into intrinsic mode functions. Each hand movement noise is identified within specific modes and removed separately using correlation coefficient–dependent thresholding and wavelet denoising. The performance metrics signal-to-noise ratio (SNR) and root mean square error (RMSE) were used to evaluate the noise removal performance from the EMG signals of five intact subjects. The proposed method outperforms the wavelet denoising method in terms of noise interference removal. In this method, the SNR is obtained in the 17-22 dB range with a very low RMSE. Results:: The experimental results illustrate that the proposed method removes noise from six repetitions of six movements performed by five subjects. This study explores the special characteristics of EMD and demonstrates the possibility of using the EMD-based CCT filter for denoising EMG signals. Conclusion:: The proposed filter is more efficient than wavelet denoising in removing noise interference. It can also be used in any application that requires EMG signal filtering at the preprocessing stage, such as EMG pattern recognition.

A comprehensive analysis of gesture recognition systems: Advancements, challenges, and future direct

Gesture recognition emerges as a potent avenue for human-computer interaction, harnessing mathematical algorithms to interpret gestures. It promises to surpass text-based or graphical interfaces, enabling touchless device control through simple gestures. Our review of 7 papers encompassing various fields and methods underscores its diverse applications. Challenges persist, such as distinguishing genuine user intent from accidental actions amid environmental interference. Creating a universal EMG pattern recognition model demands intricate individual pre-training. Sensor-based gesture recognition grapples with real-world dynamics, necessitating adaptable models that discern user intent from non-intent actions. Addressing these gaps holds the key. Adaptable models and personalized approaches can enhance robustness and accuracy across applications, surmounting challenges in the gesture interaction technology realm.

Cross-User Electromyography Pattern Recognition Based on a Novel Spatial-Temporal Graph Convolutional Network

Cross-User Electromyography Pattern Recognition Based on a Novel Spatial-Temporal Graph Convolutional Network

An Introduction to Electromyography Signal Processing and Machine Learning for Pattern Recognition: A Brief Overview

Electromyography (EMG) is about studying electrical signals from muscles and can provide a wealth of information on the function, contraction, and activity of your muscles. In the field of EMG pattern recognition, these signals are used to identify and categorize patterns linked to muscle activity. Various machine learning (ML) methods are used for this purpose. Successful detection of these patterns depends on using effective signal-processing techniques. It is crucial to reduce noise in EMG for accurate and meaningful information about muscle activity, improving signal quality for precise assessments. ML tools such as SVMs, neural networks, KNNs, and decision trees play a crucial role in sorting out complex EMG signals for different pattern recognition tasks. Clustering algorithms also help analyze and interpret muscle activity. EMG and ML find diverse uses in rehabilitation, prosthetics, and human-computer interfaces, though real-time applications come with challenges. They bring significant changes to prosthetic control, human-computer interfaces, and rehabilitation, playing a vital role in pattern recognition. They make prosthetic control more intuitive by understanding user intent from muscle signals, enhance human-computer interaction with responsive interfaces, and support personalized rehabilitation for those with motor impairments. The combination of EMG and ML opens doors for further research into understanding muscle behavior, improving feature extraction, and advancing classification algorithms.

Implementation of an Intelligent EMG Signal Classifier Using Open-Source Hardware

This paper presents the implementation of an intelligent real-time single-channel electromyography (EMG) signal classifier based on open-source hardware. The article shows the experimental design, analysis, and implementation of a solution to identify four muscle movements from the forearm (extension, pronation, supination, and flexion), for future applications in transradial active prostheses. An EMG signal acquisition instrument was developed, with a 20–450 Hz bandwidth and 2 kHz sampling rate. The signals were stored in a Database, as a multidimensional array, using a desktop application. Numerical and graphic analysis approaches for discriminative capacity were proposed for feature analysis and four feature sets were used to feed the classifier. Artificial Neural Networks (ANN) were implemented for time-domain EMG pattern recognition (PR). The system obtained a classification accuracy of 98.44% and response times per signal of 8.522 ms. Results suggest these methods allow us to understand, intuitively, the behavior of user information.

