Feature extraction of the first difference of EMG time series for EMG pattern recognition

The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions

The rapid advancements in artificial intelligence (AI), including machine learning (ML), and deep learning (DL) have ushered in a new era of technological breakthroughs in healthcare. These technologies are revolutionizing the way we utilize medical data, enabling improved disease classification, more precise diagnoses, better treatment selection, therapeutic monitoring, and highly accurate prognostication. Different ML and DL models have been used to distinguish between electromyography signals in normal individuals and those with amyotrophic lateral sclerosis and myopathy, with accuracy ranging from 67% to 99.5%. DL models have also been successfully applied in neuromuscular ultrasound, with the use of segmentation techniques achieving diagnostic accuracy of at least 90% for nerve entrapment disorders, and 87% for inflammatory myopathies. Other successful AI applications include prediction of treatment response, and prognostication including prediction of intensive care unit admissions for patients with myasthenia gravis. Despite these remarkable strides, significant knowledge, attitude, and practice gaps persist, including within the field of electrodiagnostic and neuromuscular medicine. In this narrative review, we highlight the fundamental principles of AI and draw parallels with the intricacies of human brain networks. Specifically, we explore the immense potential that AI holds for applications in electrodiagnostic studies, neuromuscular ultrasound, and other aspects of neuromuscular medicine. While there are exciting possibilities for the future, it is essential to acknowledge and understand the limitations of AI and take proactive steps to mitigate these challenges. This collective endeavor holds immense potential for the advancement of healthcare through the strategic and responsible integration of AI technologies.

Classification of EMG signals with CNN features and voting ensemble classifier

Electromyography (EMG) signals are primarily used to control prosthetic hands. Classifying hand gestures efficiently with EMG signals presents numerous challenges. In addition to overcoming these challenges, a successful combination of feature extraction and classification approaches will improve classification accuracy. In the current work, convolutional neural network (CNN) features are used to reduce the redundancy problems associated with time and frequency domain features to improve classification accuracy. The features from the EMG signal are extracted using a CNN and are fed to the 'k' nearest neighbor (KNN) classifier with a different number of neighbors ( 1 N N , 3 N N , 5 N N , and   7 N N ) . It results in an ensemble of classifiers that are combined using a hard voting-based classifier. Based on the benchmark Ninapro DB4 database and CapgMyo database, the proposed framework obtained 91.3 % classification accuracy on CapgMyo and 89.5 % on Ninapro DB4.

Adaptive neuro-fuzzy inference system model driven by the non-negative matrix factorization-extracted muscle synergy patterns to estimate lower limb joint movements

BACKGROUND AND OBJECTIVE

For patients with movement disorders, the main clinical focus is on exercise rehabilitation to help recover lost motor function, which is achieved by relevant assisted equipment. The basis for seamless control of the assisted equipment is to achieve accurate inference of the user's movement intentions in the human-machine interface. This study proposed a novel movement intention detection technology for estimating lower limb joint continuous kinematic variables following muscle synergy patterns, to develop applications for more efficient assisted rehabilitation training.

METHODS

This study recruited 16 healthy males and 16 male patients with symptomatic patellar tendinopathy (VISA-P: 59.1 ± 8.7). The surface electromyography of 12 muscles and lower limb joint kinematic and kinetic data from healthy subjects and patients during step-off landings from 30 cm-high stair steps were collected. We subsequently solved the preprocessed data based on the established recursive model of second-order differential equation to obtain the muscle activation matrix, and then imported it into the non-negative matrix factorization model to obtain the muscle synergy matrix. Finally, the lower limb neuromuscular synergy pattern was then imported into the developed adaptive neuro-fuzzy inference system non-linear regression model to estimate the human movement intention during this movement pattern.

RESULTS

Six muscle synergies were determined to construct the muscle synergy pattern driven ANFIS model. Three fuzzy rules were determined in most estimation cases. Combining the results of the four error indicators across the estimated variables indicates that the current model has excellent estimated performance in estimating lower limb joint movement. The estimation errors between the healthy (Angle: R2=0.98±0.03; Torque: R2=0.96±0.04) and patient (Angle: R2=0.98±0.02; Torque: R2=0.96±0.03) groups are consistent.

CONCLUSION

The proposed model of this study can accurately and reliably estimate lower limb joint movements, and the effectiveness will also be radiated to the patient group. This revealed that our models also have certain advantages in the recognition of motor intentions in patients with relevant movement disorders. Future work from this study can be focused on sports rehabilitation in the clinical field by achieving more flexible and precise movement control of the lower limb assisted equipment to help the rehabilitation of patients.

