Identification of constant-posture EMG-torque relationship about the elbow using nonlinear dynamic models

Consensus for experimental design in electromyography (CEDE) project: Application of EMG to estimate muscle force

Skeletal muscles power movement. Deriving the forces produced by individual muscles has applications across various fields including biomechanics, robotics, and rehabilitation. Since direct in vivo measurement of muscle force in humans is invasive and challenging, its estimation through non-invasive methods such as electromyography (EMG) holds considerable appeal. This matrix, developed by the Consensus for Experimental Design in Electromyography (CEDE) project, summarizes recommendations on the use of EMG to estimate muscle force. The matrix encompasses the use of bipolar surface EMG, high density surface EMG, and intra-muscular EMG (1) to identify the onset of muscle force during isometric contractions, (2) to identify the offset of muscle force during isometric contractions, (3) to identify force fluctuations during isometric contractions, (4) to estimate force during dynamic contractions, and (5) in combination with musculoskeletal models to estimate force during dynamic contractions. For each application, recommendations on the appropriateness of using EMG to estimate force and justification for each recommendation are provided. The achieved consensus makes clear that there are limited scenarios in which EMG can be used to accurately estimate muscle forces. In most cases, it remains important to consider the activation as well as the muscle state and other biomechanical and physiological factors- such as in the context of a formal mechanical model. This matrix is intended to encourage interdisciplinary discussions regarding the integration of EMG with other experimental techniques and to promote advances in the application of EMG towards developing muscle models and musculoskeletal simulations that can accurately predict muscle forces in healthy and clinical populations.

Multi-branch deep learning neural network prediction model for the development of angular biosensors based on sEMG

Introduction

Human gait motion intention recognition is very important for the lower extremity exoskeleton robot to accurately synchronize and respond to the user's natural motion. And motion intention recognition is generally performed through sEMG. Deep learning neural networks perform well in dealing with high-dimensional data and nonlinear relationships such as sEMG, but different deep learning neural networks have their own advantages in dealing with different types of data. Therefore, a multi-branch deep learning neural network, which enables different neural networks to process different feature items, could achieve more accurate and efficient motion intention recognition. The purpose of this study is to 1) Establish a multi-branch deep learning neural network model to achieve accurate gait recognition and effective estimation of joint angles. 2) Quantify the performance of the multi-branch deep learning neural network model in gait recognition and joint angle prediction using sEMG.

Methodology

This study involved the collection of sEMG and plantar pressure data during walking in human subjects. Firstly, the collected signals are filtered and denoised to ensure the quality and reliability of the data. Calculate the time domain features and the frequency domain features to capture the key information of gait. Then, using the sensitivity difference of different structural neural networks to different feature data, a multi-branch deep learning neural network model is developed, in which the extracted features are used as the input of the model. The output of the model includes gait cycle and joint angle, so as to realize the accurate recognition of human gait and the effective estimation of joint angle.

Results

The results show that the proposed method has high accuracy in identifying human gait and estimating joint angles. The multi-branch neural network model successfully integrates time-domain and frequency-domain features and provides reliable prediction of gait cycle and joint angle. The highest accuracy of gait recognition is 95.42%, the lowest is 90.11%, and the average is 92.16%. The average error of joint angle estimation is 3.19.

Discussion

This study designed a human walking gait recognition and joint angle prediction model to achieve accurate human lower limb motion intention recognition.The model can be integrated into the sEMG sensor to design a angular biosensors, which can predict the human joint angle in real time.

Evaluation of generic EMG-Torque models across two Upper-Limb joints

Advanced single-use dynamic EMG-torque models require burdensome subject-specific calibration contractions and have historically been assumed to produce lower error than generic models (i.e., models that are identical across subjects and muscles). To investigate this assumption, we studied generic one degree of freedom (DoF) models derived from the ensemble median of subject-specific models, evaluated across subject, DoF and joint. We used elbow (N = 64) and hand-wrist (N = 9) datasets. Subject-specific elbow models performed statistically better [5.79 ± 1.89 %MVT (maximum voluntary torque) error] than generic elbow models (6.21 ± 1.85 %MVT error). However, there were no statistical differences between subject-specific vs. generic models within each hand-wrist DoF. Next, we evaluated generic models across joints. The best hand-wrist generic model had errors of 6.29 ± 1.85 %MVT when applied to the elbow. The elbow generic model had errors of 7.04 ± 2.29 %MVT when applied to the hand-wrist. The generic elbow model was statistically better in both joints, compared to the generic hand-wrist model. Finally, we tested Butterworth filter models (a simpler generic model), finding no statistical differences between optimum Butterworth and subject-specific models. Overall, generic models simplified EMG-torque training without substantive performance degradation and provided the possibility of transfer learning between joints.