Short-term hand gestures recognition based on electromyography signals

<p>Electromyography pattern recognition to predict limb movements can<br />significantly enhance the control of the prosthesis. However, this technique<br />has not yet been widely used in clinical practice. Improvements in the<br />myoelectric pattern recognition (MPR) system can improve the functionality<br />of the prosthesis. This study proposes new sets of time domain features to<br />enhance the MPR control system. Three groups of features are evaluated, time<br />domain with auto regression (TD-AR), frequency domain (FD), and timefrequency domain (TFD). The electromyography signals (EMG) are obtained from the Ninapro database-5 (DB5), a publicly available dataset for hand prosthetics. The long-term signals of DB5 are divided into short-term signals to perform short-term signals recognition. The three feature sets are extracted from the short-term signals. The results showed that the performance of the proposed TD-AR features outperformed that of the FD and TFD feature sets. The TD-AR-based discrimination performance of 40 gestures achieved a precision of 88.8% and a sensitivity of 82.6%. The integration of short-term identification with reliable features can improve classification accuracy even for a large number of gestures. A comparison with the latest works shows the reliability of the proposed work.</p>

A novel unsupervised dynamic feature domain adaptation strategy for cross-individual myoelectric gesture recognition

Objective. Surface electromyography pattern recognition (sEMG-PR) is considered as a promising control method for human-machine interaction systems. However, the performance of a trained classifier would greatly degrade for novel users since sEMG signals are user-dependent and largely affected by a number of individual factors such as the quantity of subcutaneous fat and the skin impedance. Approach. To solve this issue, we proposed a novel unsupervised cross-individual motion recognition method that aligned sEMG features from different individuals by self-adaptive dimensional dynamic distribution adaptation (SD-DDA) in this study. In the method, both the distances of marginal and conditional distributions between source and target features were minimized through automatically selecting the optimal feature domain dimension by using a small amount of unlabeled target data. Main results. The effectiveness of the proposed method was tested on four different feature sets, and results showed that the average classification accuracy was improved by above 10% on our collected dataset with the best accuracy reached 90.4%. Compared to six kinds of classic transfer learning methods, the proposed method showed an outstanding performance with improvements of 3.2%-13.8%. Additionally, the proposed method achieved an approximate 9% improvement on a publicly available dataset. Significance. These results suggested that the proposed SD-DDA method is feasible for cross-individual motion intention recognition, which would provide help for the application of sEMG-PR based system.

Estimating finger joint angles by surface EMG signal using feature extraction and transformer-based deep learning model

Human-machine interfaces frequently use electromyography (EMG) signals. Based on previous work, feature extraction has a great deal of influence on the performance of EMG pattern recognition. Furthermore, the Deep Learning method is supposed to increase performance and not depend on feature engineering. However, directly processing raw signals will require a higher computation rate. This study proposed a new method that combines feature extraction and Deep Learning to address those issues while improving performance, reducing architecture size, and producing a more representative output. The proposed architecture employs the Transformer model as the backbone to get the correlation between elements and focus on the important information for estimating the flexion-extension of finger joint angles. This study uses experiment three of the NinaPro (Non-Invasive Adaptive Hand Prosthetics) DB5 dataset. Each experiment produces 16 Surface EMG data streams from two Myo Armbands devices representing 22 finger joint angles as output. This study compares the windowing process, feature extraction, execution time, and results with previous studies. The results show that the proposed model outperforms the previous study, from 0.957 in the previous study to become 0.970 in this study for the R-Square score. This result is obtained using 100 data points for the windowing process and Median Frequency for the best feature extraction method.

A Novel Event-Driven Spiking Convolutional Neural Network for Electromyography Pattern Recognition.