Evaluation of skin sympathetic nervous activity for classification of intracerebral hemorrhage and outcome prediction

Classification and outcome prediction of intracerebral hemorrhage (ICH) is critical for improving the survival rate of patients. Early or delayed neurological deterioration is common in ICH patients, which may lead to changes in the autonomic nervous system (ANS). Therefore, we proposed a new framework for ICH classification and outcome prediction based on skin sympathetic nervous activity (SKNA) signals. A customized measurement device presented in our previous papers was used to collect data. 117 subjects (50 healthy control subjects and 67 ICH patients) were recruited for this study to obtain their 5-min electrocardiogram (ECG) and SKNA signals. We extracted the signal's time-domain, frequency-domain, and nonlinear features and analyzed their differences between healthy control subjects and ICH patients. Subsequently, we established the ICH classification and outcome evaluation model based on the eXtreme Gradient Boosting (XGBoost). In addition, heart rate variability (HRV) as an ANS assessment method was also included as a comparison method in this study. The results showed significant differences in most features of the SKNA signal between healthy control subjects and ICH patients. The ICH patients with good outcomes have a higher change rate and complexity of SKNA signal than those with bad outcomes. In addition, the accuracy of the model for ICH classification and outcome prediction based on the SKNA signal was more than 91% and 83%, respectively. The ICH classification and outcome prediction based on the SKNA signal proved to be a feasible method in this study. Furthermore, the features of change rate and complexity, such as entropy measures, can be used to characterize the difference in SKNA signals of different groups. The method can potentially provide a new tool for rapid classification and outcome prediction of ICH patients. Index Terms-intracerebral hemorrhage (ICH), skin sympathetic nervous activity (SKNA), classification, outcome prediction, cardiovascular and cerebrovascular diseases.

Speech Emotion Recognition Using Convolution Neural Networks and Multi-Head Convolutional Transformer

Speech emotion recognition (SER) is a challenging task in human-computer interaction (HCI) systems. One of the key challenges in speech emotion recognition is to extract the emotional features effectively from a speech utterance. Despite the promising results of recent studies, they generally do not leverage advanced fusion algorithms for the generation of effective representations of emotional features in speech utterances. To address this problem, we describe the fusion of spatial and temporal feature representations of speech emotion by parallelizing convolutional neural networks (CNNs) and a Transformer encoder for SER. We stack two parallel CNNs for spatial feature representation in parallel to a Transformer encoder for temporal feature representation, thereby simultaneously expanding the filter depth and reducing the feature map with an expressive hierarchical feature representation at a lower computational cost. We use the RAVDESS dataset to recognize eight different speech emotions. We augment and intensify the variations in the dataset to minimize model overfitting. Additive White Gaussian Noise (AWGN) is used to augment the RAVDESS dataset. With the spatial and sequential feature representations of CNNs and the Transformer, the SER model achieves 82.31% accuracy for eight emotions on a hold-out dataset. In addition, the SER system is evaluated with the IEMOCAP dataset and achieves 79.42% recognition accuracy for five emotions. Experimental results on the RAVDESS and IEMOCAP datasets show the success of the presented SER system and demonstrate an absolute performance improvement over the state-of-the-art (SOTA) models.

Gait Pattern Recognition Based on Supervised Contrastive Learning Between EEG and EMG

Electroencephalography (EEG) and lower-limb electromyography (EMG) signals are widely used in lower-limb kinematic classification and regression tasks. Since it directly measures muscle responses, EMG usually works better. However, due to the susceptibility of EMG signals to muscle fatigue, insufficient residual myoelectric activity, and the difficulty of precise localization, it is difficult to acquire EMG signals in practice. In contrast, EEG signals are stable and easy to sample. Therefore, in this work, we propose a multimodal training strategy based on supervised contrastive learning. With this training strategy, we can effectively use the guiding role of EMG in the training phase to help the model fit the gait with EEG signal while using only EEG signal in the testing phase to obtain better results than using any single modal signal to train and test the model. Finally, we compared the models trained with the strategy proposed in this paper with other models trained with EEG signals. The obtained Pearson's Correlation Coefficient value exceeds those of all baseline models.

EMG-Based Estimation of Lower Limb Joint Angles and Moments Using Long Short-Term Memory Network

One of the fundamental limitations in human biomechanics is that we cannot directly obtain joint moments during natural movements without affecting the motion. However, estimating these values is feasible with inverse dynamics computation by employing external force plates, which can cover only a small area of the plate. This work investigated the Long Short-Term Memory (LSTM) network for the kinetics and kinematics prediction of human lower limbs when performing different activities without using force plates after the learning. We measured surface electromyography (sEMG) signals from 14 lower extremities muscles to generate a 112-dimensional input vector from three sets of features: root mean square, mean absolute value, and sixth-order autoregressive model coefficient parameters for each muscle in the LSTM network. With the recorded experimental data from the motion capture system and the force plates, human motions were reconstructed in a biomechanical simulation created using OpenSim v4.1, from which the joint kinematics and kinetics from left and right knees and ankles were retrieved to serve as output for training the LSTM. The estimation results using the LSTM model deviated from labels with average R² scores (knee angle: 97.25%, knee moment: 94.9%, ankle angle: 91.44%, and ankle moment: 85.44%). These results demonstrate the feasibility of the joint angle and moment estimation based solely on sEMG signals for multiple daily activities without requiring force plates and a motion capture system once the LSTM model is trained.