Continuous online prediction of lower limb joints angles based on sEMG signals by deep learning approach

Continuous online prediction of human joints angles is a key point to improve the performance of man-machine cooperative control. In this study, a framework of online prediction method of joints angles by long short-term memory (LSTM) neural network only based on surface electromyography (sEMG) signals was proposed. The sEMG signals from eight muscles of five subjects' right leg and three joints angles and plantar pressure signals of subjects were collected simultaneously. Different inputs (only sEMG (unimodal), sEMG combined with plantar pressure (multimodal)) after online feature extraction and standardization were used for training the angle online prediction model by LSTM. The results indicate that there is no significant difference between the two kinds of inputs for LSTM model and the proposed method can make up for the shortage of using a single type of sensor. The range of mean values of root square mean error, mean absolute error and Pearson correlation coefficient of the three joints angles achieved by the proposed model only with the input of sEMG under four kinds of predicted time (50, 100, 150, and 200 ms) are [1.63°,3.20°],[1.27°, 2.36°] and [0.9747, 0.9935]. Three popular machine learning algorithms with different inputs were compared to the proposed model only based on sEMG. Experiment results demonstrate that the proposed method has the best prediction performance and there are highly significant differences between it and other methods. The difference of prediction results under different gait phases by the proposed method was also analyzed. The results indicate that the prediction effect of support phases is generally better than that of swing phases. Above experimental results show that the proposed method can realize accurate online joint angle prediction and has better performance to promote man-machine cooperation.

Continuous grip force estimation from surface electromyography using generalized regression neural network

BACKGROUND

Grip force estimation is highly required in realizing flexible and accurate prosthetic control.

OBJECTIVE

This study presents a method to accurately estimate continuous grip force from surface electromyography (sEMG) under three forearm postures for unilateral amputees.

METHODS

Ten able-bodied subjects and a transradial amputee were recruited. sEMG signals were recorded from six forearm muscles on the dominant side of each able-bodied subject and the stump of amputee. Meanwhile, grip force was synchronously measured from the ipsilateral hands of able-bodied subjects and contralateral hand of amputee. Three force profiles (triangle, trapezoid, and fast triangle) were tested under three forearm postures (supination, neutral and pronation). Two algorithms (Generalized Regression Neural Network (GRNN) and Multilinear Regression Model (MLR)) were compared using several EMG features. The estimation performance was evaluated by coefficient of determination (R2) and mean absolute error (MAE).

RESULTS

The optimal regressor combining TD and GRNN achieved R2= 96.33 ± 1.13% and MAE= 2.11 ± 0.52% for the intact subjects, and R2= 86.86% and MAE= 2.13% for the amputee. The results indicated that multiple grip force curves under three forearm postures could be accurately estimated for unilateral amputees using mirrored bilateral training.

CONCLUSIONS

The proposed method has the potential for precise force control of prosthetic hands.

Myoelectric Control Performance of Two Degree of Freedom Hand-Wrist Prosthesis by Able-Bodied and Limb-Absent Subjects

Recent research has advanced two degree-of-freedom (DoF), simultaneous, independent and proportional control of hand-wrist prostheses using surface electromyogram signals from remnant muscles as the control input. We evaluated two such regression-based controllers, along with conventional, sequential two-site control with co-contraction mode switching (SeqCon), in box-block, refined-clothespin and door-knob tasks, on 10 able-bodied and 4 limb-absent subjects. Subjects operated a commercial hand and wrist using a socket bypass harness. One 2-DoF controller (DirCon) related the intuitive hand actions of open-close and pronation-supination to the associated prosthesis hand-wrist actions, respectively. The other (MapCon) mapped myoelectrically more distinct, but less intuitive, actions of wrist flexion-extension and ulnar-radial deviation. Each 2-DoF controller was calibrated from separate 90 s calibration contractions. SeqCon performed better statistically than MapCon in the predominantly 1-DoF box-block task (>20 blocks/minute vs. 8-18 blocks/minute, on average). In this task, SeqCon likely benefited from an ability to easily focus on 1-DoF and not inadvertently trigger co-contraction for mode switching. The remaining two tasks require 2-DoFs, and both 2-DoF controllers each performed better (factor of 2-4) than SeqCon. We also compared the use of 12 vs. 6 optimally-selected EMG electrodes as inputs, finding no statistical difference. Overall, we provide further evidence of the benefits of regression-based EMG prosthesis control of 2-DoFs in the hand-wrist.

sEMG-Based Continuous Estimation of Finger Kinematics via Large-Scale Temporal Convolutional Network