Electromyography (EMG) pattern recognition is an important technology for prosthesis control and human-computer interaction etc. However, the practical application of EMG pattern recognition is hampered by poor accuracy and robustness due to electrode shift caused by repeated wearing of the signal acquisition device. Moreover, the user's acceptability is low due to the heavy training burden, which is caused by the need for a large amount of training data by traditional methods. In order to explore the advantage of spiking neural network (SNN) in solving the poor robustness and heavy training burden problems in EMG pattern recognition, a spiking convolutional neural network (SCNN) composed of cyclic convolutional neural network (CNN) and fully connected modules is proposed and implemented in this study. High density surface electromyography (HD-sEMG) signals collected from 6 gestures of 10 subjects at 6 electrode positions are taken as the research object. Compared to CNN with the same structure, CNN-Long Short Term Memory (CNN-LSTM), linear kernel linear discriminant analysis classifier (LDA) and spiking multilayer perceptron (Spiking MLP), the accuracy of SCNN is 50.69%, 33.92%, 32.94% and 9.41% higher in the small sample training experiment, 6.50%, 4.23%, 28.73%, and 2.57% higher in the electrode shifts experiment respectively. In addition, the power consumption of SCNN is about 1/93 of CNN. The advantages of the proposed framework in alleviating user training burden, mitigating the adverse effect of electrode shifts and reducing power consumption make it very meaningful for promoting the development of user-friendly real-time myoelectric control system.

Features selection for estimating hand gestures based on electromyography signals

Hand prosthesis controlled by surface electromyography (sEMG) is promising due to the control capabilities and the noninvasive technique that machine learning (ML) offers to help physically disabled people during daily life. Nevertheless, dexterous prostheses are still infrequently popular due to control problems and limited robustness. This paper proposes a new set of time domain (TD) features to improve the EMG pattern recognition performance. The effect of five feature sets is evaluated based on the three classifiers k-nearest neighbor (KNN), linear discriminate analysis (LDA), and support vector machine (SVM). The EMG signals are obtained from database-5 (DB5) of the ninapro project datasets. In this study, the long-term signals of DB5 are segmented into short-term signals to perform short-term recognition. The results showed that the LDA classifier based on the proposed features achieved high classification accuracy for classifing 17 gestures. The LDA classifier achieved about 96.47% compared to 94.12%, and 93.82% for KNN and SVM classifiers, respectively. The results confirm that the suitable features extracted from short term signals with the appropriate classifier, has an important impact on improving the performance of gesture classification.

Features selection for estimating hand gestures based on electromyography signals

Hand prosthesis controlled by surface electromyography (sEMG) is promising due to the control capabilities and the noninvasive technique that machine learning (ML) offers to help physically disabled people during daily life. Nevertheless, dexterous prostheses are still infrequently popular due to control problems and limited robustness. This paper proposes a new set of time domain (TD) features to improve the EMG pattern recognition performance. The effect of five feature sets is evaluated based on the three classifiers k-nearest neighbor (KNN), linear discriminate analysis (LDA), and support vector machine (SVM). The EMG signals are obtained from database-5 (DB5) of the ninapro project datasets. In this study, the long-term signals of DB5 are segmented into short-term signals to perform short-term recognition. The results showed that the LDA classifier based on the proposed features achieved high classification accuracy for classifing 17 gestures. The LDA classifier achieved about 96.47% compared to 94.12%, and 93.82% for KNN and SVM classifiers, respectively. The results confirm that the suitable features extracted from short term signals with the appropriate classifier, has an important impact on improving the performance of gesture classification.

Feasibility study on the application of a spiking neural network in myoelectric control systems.