Generation and analysis of synthetic surface electromyography signals under varied muscle fiber type proportions and validation using recorded signals

The magnitude and duration of muscle force production are influenced by the fiber type proportion. In this work, surface electromyography (sEMG) signals of muscles with varied fiber type proportions, are generated. For this, relevant components of existing models reported in various literature have been adopted. Also, a method to calculate the motor unit size factor is proposed. sEMG signals of adductor pollicis (AP) and triceps brachii (TB) muscles are simulated from the onset of force production to muscle fatigue state at various percentages of maximal voluntary contraction (MVC) values. The model is validated using signals recorded from these muscles using well-defined isometric exercise protocols. Root mean square and mean power spectral density values extracted from the simulated and recorded signals are found to increase for TB and decrease for AP with time. A linear variation of the features with %MVC values is obtained for simulated and experimental results. The Bland-Altman plot is used to analyze the agreement between simulated and experimental feature values. Good agreement is obtained for the feature values at various %MVCs. The mean endurance time calculated using the model is found to be comparable to that of the experimental value. This method can be used to generate sEMG signals of different muscles with varying fiber type ratios under various neuromuscular conditions.

Biosignal processing methods to explore the effects of side-dominance on patterns of bi- and unilateral standing stability in healthy young adults

We examined the effects of side-dominance on the laterality of standing stability using ground reaction force, motion capture (MoCap), and EMG data in healthy young adults. We recruited participants with strong right (n = 15) and left (n = 9) hand and leg dominance (side-dominance). They stood on one or two legs on a pair of synchronized force platforms for 50 s with 60 s rest between three randomized stance trials. In addition to 23 CoP-related variables, we also computed six MoCap variables representing each lower-limb joint motion time series. Moreover, 39 time- and frequency-domain features of EMG data from five muscles in three muscle groups were analyzed. Data from the multitude of biosignals converged and revealed concordant patterns: no differences occurred between left- and right-side dominant participants in kinetic, kinematic, or EMG outcomes during bipedal stance. Regarding single leg stance, larger knee but lower ankle joint kinematic values appeared in left vs right-sided participants during non-dominant stance. Left-vs right-sided participants also had lower medial gastrocnemius EMG activation during non-dominant stance. While right-side dominant participants always produced larger values for kinematic data of ankle joint and medial gastrocnemius EMG activation during non-dominant vs dominant unilateral stance, this pattern was the opposite for left-sided participants, showing larger values when standing on their dominant vs non-dominant leg, i.e., participants had a more stable balance when standing on their right leg. Our results suggest that side-dominance affects biomechanical and neuromuscular control strategies during unilateral standing.

An intelligent neuromarketing system for predicting consumers' future choice from electroencephalography signals

Neuromarketing utilizes Brain-Computer Interface (BCI) technologies to provide insight into consumers responses on marketing stimuli. In order to achieve insight information, marketers spend about $400 billion annually on marketing, promotion, and advertisement using traditional marketing research tools. In addition, these tools like personal depth interviews, surveys, focus group discussions, etc. are expensive and frequently criticized for failing to extract actual consumer preferences. Neuromarketing, on the other hand, promises to overcome such constraints. In this work, an EEG-based neuromarketing framework is employed for predicting consumer future choice (affective attitude) while they view E-commerce products. After preprocessing, three types of features, namely, time, frequency, and time-frequency domain features are extracted. Then, wrapper-based Support Vector Machine-Recursive Feature Elimination (SVM-RFE) along with correlation bias reduction is used for feature selection. Lastly, we use SVM for categorizing positive affective attitude and negative affective attitude. Experiments show that the frontal cortex achieves the best accuracy of 98.67±2.98, 98±3.22, and 98.67±3.52 for 5-fold, 10-fold, and leave-one-subject-out (LOSO) respectively. In addition, among all the channels, F_z achieves best accuracy 90±7.81, 90.67±9.53, and 92.67±7.03 for 5-fold, 10-fold, and LOSO respectively. Subsequently, this work opens the door for implementing such a neuromarketing framework using consumer-grade devices in a real-life setting for marketers. As a result, it is evident that EEG-based neuromarketing technologies can assist brands and enterprises in forecasting future consumer preferences accurately. Hence, it will pave the way for the creation of an intelligent marketing assistive system for neuromarketing applications in future.

Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography

Many researchers have used machine learning models to control artificial hands, walking aids, assistance suits, etc., using the biological signal of electromyography (EMG). The use of such devices requires high classification accuracy. One method for improving the classification performance of machine learning models is normalization, such as z-score. However, normalization is not used in most EMG-based motion prediction studies because of the need for calibration and fluctuation of reference value for calibration (cannot re-use). Therefore, in this study, we proposed a normalization method that combines sliding-window and z-score normalization that can be implemented in real-time processing without need for calibration. The effectiveness of this normalization method was confirmed by conducting a single-joint movement experiment of the elbow and predicting its rest, flexion, and extension movements from the EMG signal. The proposed method achieved 77.7% accuracy, an improvement of 21.5% compared to the non-normalization (56.2%). Furthermore, when using a model trained by other people’s data for application without calibration, the proposed method achieved 63.1% accuracy, an improvement of 8.8% compared to the z-score (54.4%). These results showed the effectiveness of the simple and easy-to-implement method, and that the classification performance of the machine learning model could be improved.