Since continuous motion control can provide a more natural, fast and accurate man–machine interface than that of discrete motion control, it has been widely used in human–robot cooperation (HRC). Among various biological signals, the surface electromyogram (sEMG)—the signal of actions potential superimposed on the surface of the skin containing the temporal and spatial information—is one of the best signals with which to extract human motion intentions. However, most of the current sEMG control methods can only perform discrete motion estimation, and thus fail to meet the requirements of continuous motion estimation. In this paper, we propose a novel method that applies a temporal convolutional network (TCN) to sEMG-based continuous estimation. After analyzing the relationship between the convolutional kernel’s size and the lengths of atomic segments (defined in this paper), we propose a large-scale temporal convolutional network (LS-TCN) to overcome the TCN’s problem: that it is difficult to fully extract the sEMG’s temporal features. When applying our proposed LS-TCN with a convolutional kernel size of 1 × 31 to continuously estimate the angles of the 10 main joints of fingers (based on the public dataset Ninapro), it can achieve a precision rate of 71.6%. Compared with TCN (kernel size of 1 × 3), LS-TCN (kernel size of 1 × 31) improves the precision rate by 6.6%.

Elbow Motion Trajectory Prediction Using a Multi-Modal Wearable System: A Comparative Analysis of Machine Learning Techniques

Motion intention detection is fundamental in the implementation of human-machine interfaces applied to assistive robots. In this paper, multiple machine learning techniques have been explored for creating upper limb motion prediction models, which generally depend on three factors: the signals collected from the user (such as kinematic or physiological), the extracted features and the selected algorithm. We explore the use of different features extracted from various signals when used to train multiple algorithms for the prediction of elbow flexion angle trajectories. The accuracy of the prediction was evaluated based on the mean velocity and peak amplitude of the trajectory, which are sufficient to fully define it. Results show that prediction accuracy when using solely physiological signals is low, however, when kinematic signals are included, it is largely improved. This suggests kinematic signals provide a reliable source of information for predicting elbow trajectories. Different models were trained using 10 algorithms. Regularization algorithms performed well in all conditions, whereas neural networks performed better when the most important features are selected. The extensive analysis provided in this study can be consulted to aid in the development of accurate upper limb motion intention detection models.

EMG-Force and EMG-Target Models During Force-Varying Bilateral Hand-Wrist Contraction in Able-Bodied and Limb-Absent Subjects

System identification models relating forearm electromyogram (EMG) signals to phantom wrist radial-ulnar deviation force, pronation-supination moment and/or hand open-close force (EMG-force) are hampered by lack of supervised force/moment output signals in limb-absent subjects. In 12 able-bodied and 7 unilateral transradial limb-absent subjects, we studied three alternative supervised output sources in one degree of freedom (DoF) and 2-DoF target tracking tasks: (1) bilateral tracking with force feedback from the contralateral side (non-dominant for able-bodied/ sound for limb-absent subjects) with the contralateral force as the output, (2) bilateral tracking with force feedback from the contralateral side with the target as the output, and (3) dominant/limb-absent side unilateral target tracking without feedback and the target used as the output. "Best-case" EMG-force errors averaged ~ 10% of maximum voluntary contraction (MVC) when able-bodied subjects' dominant limb produced unilateral force/moment with feedback. When either bilateral tracking source was used as the model output, statistically larger errors of 12-16 %MVC resulted. The no-feedback alternative produced errors of 25-30 %MVC, which was nearly half the tested force range of ± 30 %MVC. Therefore, the no-feedback model output was not acceptable. We found little performance variation between DoFs. Many subjects struggled to perform 2-DoF target tracking.

Estimating Individual and Combined Fingertip Forces From Forearm EMG During Constant-Pose, Force-Varying Tasks

Numerous applications in areas such as ergonomics assessment, clinical biomechanics and motor control research would benefit from accurately modeling the relationship between forearm EMG and fingertip force, using conventional electrodes. Herein, we describe a methodological study of relating 12 conventional surface EMGs, applied circumferentially about the forearm, to fingertip force during constant-pose, force-varying (dynamic) contractions. We studied independent contraction of one, two, three or four fingers (thumb excluded), as well as contraction of four fingers in unison. Using regression, we found that a pseudo-inverse tolerance (ratio of largest to smallest singular value) of 0.01 was optimal. Lower values produced erratic models and higher values produced models with higher errors. EMG-force errors using one finger ranged from 2.5-3.8% maximum voluntary contraction (MVC), using the optimal pseudo-inverse tolerance. With additional fingers (two, three or four), the average error ranged from 5-8 %MVC. When four fingers contracted in unison, the average error was 4.3 %MVC.