In recent years, the effectiveness of a spiking neural network (SNN) for Electromyography (EMG) pattern recognition has been validated, but there is a lack of comprehensive consideration of the problems of heavy training burden, poor robustness, and high energy consumption in the application of actual myoelectric control systems. In order to explore the feasibility of the application of SNN in actual myoelectric control systems, this paper investigated an EMG pattern recognition scheme based on SNN. To alleviate the differences in EMG distribution caused by electrode shifts and individual differences, the adaptive threshold encoding was applied to gesture sample encoding. To improve the feature extraction ability of SNN, the leaky-integrate-and-fire (LIF) neuron that combines voltage-current effect was adopted as a spike neuron model. To balance recognition accuracy and power consumption, experiments were designed to determine encoding parameter and LIF neuron release threshold. By conducting the gesture recognition experiments considering different training test ratios, electrode shifts, and user independences on the nine-gesture high-density and low-density EMG datasets respectively, the advantages of the proposed SNN-based scheme have been verified. Compared with a Convolutional Neural Network (CNN), Long Short-Term Memory Network (LSTM) and Linear Discriminant Analysis (LDA), SNN can effectively reduce the number of repetitions in the training set, and its power consumption was reduced by 1-2 orders of magnitude. For the high-density and low-density EMG datasets, SNN improved the overall average accuracies by about (0.99 ~ 14.91%) under different training test ratios. For the high-density EMG dataset, the accuracy of SNN was improved by (0.94 ~ 13.76%) under electrode-shift condition and (3.81 ~ 18.95%) in user-independent case. The advantages of SNN in alleviating the user training burden, reducing power consumption, and improving robustness are of great significance for the implementation of user-friendly low-power myoelectric control systems.

Comparing Online Performance of EMG Pattern Recognition with and Without Joint Movements

Comparing Online Performance of EMG Pattern Recognition with and Without Joint Movements

Single Lead EMG signal to Control an Upper Limb Exoskeleton Using Embedded Machine Learning on Raspberry Pi

Post-stroke can cause partial or complete paralysis of the human limb. Delayed rehabilitation steps in post-stroke patients can cause muscle atrophy and limb stiffness. Post-stroke patients require an upper limb exoskeleton device for the rehabilitation process. Several previous studies used more than one electrode lead to control the exoskeleton. The use of many electrode leads can lead to an increase in complexity in terms of hardware and software. Therefore, this research aims to develop single lead EMG pattern recognition to control an upper limb exoskeleton. The main contribution of this research is that the robotic upper limb exoskeleton device can be controlled using a single lead EMG. EMG signals were tapped at the biceps point with a sampling frequency of 2000 Hz. A Raspberry Pi 3B+ was used to embed the data acquisition, feature extraction, classification and motor control by using multithread algorithm. The exoskeleton arm frame is made using 3D printing technology using a high torque servo motor drive. The control process is carried out by extracting EMG signals using EMG features (mean absolute value, root mean square, variance) further extraction results will be trained on machine learning (decision tree (DT), linear regression (LR), polynomial regression (PR), and random forest (RF)). The results show that machine learning decision tree and random forest produce the highest accuracy compared to other classifiers. The accuracy of DT and RF are of 96.36±0.54% and 95.67±0.76%, respectively. Combining the EMG features, shows that there is no significant difference in accuracy (p-value 0.05). A single lead EMG electrode can control the upper limb exoskeleton robot device well.

A hybrid filter-wrapper feature selection using Fuzzy KNN based on Bonferroni mean for medical datasets classification: A COVID-19 case study

Several feature selection methods have been developed to extract the optimal features from a dataset in medical datasets classification. Creating an efficient technique has become a challenge because of the high dimensions, noise, and redundant information. In this paper, we propose a hybrid filter-wrapper approach for feature selection. An ensemble of filter methods, ReliefF and Fuzzy Entropy (RFE) is developed, and the union of top-n features from each method are considered. The Equilibrium Optimizer (EO) technique is combined with Opposition Based Learning (OBL), Cauchy Mutation operator and a novel search strategy to enhance its capabilities. The OBL strategy improves the diversity of the population in the search space. The Cauchy Mutation operator enhances its ability to evade the local optima during the search, and the novel search strategy improves the exploration capability of the algorithm. This enhanced form of EO is integrated with eight time-varying S and V-shaped transfer functions to convert the solutions into binary form, Binary Enhanced Equilibrium Optimizer (BEE). The features from the ensemble are given as input to the Binary Enhanced Equilibrium Optimizer to extract the essential features. Fuzzy KNN based on Bonferroni mean is used as the learning algorithm. Twenty-two benchmark datasets and four microarray datasets are used to test the algorithm’s efficiency. This method is also applied to a COVID-19 case study. The results demonstrate the superiority of the proposed approach, RFE-BEE, among other methods in terms of fitness values, accuracy, precision, sensitivity, and F-measure, among several other state-of-the-art algorithms. RFE-BEE can be applied to various biomedical, computer vision and engineering applications such as electromyography pattern recognition, COVID-19 diagnosis, face recognition and fault diagnosis.