Review on electromyography based intention for upper limb control using pattern recognition for human-machine interaction

Upper limb myoelectric prosthetic control is an essential topic in the field of rehabilitation. The technique controls prostheses using surface electromyogram (sEMG) and intramuscular EMG (iEMG) signals. EMG signals are extensively used in controlling prosthetic upper and lower limbs, virtual reality entertainment, and human-machine interface (HMI). EMG signals are vital parameters for machine learning and deep learning algorithms and help to give an insight into the human brain’s function and mechanisms. Pattern recognition techniques pertaining to support vector machine (SVM), k-nearest neighbor (KNN) and Bayesian classifiers have been utilized to classify EMG signals. This paper presents a review on current EMG signal techniques, including electrode array utilization, signal acquisition, signal preprocessing and post-processing, feature selection and extraction, data dimensionality reduction, classification, and ultimate application to the community. The paper also discusses using alternatives to EMG signals, such as force sensors, to measure muscle activity with reliable results. Future implications for EMG classification include employing deep learning techniques such as artificial neural networks (ANN) and recurrent neural networks (RNN) for achieving robust results.

Electromyogram-Based Classification of Hand and Finger Gestures Using Artificial Neural Networks

Electromyogram (EMG) signals have been increasingly used for hand and finger gesture recognition. However, most studies have focused on the wrist and whole-hand gestures and not on individual finger (IF) gestures, which are considered more challenging. In this study, we develop EMG-based hand/finger gesture classifiers based on fixed electrode placement using machine learning methods. Ten healthy subjects performed ten hand/finger gestures, including seven IF gestures. EMG signals were measured from three channels, and six time-domain (TD) features were extracted from each channel. A total of 18 features was used to build personalized classifiers for ten gestures with an artificial neural network (ANN), a support vector machine (SVM), a random forest (RF), and a logistic regression (LR). The ANN, SVM, RF, and LR achieved mean accuracies of 0.940, 0.876, 0.831, and 0.539, respectively. One-way analyses of variance and F-tests showed that the ANN achieved the highest mean accuracy and the lowest inter-subject variance in the accuracy, respectively, suggesting that it was the least affected by individual variability in EMG signals. Using only TD features, we achieved a higher ratio of gestures to channels than other similar studies, suggesting that the proposed method can improve the system usability and reduce the computational burden.

Gesture Classification of Surface Electromyography Signals Using Machine Learning Algorithms for Hand Prosthetics

The actions of humans executed by their hands play a remarkable part in controlling and handling variety of objects in their daily life activities. The effect of losing or degradation in the functioning of one hand has a greater influence in bringing down the regular activity. Hence the design of prosthetic hands which assists the individuals to enhance their regular activity seems a better remedy in this new era. This paper puts forward a classification framework using machine learning algorithms for classifying hand gesture signals. The surface electromyography (sEMG) dataset acquired for 9 wrist movements of publicly available database are utilized to identify the potential biomarkers for classification and in evaluating the efficacy of the proposed algorithm. The statistical and time domain features of the sEMG signals from 27 intact subjects and 11 trans-radial amputated subjects are extracted and the optimal features are determined implementing the feature selection approach based on correlation factor. The classifiers performance of machine learning algorithms namely support vector machine (SVM), Naïve bayes (NB) and Ensemble classifier are evaluated. The experimental results highlight that the SVM classifier can yield the maximum accuracy movement classification of 99.6% for intact and 97.56% for trans-amputee subjects. The proposed approach offers better accuracy and sensitivity compared to other approaches that have used the sEMG dataset for movement classification.

Simplified Optimal Estimation of Time-Varying Electromyogram Standard Deviation (EMGσ): Evaluation on Two Datasets

To facilitate the broader use of EMG signal whitening, we studied four whitening procedures of various complexities, as well as the roles of sampling rate and noise correction. We separately analyzed force-varying and constant-force contractions from 64 subjects who completed constant-posture tasks about the elbow over a range of forces from 0% to 50% maximum voluntary contraction (MVC). From the constant-force tasks, we found that noise correction via the root difference of squares (RDS) method consistently reduced EMG recording noise, often by a factor of 5-10. All other primary results were from the force-varying contractions. Sampling at 4096 Hz provided small and statistically significant improvements over sampling at 2048 Hz (~3%), which, in turn, provided small improvements over sampling at 1024 Hz (~4%). In comparing equivalent processing variants at a sampling rate of 4096 Hz, whitening filters calibrated to the EMG spectrum of each subject generally performed best (4.74% MVC EMG-force error), followed by one universal whitening filter for all subjects (4.83% MVC error), followed by a high-pass filter whitening method (4.89% MVC error) and then a first difference whitening filter (4.91% MVC error)-but none of these statistically differed. Each did significantly improve from EMG-force error without whitening (5.55% MVC). The first difference is an excellent whitening option over this range of contraction forces since no calibration or algorithm decisions are required.

Muscle network topology analysis for the classification of chronic neck pain based on EMG biomarkers extracted during walking

Neuromuscular impairments are frequently observed in patients with chronic neck pain (CNP). This study uniquely investigates whether changes in neck muscle synergies detected during gait are sensitive enough to differentiate between people with and without CNP. Surface electromyography (EMG) was recorded from the sternocleidomastoid, splenius capitis, and upper trapezius muscles bilaterally from 20 asymptomatic individuals and 20 people with CNP as they performed rectilinear and curvilinear gait. Intermuscular coherence was computed to generate the functional inter-muscle connectivity network, the topology of which is quantified based on a set of graph measures. Besides the functional network, spectrotemporal analysis of each EMG was used to form the feature set. With the use of Neighbourhood Component Analysis (NCA), we identified the most significant features and muscles for the classification/differentiation task conducted using K-Nearest Neighbourhood (K-NN), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) algorithms. The NCA algorithm selected features from muscle network topology as one of the most relevant feature sets, which further emphasize the presence of major differences in muscle network topology between people with and without CNP. Curvilinear gait achieved the best classification performance through NCA-SVM based on only 16 features (accuracy: 85.00%, specificity: 81.81%, and sensitivity: 88.88%). Intermuscular muscle networks can be considered as a new sensitive tool for the classification of people with CNP. These findings further our understanding of how fundamental muscle networks are altered in people with CNP.