Efficiently Training Two-DoF Hand-Wrist EMG-Force Models

Single-use EMG-force models (i.e., a new model is trained each time the electrodes are donned) are used in various areas, including ergonomics assessment, clinical biomechanics, and motor control research. For one degree of freedom (1-DoF) tasks, input-output (black box) models are common. Recently, black box models have expanded to 2-DoF tasks. To facilitate efficient training, we examined parameters of black box model training methods in 2-DoF force-varying, constant-posture tasks consisting of hand open-close combined with one wrist DoF. We found that approximately 40-60 s of training data is best, with progressively higher EMG-force errors occurring for progressively shorter training durations. Surprisingly, 2-DoF models in which the dynamics were universal across all subjects (only channel gain was trained to each subject) generally performed 15-21% better than models in which the complete dynamics were trained to each subject. In summary, lower error EMG-force models can be formed through diligent attention to optimization of these factors.

Fuzzy jump wavelet neural network based on rule induction for dynamic nonlinear system identification with real data applications

Aim

Fuzzy wavelet neural network (FWNN) has proven to be a promising strategy in the identification of nonlinear systems. The network considers both global and local properties, deals with imprecision present in sensory data, leading to desired precisions. In this paper, we proposed a new FWNN model nominated “Fuzzy Jump Wavelet Neural Network” (FJWNN) for identifying dynamic nonlinear-linear systems, especially in practical applications.

Methods

The proposed FJWNN is a fuzzy neural network model of the Takagi-Sugeno-Kang type whose consequent part of fuzzy rules is a linear combination of input regressors and dominant wavelet neurons as a sub-jump wavelet neural network. Each fuzzy rule can locally model both linear and nonlinear properties of a system. The linear relationship between the inputs and the output is learned by neurons with linear activation functions, whereas the nonlinear relationship is locally modeled by wavelet neurons. Orthogonal least square (OLS) method and genetic algorithm (GA) are respectively used to purify the wavelets for each sub-JWNN. In this paper, fuzzy rule induction improves the structure of the proposed model leading to less fuzzy rules, inputs of each fuzzy rule and model parameters. The real-world gas furnace and the real electromyographic (EMG) signal modeling problem are employed in our study. In the same vein, piecewise single variable function approximation, nonlinear dynamic system modeling, and Mackey–Glass time series prediction, ratify this method superiority. The proposed FJWNN model is compared with the state-of-the-art models based on some performance indices such as RMSE, RRSE, Rel ERR%, and VAF%.

Results

The proposed FJWNN model yielded the following results: RRSE (mean±std) of 10e-5±6e-5 for piecewise single-variable function approximation, RMSE (mean±std) of 2.6–4±2.6e-4 for the first nonlinear dynamic system modelling, RRSE (mean±std) of 1.59e-3±0.42e-3 for Mackey–Glass time series prediction, RMSE of 0.3421 for gas furnace modelling and VAF% (mean±std) of 98.24±0.71 for the EMG modelling of all trial signals, indicating a significant enhancement over previous methods.

Conclusions

The FJWNN demonstrated promising accuracy and generalization while moderating network complexity. This improvement is due to applying main useful wavelets in combination with linear regressors and using fuzzy rule induction. Compared to the state-of-the-art models, the proposed FJWNN yielded better performance and, therefore, can be considered a novel tool for nonlinear system identification.

Estimating Biomechanical Time-Series with Wearable Sensors: A Systematic Review of Machine Learning Techniques

Wearable sensors have the potential to enable comprehensive patient characterization and optimized clinical intervention. Critical to realizing this vision is accurate estimation of biomechanical time-series in daily-life, including joint, segment, and muscle kinetics and kinematics, from wearable sensor data. The use of physical models for estimation of these quantities often requires many wearable devices making practical implementation more difficult. However, regression techniques may provide a viable alternative by allowing the use of a reduced number of sensors for estimating biomechanical time-series. Herein, we review 46 articles that used regression algorithms to estimate joint, segment, and muscle kinematics and kinetics. We present a high-level comparison of the many different techniques identified and discuss the implications of our findings concerning practical implementation and further improving estimation accuracy. In particular, we found that several studies report the incorporation of domain knowledge often yielded superior performance. Further, most models were trained on small datasets in which case nonparametric regression often performed best. No models were open-sourced, and most were subject-specific and not validated on impaired populations. Future research should focus on developing open-source algorithms using complementary physics-based and machine learning techniques that are validated in clinically impaired populations. This approach may further improve estimation performance and reduce barriers to clinical adoption.