Comparing EMG Continuous Movement Decoding With Joints Unconstrained and Constrained

Electromyography (EMG) signals have been employed for continuous movement decoding in recent years. However, several studies demonstrated that due to physiological factors, the EMG signals of amputees were poorer with respect to that of the able-bodied subjects. Our previous study demonstrated that the joint movements affected the performance of EMG pattern recognition. In this study, we aimed to investigate whether the movement of metacarpophalangeal (MCP) and wrist joints have effects on the performance of EMG continuous movement decoding. Six able-bodied subjects performed MCP and wrist flexion/extension simultaneously or independently with the MCP and wrist joints unconstrained (MWJU) and constrained (MWJC), while the EMG signals of the four forearm muscles were recorded. The musculoskeletal model was used to predict the joint angles from EMG signals. The performance of continuous movement decoding was quantified by the Pearson's correlation coefficient (r) and the normalized root mean square error (NRMSE) between the measured and predicted joint angles. The results showed that the MWJC significantly reduced the prediction performance of continuous movement for all subjects when compared to the MWJU. The average r values of the wrist and MCP flexion/extension decreased from 0.89 to 0.82 and 0.86 to 0.52, respectively. The average NRMSE values of the wrist and MCP flexion/extension increased from 0.18 to 0.21 and 0.22 to 0.31, respectively. The results demonstrated that the movements of the MCP and the wrist joints have a significant effect on the continuous movement decoding. Our study revealed a potential factor inducing the poor performance of continuous movement decoding in amputees.

Analyzing Human Muscle State with Flexible Sensors

Analyzing human muscle states has attracted extensive attention. EMG (electromyography) pattern recognition methods based on these works have been proposed for many years. However, uncomfortable wearing and high prices make it inconvenient for motion tracking and muscle analysis by using robotic arms and inertial sensors in daily life. In this study, we propose to use smart clothes integrated with flexible sensors to collect arm motion data, estimate the kinematic information of continuous arm motion, and predict the EMG signal of each arm muscle. Firstly, the neural network regression model integrated with the LSTM (long short-term memory) module is used to continuously estimate the sensor resistances collected by the smart clothes and the angles collected by Kinect. Then, six types of shoulder and elbow movements’ angles and the corresponding EMG signals of 5 subjects are preprocessed and aligned. The stacked regression model based on extremely randomized trees (extra trees) is used for regression. Our experimental results show that the average estimation absolute error from the sensor resistances to the joint angle is 3.45 degrees, and the absolute percentage error from the joint angle to the EMG signal is only 1.82%.

Electromyography pattern-recognition based prosthetic limb control using various machine learning techniques

People who have lost their limbs to amputation and neurological disorders confront this loss every morning. As per the literature review, nearly 30% of the Indian population suffered from upper extremity amputation. As a coping-up measure, a force-controlled prosthetic limb has been developed to improve their self-reliance, quality of lifestyle and mental strength. The current prosthetic limb operation is done by residual muscle contraction, which contributes to the activation of the sensor and the motor. But there are some cons, the amputee does not know how much pressure needs to be exerted for holding various objects. Also, the amputee still has to undergo the surgical procedure. However, this paper proposes a way to predict the force which is needed to regulate the voltage for the servomotors using different Machine Learning (ML) regression approaches. Support Vector Regressor (SVR), Linear Regression and Random Forest models have been used to predict that force requirement. After comparing the results, the Random Forest model gave a highly accurate prediction of the force needed to control the voltage for the DC servomotors

EMG Pattern Recognition Using TFD for Future Control of In-Car Electronic Equipment

Ezreen Farina Shair, Radhi Hafizuddin Razali, Abdul Rahim Abdullah, and Nurul Fauzani Jamaluddin. International Journal of Fuzzy Logic and Intelligent Systems 2022;22:11-22. https://doi.org/10.5391/IJFIS.2022.22.1.11