A Multi-DoF Prosthetic Hand Finger Joint Controller for Wearable sEMG Sensors by Nonlinear Autoregressive Exogenous Model

The loss of mobility function and sensory information from the arm, hand, and fingertips hampers the activities of daily living (ADL) of patients. A modern bionic prosthetic hand can compensate for the lost functions and realize multiple degree of freedom (DoF) movements. However, the commercially available prosthetic hands usually have limited DoFs due to limited sensors and lack of stable classification algorithms. This study aimed to propose a controller for finger joint angle estimation by surface electromyography (sEMG). The sEMG data used for training were gathered with the Myo armband, which is a commercial EMG sensor. Two features in the time domain were extracted and fed into a nonlinear autoregressive model with exogenous inputs (NARX). The NARX model was trained with pre-selected parameters using the Levenberg-Marquardt algorithm. Comparing with the targets, the regression correlation coefficient (R) of the model outputs was more than 0.982 over all test subjects, and the mean square error was less than 10.02 for a signal range in arbitrary units equal to [0, 255]. The study also demonstrated that the proposed model could be used in daily life movements with good accuracy and generalization abilities.

Electronic Devices for Stress Detection in Academic Contexts during Confinement Because of the COVID-19 Pandemic

This article studies the development and implementation of different electronic devices for measuring signals during stress situations, specifically in academic contexts in a student group of the Engineering Department at the University of Pamplona (Colombia). For the research’s development, devices for measuring physiological signals were used through a Galvanic Skin Response (GSR), the electrical response of the heart by using an electrocardiogram (ECG), the electrical activity produced by the upper trapezius muscle (EMG), and the development of an electronic nose system (E-nose) as a pilot study for the detection and identification of the Volatile Organic Compounds profiles emitted by the skin. The data gathering was taken during an online test (during the COVID-19 Pandemic), in which the aim was to measure the student’s stress state and then during the relaxation state after the exam period. Two algorithms were used for the data process, such as Linear Discriminant Analysis and Support Vector Machine through the Python software for the classification and differentiation of the assessment, achieving 100% of classification through GSR, 90% with the E-nose system proposed, 90% with the EMG system, and 88% success by using ECG, respectively.

A Review of Algorithm & Hardware Design for AI-Based Biomedical Applications

This paper reviews the state of the arts and trends of the AI-Based biomedical processing algorithms and hardware. The algorithms and hardware for different biomedical applications such as ECG, EEG and hearing aid have been reviewed and discussed. For algorithm design, various widely used biomedical signal classification algorithms have been discussed including support vector machine (SVM), back propagation neural network (BPNN), convolutional neural networks (CNN), probabilistic neural networks (PNN), recurrent neural networks (RNN), Short-term Memory Network (LSTM), fuzzy neural network and etc. The pros and cons of the classification algorithms have been analyzed and compared in the context of application scenarios. The research trends of AI-Based biomedical processing algorithms and applications are also discussed. For hardware design, various AI-Based biomedical processors have been reviewed and discussed, including ECG classification processor, EEG classification processor, EMG classification processor and hearing aid processor. Various techniques on architecture and circuit level have been analyzed and compared. The research trends of the AI-Based biomedical processor have also been discussed.

Current Trends and Confounding Factors in Myoelectric Control: Limb Position and Contraction Intensity

This manuscript presents a hybrid study of a comprehensive review and a systematic(research) analysis. Myoelectric control is the cornerstone ofmany assistive technologies used in clinicalpractice, such as prosthetics and orthoses, and human-computer interaction, such as virtual reality control.Although the classification accuracy of such devices exceeds 90% in a controlled laboratory setting,myoelectric devices still face challenges in robustness to variability of daily living conditions.The intrinsic physiological mechanisms limiting practical implementations of myoelectric deviceswere explored: the limb position effect and the contraction intensity effect. The degradationof electromyography (EMG) pattern recognition in the presence of these factors was demonstratedon six datasets, where classification performance was 13% and 20% lower than the controlledsetting for the limb position and contraction intensity effect, respectively. The experimental designsof limb position and contraction intensity literature were surveyed. Current state-of-the-art trainingstrategies and robust algorithms for both effects were compiled and presented. Recommendationsfor future limb position effect studies include: the collection protocol providing exemplars of at least 6positions (four limb positions and three forearm orientations), three-dimensional space experimentaldesigns, transfer learning approaches, and multi-modal sensor configurations. Recommendationsfor future contraction intensity effect studies include: the collection of dynamic contractions, nonlinearcomplexity features, and proportional control.