Two degrees of freedom, dynamic, hand-wrist EMG-force using a minimum number of electrodes

Few studies have related the surface electromyogram (EMG) of forearm muscles to two degree of freedom (DoF) hand-wrist forces; ones that have, used large high-density electrode arrays that are impractical for most applied biomechanics research. Hence, we researched EMG-force in two DoFs-hand open-close paired with one wrist DoF-using as few as four conventional electrodes, comparing equidistant placement about the forearm to optimized site selection. Nine subjects produced 1-DoF and 2-DoF uniformly distributed random forces (bandlimited to 0.75 Hz) up to 30% maximum voluntary contraction (MVC). EMG standard deviation (EMGσ) was related to force offline using linear dynamic regression models. For 1-DoF forces, average RMS errors using two optimally-sited electrodes ranged from 8.3 to 9.0 %MVC, depending on the DoF. For 2-DoFs, overall performance was best when training from both 1- and 2-DoF trials, giving average RMS errors using four optimally-sited electrodes of 9.2 %MVC for each DoF pair (hand open-close paired with one wrist DoF). For each model, additional optimally-sited electrodes showed little statistical improvement. Electrodes placed equidistant performed noticeably poorer than an equal number of electrodes that were optimally sited. The results suggest that reliable 2-DoF hand-wrist EMG-force with a small number of electrodes may be feasible.

Single-trial estimation of quasi-static EMG-to-joint-mechanical-impedance relationship over a range of joint torques

Joint mechanical impedance is commonly measured by applying dynamic perturbations about a joint at a fixed operating point/background torque, and quantifying torque change vs. angle change. Impedance characterization in functional tasks, therefore, requires multiple experimental trials over a range of operating points-a cumbersome, invasive, time-consuming and impractical task. As an alternative, studies have related EMG to impedance, after which EMG can estimate impedance without applying joint perturbations. But, the cumbersome calibration trials are still required. We describe a method of single contraction perturbations in which the background torque slowly ramps over the operating range, with EMG simultaneously acquired. Using one such "quasi-static" contraction for model training and another for testing, we show this method to be a reasonable surrogate for traditional second-order, linear impedance modeling. A simple, short-duration calibration results. We compared our single-trial ramp method to multiple constant background torque trials at 10, 20, 30, and 40% maximum effort (extension and flexion), finding only limited differences in traditional vs. EMG-based ramp impedance estimates (12-22%, most prominent at the two lower contraction levels). Such constant force and slowly-variable force contractions are relevant to many practical applications, including ergonomics assessment, prosthetic control and clinical biomechanics.

Real-time, simultaneous myoelectric control using a convolutional neural network

The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts' law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration.

Evaluating Muscle Activation Models for Elbow Motion Estimation

Adoption of wearable assistive technologies relies heavily on improvement of existing control system models. Knowing which models to use and how to improve them is difficult to determine due to the number of proposed solutions with relatively little broad comparisons. One type of these models, muscle activation models, describes the nonlinear relationship between neural inputs and mechanical activation of the muscle. Many muscle activation models can be found in the literature, but no comparison is available to guide the community on limitations and improvements. In this research, an EMG-driven elbow motion model is developed for the purpose of evaluating muscle activation models. Seven muscle activation models are used in an optimization procedure to determine which model has the best performance. Root mean square errors in muscle torque estimation range from 1.67–2.19 Nm on average over varying input trajectories. The computational resource demand was also measured during the optimization procedure, as it is an important aspect for determining if a model is feasible for use in a particular wearable assistive device. This study provides insight into the ability of these models to estimate elbow motion and the trade-off between estimation accuracy and computational demand.

Simultaneous and Continuous Estimation of Shoulder and Elbow Kinematics from Surface EMG Signals

In this paper, we present a simultaneous and continuous kinematics estimation method for multiple DoFs across shoulder and elbow joint. Although simultaneous and continuous kinematics estimation from surface electromyography (EMG) is a feasible way to achieve natural and intuitive human-machine interaction, few works investigated multi-DoF estimation across the significant joints of upper limb, shoulder and elbow joints. This paper evaluates the feasibility to estimate 4-DoF kinematics at shoulder and elbow during coordinated arm movements. Considering the potential applications of this method in exoskeleton, prosthetics and other arm rehabilitation techniques, the estimation performance is presented with different muscle activity decomposition and learning strategies. Principle component analysis (PCA) and independent component analysis (ICA) are respectively employed for EMG mode decomposition with artificial neural network (ANN) for learning the electromechanical association. Four joint angles across shoulder and elbow are simultaneously and continuously estimated from EMG in four coordinated arm movements. By using ICA (PCA) and single ANN, the average estimation accuracy 91.12% (90.23%) is obtained in 70-s intra-cross validation and 87.00% (86.30%) is obtained in 2-min inter-cross validation. This result suggests it is feasible and effective to use ICA (PCA) with single ANN for multi-joint kinematics estimation in variant application conditions.

Two degrees of freedom quasi-static EMG-force at the wrist using a minimum number of electrodes

Surface electromyogram-controlled powered hand/wrist prostheses return partial upper-limb function to limb-absent persons. Typically, one degree of freedom (DoF) is controlled at a time, with mode switching between DoFs. Recent research has explored using large-channel EMG systems to provide simultaneous, independent and proportional (SIP) control of two joints-but such systems are not practical in current commercial prostheses. Thus, we investigated site selection of a minimum number of conventional EMG electrodes in an EMG-force task, targeting four sites for a two DoF controller. In a laboratory experiment with 10 able-bodied subjects and three limb-absent subjects, 16 electrodes were placed about the proximal forearm. Subjects produced 1-DoF and 2-DoF slowly force-varying contractions up to 30% maximum voluntary contraction (MVC). EMG standard deviation was related to forces via regularized regression. Backward stepwise selection was used to retain those progressively fewer electrodes that exhibited minimum error. For 1-DoF models using two retained electrodes (which mimics the current state of the art), subjects had average RMS errors of (depending on the DoF): 7.1-9.5% MVC for able-bodied and 13.7-17.1% MVC for limb-absent subjects. For 2-DoF models, subjects using four electrodes had errors on 1-DoF trials of 6.7-8.5% MVC for able-bodied and 11.9-14.0% MVC for limb-absent; and errors on 2-DoF trials of 9.9-11.2% MVC for able-bodied and 15.8-16.7% MVC for limb-absent subjects. For each model, retaining more electrodes did not statistically improve performance. The able-bodied results suggest that backward selection is a viable method for minimum error selection of as few as four electrode sites for these EMG-force tasks. Performance evaluation in a prosthesis control task is a necessary and logical next step for this site selection method.

Comparison of Constant-Posture Force-Varying EMG-Force Dynamic Models About the Elbow

Numerous techniques have been used to minimize error in relating the surface electromyogram (EMG) to elbow joint torque. We compare the use of three techniques to further reduce error. First, most EMG-torque models only use estimates of EMG standard deviation as inputs. We studied the additional features of average waveform length, slope sign change rate and zero crossing rate. Second, multiple channels of EMG from the biceps, and separately from the triceps, have been combined to produce two low-variance model inputs. We contrasted this channel combination with using each EMG separately. Third, we previously modeled nonlinearity in the EMG-torque relationship via a polynomial. We contrasted our model versus that of the classic exponential power law of Vredenbregt and Rau (1973). Results from 65 subjects performing constant-posture, force-varying contraction gave a "baseline" comparison error (i.e., error with none of the new techniques) of 5.5 ± 2.3% maximum flexion voluntary contraction (%MVC_F). Combining the techniques of multiple features with individual channels reduced error to 4.8 ± 2.2 %MVC_F, while combining individual channels with the power-law model reduced error to 4.7 ± 2.0 %MVC_F. The new techniques further reduced error from that of the baseline by ≈ 15 %.

Real-time estimation of FES-induced joint torque with evoked EMG : Application to spinal cord injured patients

Background

Functional electrical stimulation (FES) is a neuroprosthetic technique for restoring lost motor function of spinal cord injured (SCI) patients and motor-impaired subjects by delivering short electrical pulses to their paralyzed muscles or motor nerves. FES induces action potentials respectively on muscles or nerves so that muscle activity can be characterized by the synchronous recruitment of motor units with its compound electromyography (EMG) signal is called M-wave. The recorded evoked EMG (eEMG) can be employed to predict the resultant joint torque, and modeling of FES-induced joint torque based on eEMG is an essential step to provide necessary prediction of the expected muscle response before achieving accurate joint torque control by FES.

Methods

Previous works on FES-induced torque tracking issues were mainly based on offline analysis. However, toward personalized clinical rehabilitation applications, real-time FES systems are essentially required considering the subject-specific muscle responses against electrical stimulation. This paper proposes a wireless portable stimulator used for estimating/predicting joint torque based on real time processing of eEMG. Kalman filter and recurrent neural network (RNN) are embedded into the real-time FES system for identification and estimation.

Results

Prediction results on 3 able-bodied subjects and 3 SCI patients demonstrate promising performances. As estimators, both Kalman filter and RNN approaches show clinically feasible results on estimation/prediction of joint torque with eEMG signals only, moreover RNN requires less computational requirement.

Conclusion

The proposed real-time FES system establishes a platform for estimating and assessing the mechanical output, the electromyographic recordings and associated models. It will contribute to open a new modality for personalized portable neuroprosthetic control toward consolidated personal healthcare for motor-impaired patients.