Towards resolving the co-existing impacts of multiple dynamic factors on the performance of EMG-pattern recognition based prostheses

BACKGROUND AND OBJECTIVE

Mobility of subject (MoS) and muscle contraction force variation (MCFV) have been shown to individually degrade the performance of multiple degrees of freedom electromyogram (EMG) pattern recognition (PR) based prostheses control systems. Though these factors (MoS-MCFV) co-exist simultaneously in the practical use of the prosthesis, their combined impact on PR-based system has rarely been studied especially in the context of amputees who are the target users of the device.

METHODS

To address this problem, this study systematically investigated the co-existing impact of MoS-MCFV on the performance of PR-based movement intent classifier, using EMG recordings acquired from eight participants who performed multiple classes of targeted limb movements across static and non-static scenarios with three distinct muscle contraction force levels. Then, a robust feature extraction method that is invariant to the combined effect of MoS-MCFV, namely, invariant time-domain descriptor (invTDD), was proposed to optimally characterize the multi-class EMG signal patterns in the presence of both factors.

RESULTS

Experimental results consistently showed that the proposed invTDD method could significantly mitigate the co-existing impact of MoS-MCFV on PR-based movement-intent classifier with error reduction in the range of 7.50%~17.97% (p<0.05), compared to the commonly applied methods. Further evaluation using 2-dimentional principal component analysis (PCA) technique, revealed that the proposed invTDD method has obvious class-separability in the PCA feature space, with a significantly lower standard error (0.91%) compared to the existing methods.

CONCLUSION

This study offers compelling insight on how to develop accurately robust multiple degrees of freedom control scheme for multifunctional prostheses that would be clinically viable. Also, the study may spur positive advancement in other application areas of medical robotics that adopts myoelectric control schemes such as the electric wheelchair and human-computer-interaction systems.

Enhancing the Security of Pattern Unlock with Surface EMG-Based Biometrics

Pattern unlock is a popular screen unlock scheme that protects the sensitive data and information stored in mobile devices from unauthorized access. However, it is also susceptible to various attacks, including guessing attacks, shoulder surfing attacks, smudge attacks, and side-channel attacks, which can achieve a high success rate in breaking the patterns. In this paper, we propose a new two-factor screen unlock scheme that incorporates surface electromyography (sEMG)-based biometrics with patterns for user authentication. sEMG signals are unique biometric traits suitable for person identification, which can greatly improve the security of pattern unlock. During a screen unlock session, sEMG signals are recorded when the user draws the pattern on the device screen. Time-domain features extracted from the recorded sEMG signals are then used as the input of a one-class classifier to identify the user is legitimate or not. We conducted an experiment involving 10 subjects to test the effectiveness of the proposed scheme. It is shown that the adopted time-domain sEMG features and one-class classifiers achieve good authentication performance in terms of the F 1 score and Half of Total Error Rate (HTER). The results demonstrate that the proposed scheme is a promising solution to enhance the security of pattern unlock.

Selection of Features and Classifiers for EMG-EEG-Based Upper Limb Assistive Devices-A Review

Bio-signals are distinctive factors in the design of human-machine interface, essentially useful for prosthesis, orthosis, and exoskeletons. Despite the progress in the analysis of pattern recognition based devices; the acceptance of these devices is still questionable. One reason is the lack of information to identify the possible combinations of features and classifiers. Besides; there is also a need for optimal selection of various sensors for sensations such as touch, force, texture, along with EMGs/EEGs. This article reviews the two bio-signal techniques, named as electromyography and electroencephalography. The details of the features and the classifiers used in the data processing for upper limb assist devices are summarised here. Various features and their sets are surveyed and different classifiers for feature sets are discussed on the basis of the classification rate. The review was carried out on the basis of the last 10-12 years of published research in this area. This article also outlines the influence of modality of EMGs and EEGs with other sensors on classifications. Also, other bio-signals used in upper limb devices and future aspects are considered.

EMG-Based Real-Time Linear-Nonlinear Cascade Regression Decoding of Shoulder, Elbow, and Wrist Movements in Able-Bodied Persons and Stroke Survivors

OBJECTIVE

This study aimed to decode shoulder, elbow and wrist dynamic movements continuously and simultaneously based on multi-channel surface electromyography signals, useful for electromyography controlled exoskeleton robots for upper-limb rehabilitation.

METHODS

Ten able-bodied subjects and ten stroke subjects were instructed to voluntarily move the shoulder, elbow and wrist joints back and forth in a horizontal plane with an exoskeleton robot. The shoulder, elbow and wrist movements and surface electromyography signals from six muscles crossing the joints were recorded. A set of three parallel linear-nonlinear cascade decoders was developed to continuously estimate the selected shoulder, elbow and wrist movements based on a generalized linear model using the anterior deltoid, posterior deltoid, biceps brachii, long head triceps brachii, flexor carpi radialis, and extensor carpi radialis muscle electromyography signals as the model inputs.

RESULTS

The decoder performed well for both healthy and stroke populations. As movement smoothness decreased, decoding performance decreased for the stroke population.

CONCLUSION

The proposed method is capable of simultaneously and continuously estimating multi-joint movements of the human arm in real-time by characterizing the nonlinear mappings between muscle activity and kinematic signals based on linear regression.

SIGNIFICANCE

This may prove useful in developing myoelectric controlled exoskeletons for motor rehabilitation of neurological disorders.

Feature Extraction and Selection for Pain Recognition Using Peripheral Physiological Signals

In pattern recognition, the selection of appropriate features is paramount to both the performance and the robustness of the system. Over-reliance on machine learning-based feature selection methods can, therefore, be problematic; especially when conducted using small snapshots of data. The results of these methods, if adopted without proper interpretation, can lead to sub-optimal system design or worse, the abandonment of otherwise viable and important features. In this work, a deep exploration of pain-based emotion classification was conducted to better understand differences in the results of the related literature. In total, 155 different time domain and frequency domain features were explored, derived from electromyogram (EMG), skin conductance levels (SCL), and electrocardiogram (ECG) readings taken from the 85 subjects in response to heat-induced pain. To address the inconsistency in the optimal feature sets found in related works, an exhaustive and interpretable feature selection protocol was followed to obtain a generalizable feature set. Associations between features were then visualized using a topologically-informed chart, called Mapper, of this physiological feature space, including synthesis and comparison of results from previous literature. This topological feature chart was able to identify key sources of information that led to the formation of five main functional feature groups: signal amplitude and power, frequency information, nonlinear complexity, unique, and connecting. These functional groupings were used to extract further insight into observable autonomic responses to pain through a complementary statistical interaction analysis. From this chart, it was observed that EMG and SCL derived features could functionally replace those obtained from ECG. These insights motivate future work on novel sensing modalities, feature design, deep learning approaches, and dimensionality reduction techniques.

EMG Feature Selection and Classification Using a Pbest-Guide Binary Particle Swarm Optimization

Due to the increment in hand motion types, electromyography (EMG) features are increasingly required for accurate EMG signals classification. However, increasing in the number of EMG features not only degrades classification performance, but also increases the complexity of the classifier. Feature selection is an effective process for eliminating redundant and irrelevant features. In this paper, we propose a new personal best (Pbest) guide binary particle swarm optimization (PBPSO) to solve the feature selection problem for EMG signal classification. First, the discrete wavelet transform (DWT) decomposes the signal into multiresolution coefficients. The features are then extracted from each coefficient to form the feature vector. After which pbest-guide binary particle swarm optimization (PBPSO) is used to evaluate the most informative features from the original feature set. In order to measure the effectiveness of PBPSO, binary particle swarm optimization (BPSO), genetic algorithm (GA), modified binary tree growth algorithm (MBTGA), and binary differential evolution (BDE) were used for performance comparison. Our experimental results show the superiority of PBPSO over other methods, especially in feature reduction; where it can reduce more than 90% of features while keeping a very high classification accuracy. Hence, PBPSO is more appropriate for application in clinical and rehabilitation applications.

Device-measured physical activity data for classification of patients with ventricular arrhythmia events: A pilot investigation

Low levels of physical activity are associated with increased mortality risk, especially in cardiac patients, but most studies are based on self-report. Cardiac implantable electronic devices (CIEDs) offer an opportunity to collect data for longer periods of time. However, there is limited agreement on the best approaches for quantification of activity measures due to the time series nature of the data. We examined physical activity time series data from 235 subjects with CIEDs and at least 365 days of uninterrupted measures. Summary statistics for raw daily physical activity (minutes/day), including statistical moments (e.g., mean, standard deviation, skewness, kurtosis), time series regression coefficients, frequency domain components, and forecasted predicted values, were calculated for each individual, and used to predict occurrence of ventricular tachycardia (VT) events as recorded by the device. In unsupervised analyses using principal component analysis, we found that while certain features tended to cluster near each other, most provided a reasonable spread across activity space without a large degree of redundancy. In supervised analyses, we found several features that were associated with the outcome (P < 0.05) in univariable and multivariable approaches, but few were consistent across models. Using a machine-learning approach in which the data was split into training and testing sets, and models ranging in complexity from simple univariable logistic regression to ensemble decision trees were fit, there was no improvement in classification of risk over naïve methods for any approach. Although standard approaches identified summary features of physical activity data that were correlated with risk of VT, machine-learning approaches found that none of these features provided an improvement in classification. Future studies are needed to explore and validate methods for feature extraction and machine learning in classification of VT risk based on device-measured activity.

Navigating features: a topologically informed chart of electromyographic features space

The success of biological signal pattern recognition depends crucially on the selection of relevant features. Across signal and imaging modalities, a large number of features have been proposed, leading to feature redundancy and the need for optimal feature set identification. A further complication is that, due to the inherent biological variability, even the same classification problem on different datasets can display variations in the respective optimal sets, casting doubts on the generalizability of relevant features. Here, we approach this problem by leveraging topological tools to create charts of features spaces. These charts highlight feature sub-groups that encode similar information (and their respective similarities) allowing for a principled and interpretable choice of features for classification and analysis. Using multiple electromyographic (EMG) datasets as a case study, we use this feature chart to identify functional groups among 58 state-of-the-art EMG features, and to show that they generalize across three different forearm EMG datasets obtained from able-bodied subjects during hand and finger contractions. We find that these groups describe meaningful non-redundant information, succinctly recapitulating information about different regions of feature space. We then recommend representative features from each group based on maximum class separability, robustness and minimum complexity.