Tennis Elbow Diagnosis Using Equivalent Uniform Voltage to Fit the Logistic and the Probit Diseased Probability Models

To develop the logistic and the probit models to analyse electromyographic (EMG) equivalent uniform voltage- (EUV-) response for the tenderness of tennis elbow. In total, 78 hands from 39 subjects were enrolled. In this study, surface EMG (sEMG) signal is obtained by an innovative device with electrodes over forearm region. The analytical endpoint was defined as Visual Analog Score (VAS) 3+ tenderness of tennis elbow. The logistic and the probit diseased probability (DP) models were established for the VAS score and EMG absolute voltage-time histograms (AVTH). TV₅₀ is the threshold equivalent uniform voltage predicting a 50% risk of disease. Twenty-one out of 78 samples (27%) developed VAS 3+ tenderness of tennis elbow reported by the subject and confirmed by the physician. The fitted DP parameters were TV₅₀ = 153.0 mV (CI: 136.3–169.7 mV), γ₅₀ = 0.84 (CI: 0.78–0.90) and TV₅₀ = 155.6 mV (CI: 138.9–172.4 mV), m = 0.54 (CI: 0.49–0.59) for logistic and probit models, respectively. When the EUV ≥ 153 mV, the DP of the patient is greater than 50% and vice versa. The logistic and the probit models are valuable tools to predict the DP of VAS 3+ tenderness of tennis elbow.

Human joint motion estimation for electromyography (EMG)-based dynamic motion control

This study aims to investigate a joint motion estimation method from Electromyography (EMG) signals during dynamic movement. In most EMG-based humanoid or prosthetics control systems, EMG features were directly or indirectly used to trigger intended motions. However, both physiological and nonphysiological factors can influence EMG characteristics during dynamic movements, resulting in subject-specific, non-stationary and crosstalk problems. Particularly, when motion velocity and/or joint torque are not constrained, joint motion estimation from EMG signals are more challenging. In this paper, we propose a joint motion estimation method based on muscle activation recorded from a pair of agonist and antagonist muscles of the joint. A linear state-space model with multi input single output is proposed to map the muscle activity to joint motion. An adaptive estimation method is proposed to train the model. The estimation performance is evaluated in performing a single elbow flexion-extension movement in two subjects. All the results in two subjects at two load levels indicate the feasibility and suitability of the proposed method in joint motion estimation. The estimation root-mean-square error is within 8.3% ∼ 10.6%, which is lower than that being reported in several previous studies. Moreover, this method is able to overcome subject-specific problem and compensate non-stationary EMG properties.

Influence of Joint Angle on EMG-Torque Model During Constant-Posture, Torque-Varying Contractions

Relating the electromyogram (EMG) to joint torque is useful in various application areas, including prosthesis control, ergonomics and clinical biomechanics. Limited study has related EMG to torque across varied joint angles, particularly when subjects performed force-varying contractions or when optimized modeling methods were utilized. We related the biceps-triceps surface EMG of 22 subjects to elbow torque at six joint angles (spanning 60° to 135°) during constant-posture, torque-varying contractions. Three nonlinear EMG σ -torque models, advanced EMG amplitude (EMG σ ) estimation processors (i.e., whitened, multiple-channel) and the duration of data used to train models were investigated. When EMG-torque models were formed separately for each of the six distinct joint angles, a minimum "gold standard" error of 4.01±1.2% MVC(F90) resulted (i.e., error relative to maximum voluntary contraction at 90° flexion). This model structure, however, did not directly facilitate interpolation across angles. The best model which did so achieved a statistically equivalent error of 4.06±1.2% MVC(F90). Results demonstrated that advanced EMG σ processors lead to improved joint torque estimation as do longer model training durations.

The role of muscle synergies in myoelectric control: trends and challenges for simultaneous multifunction control

Myoelectric control is filled with potential to significantly change human-robot interaction due to the ability to non-invasively measure human motion intent. However, current control schemes have struggled to achieve the robust performance that is necessary for use in commercial applications. As demands in myoelectric control trend toward simultaneous multifunctional control, multi-muscle coordinations, or synergies, play larger roles in the success of the control scheme. Detecting and refining patterns in muscle activations robust to the high variance and transient changes associated with surface electromyography is essential for efficient, user-friendly control. This article reviews the role of muscle synergies in myoelectric control schemes by dissecting each component of the scheme with respect to associated challenges for achieving robust simultaneous control of myoelectric interfaces. Electromyography recording details, signal feature extraction, pattern recognition and motor learning based control schemes are considered, and future directions are proposed as steps toward fulfilling the potential of myoelectric control in clinically and commercially viable applications.

Using the electromyogram to anticipate torques about the elbow

Processed (i.e., rectified, smoothed) electromyogram (EMG) activity from skeletal muscles precedes mechanical tension by 50-100 ms. This property can be exploited to anticipate muscle mechanical activity. Thus, we investigated the ability of surface EMG to estimate joint torque at future times, up to 750 ms. EMG recorded from the biceps and triceps muscles of 54 subjects during constant-posture, force-varying contractions was related to elbow torque. Higher-order FIR models, combined with advanced EMG processing (whitening; four EMG channels per muscle), provided a nearly identical minimum error of 5.48 ±2.21% MVC(F) (flexion maximum voluntary contraction) over the time advance range of 0-60 ms. Error grew for larger time advances. The more common method of filtering EMG amplitude with a Butterworth filter (second-order, 1.5 Hz cutoff frequency) produced a statistically inferior minimum torque error of 6.90 ±2.39% MVC(F), with an error nadir at a time advance of 60 ms. Error was progressively poorer at all other time advances. Lower-order FIR models mimicked the poorer performance of the Butterworth models. The more advanced models provide lower estimation error, require no selection of an electromechanical delay term and maintain their lowest error over a substantial range of advance times.