Feature Extraction and Selection for Myoelectric Control Based on Wearable EMG Sensors

Specialized myoelectric sensors have been used in prosthetics for decades, but, with recent advancements in wearable sensors, wireless communication and embedded technologies, wearable electromyographic (EMG) armbands are now commercially available for the general public. Due to physical, processing, and cost constraints, however, these armbands typically sample EMG signals at a lower frequency (e.g., 200 Hz for the Myo armband) than their clinical counterparts. It remains unclear whether existing EMG feature extraction methods, which largely evolved based on EMG signals sampled at 1000 Hz or above, are still effective for use with these emerging lower-bandwidth systems. In this study, the effects of sampling rate (low: 200 Hz vs. high: 1000 Hz) on the classification of hand and finger movements were evaluated for twenty-six different individual features and eight sets of multiple features using a variety of datasets comprised of both able-bodied and amputee subjects. The results show that, on average, classification accuracies drop significantly (p< 0.05) from 2% to 56% depending on the evaluated features when using the lower sampling rate, and especially for transradial amputee subjects. Importantly, for these subjects, no number of existing features can be combined to compensate for this loss in higher-frequency content. From these results, we identify two new sets of recommended EMG features (along with a novel feature, L-scale) that provide better performance for these emerging low-sampling rate systems.

Analysis of the Biceps Brachii Muscle by Varying the Arm Movement Level and Load Resistance Band

Biceps brachii muscle illness is one of the common physical disabilities that requires rehabilitation exercises in order to build up the strength of the muscle after surgery. It is also important to monitor the condition of the muscle during the rehabilitation exercise through electromyography (EMG) signals. The purpose of this study was to analyse and investigate the selection of the best mother wavelet (MWT) function and depth of the decomposition level in the wavelet denoising EMG signals through the discrete wavelet transform (DWT) method at each decomposition level. In this experimental work, six healthy subjects comprised of males and females (26 ± 3.0 years and BMI of 22 ± 2.0) were selected as a reference for persons with the illness. The experiment was conducted for three sets of resistance band loads, namely, 5 kg, 9 kg, and 16 kg, as a force during the biceps brachii muscle contraction. Each subject was required to perform three levels of the arm angle positions (30°, 90°, and 150°) for each set of resistance band load. The experimental results showed that the Daubechies5 (db5) was the most appropriate DWT method together with a 6-level decomposition with a soft heursure threshold for the biceps brachii EMG signal analysis.

A Framework of Temporal-Spatial Descriptors-Based Feature Extraction for Improved Myoelectric Pattern Recognition

The extraction of the accurate and efficient descriptors of muscular activity plays an important role in tackling the challenging problem of myoelectric control of powered prostheses. In this paper, we present a new feature extraction framework that aims to give an enhanced representation of muscular activities through increasing the amount of information that can be extracted from individual and combined electromyogram (EMG) channels. We propose to use time-domain descriptors (TDDs) in estimating the EMG signal power spectrum characteristics; a step that preserves the computational power required for the construction of spectral features. Subsequently, TDD is used in a process that involves: 1) representing the temporal evolution of the EMG signals by progressively tracking the correlation between the TDD extracted from each analysis time window and a nonlinearly mapped version of it across the same EMG channel and 2) representing the spatial coherence between the different EMG channels, which is achieved by calculating the correlation between the TDD extracted from the differences of all possible combinations of pairs of channels and their nonlinearly mapped versions. The proposed temporal-spatial descriptors (TSDs) are validated on multiple sparse and high-density (HD) EMG data sets collected from a number of intact-limbed and amputees performing a large number of hand and finger movements. Classification results showed significant reductions in the achieved error rates in comparison to other methods, with the improvement of at least 8% on average across all subjects. Additionally, the proposed TSDs achieved significantly well in problems with HD-EMG with average classification errors of <5% across all subjects using windows lengths of 50 ms only.

Classification of ankle joint movements based on surface electromyography signals for rehabilitation robot applications

Electromyography (EMG)-based control is the core of prostheses, orthoses, and other rehabilitation devices in recent research. Nonetheless, EMG is difficult to use as a control signal given the complex nature of the signal. To overcome this problem, the researchers employed a pattern recognition technique. EMG pattern recognition mainly involves four stages: signal detection, preprocessing feature extraction, dimensionality reduction, and classification. In particular, the success of any pattern recognition technique depends on the feature extraction stage. In this study, a modified time-domain features set and logarithmic transferred time-domain features (LTD) were evaluated and compared with other traditional time-domain features set (TTD). Three classifiers were employed to assess the two feature sets, namely linear discriminant analysis (LDA), k nearest neighborhood, and Naïve Bayes. Results indicated the superiority of the new time-domain feature set LTD, on conventional time-domain features TTD with the average classification accuracy of 97.23 %. In addition, the LDA classifier outperformed the other two classifiers considered in this study.

Automated integration of wireless biosignal collection devices for patient-centred decision-making in point-of-care systems

The proper acquisition of biosignals data from various biosensor devices and their remote accessibility are still issues that prevent the wide adoption of point-of-care systems in the routine of monitoring chronic patients. This Letter presents an advanced framework for enabling patient monitoring that utilises a cloud computing infrastructure for data management and analysis. The framework introduces also a local mechanism for uniform biosignals collection from wearables and biosignal sensors, and decision support modules, in order to enable prompt and essential decisions. A prototype smartphone application and the related cloud modules have been implemented for demonstrating the value of the proposed framework. Initial results regarding the performance of the system and the effectiveness in data management and decision-making have been quite encouraging.