Inverse estimation of muscle activations from joint torque via local multiple regression

The signal measured with an electromyogram (EMG) is the summation of all action potentials of motor units active at a certain time. According to previous literature, one can establish the relationship between torque and EMG/activations in a forward way, i.e., employing EMG of multiple channels to estimate the joint torque. Once the relationship is established, the torque can be predicted with EMG recordings. However, in some applications of neuroprosthetics where we need to make muscle control, it is required to inversely have an insight regarding the muscle activations under a specific motion scenario from the corresponding torque. Motivated by this point, this paper investigates inverse estimation of muscle activations in random contractions at the ankle joint. Local multiple regression is exploited for finding the relationship between muscle activations and torque. Such technique is able to rebuild the relationship between muscle activations and joint torque inversely based on experimental data obtained from five able-bodied subjects, and the resultant optimal weight matrix can indicate each muscle's contribution in the production of the torque. Further cross validation on prediction of muscle activations with joint torque with optimal weights shows that such approach may possess promising performance.

Electromyogram bandwidth requirements when the signal is whitened

Whitening the surface electromyogram (EMG) improves EMG amplitude (EMGσ) and EMG-torque estimation. Laboratory studies utilizing contraction levels up to maximum voluntary contraction (MVC) show that whitening is useful over a frequency band extending to 1000-2000 Hz. However, EMG electrode systems with such wide bandwidth are uncommon, particularly in real-time applications; and these contraction levels are also not common. Thus, we studied the influence of the frequency band over which whitening was performed versus the resulting performance. Low-level, torque-varying contractions (average torque level of 18.5% flexion MVC) of the elbow were contrasted with medium-level 50% MVC constant-torque contractions. For each, the maximum whitening bandwidth was varied between 30-2000 Hz. The low-level contractions (which incorporate the contraction range of most daily tasks) showed that performance utilizing frequencies out to 400-500 Hz was not statistically different than results out to the full available frequency (2000 Hz). For the medium-level (50% MVC) contractions, frequencies out to 800-900 Hz were statistically equivalent to the full bandwidth. These results suggest that conventional electrodes with a typical passband of ∼ 500 Hz are appropriate when whitening data from contraction levels typically experienced in many applications. Wider bandwidths may be advantageous for strenuous activities.

Influence of joint angle on EMG-torque model during constant-posture, quasi-constant-torque contractions

Electromyogram (EMG)-torque modeling is of value to many different application areas, including ergonomics, clinical biomechanics and prosthesis control. One important aspect of EMG-torque modeling is the ability to account for the joint angle influence. This manuscript describes an experimental study which relates the biceps/triceps surface EMG of 12 subjects to elbow torque at seven joint angles (spanning 45-135°) during constant-posture, quasi-constant-torque contractions. Advanced EMG amplitude (EMGσ) estimation processors (i.e., whitened, multiple-channel) were investigated and three non-linear EMGσ-torque models were evaluated. When EMG-torque models were formed separately for each of the seven distinct joint angles, a minimum "gold standard" error of 4.23±2.2% MVCF90 resulted (i.e., error relative to maximum voluntary contraction at 90° flexion). This model structure, however, did not directly facilitate interpolation across angles. The best model which did so (i.e., parameterized the angle dependence), achieved an error of 4.17±1.7% MVCF90. Results demonstrated that advanced EMGσ processors lead to improved joint torque estimation. We also contrasted models that did vs. did not account for antagonist muscle co-contraction. Models that accounted for co-contraction estimated individual flexion muscle torques that were ∼29% higher and individual extension muscle torques that were ∼68% higher.

Electromyogram whitening for improved classification accuracy in upper limb prosthesis control

Time and frequency domain features of the surface electromyogram (EMG) signal acquired from multiple channels have frequently been investigated for use in controlling upper-limb prostheses. A common control method is EMG-based motion classification. We propose the use of EMG signal whitening as a preprocessing step in EMG-based motion classification. Whitening decorrelates the EMG signal and has been shown to be advantageous in other EMG applications including EMG amplitude estimation and EMG-force processing. In a study of ten intact subjects and five amputees with up to 11 motion classes and ten electrode channels, we found that the coefficient of variation of time domain features (mean absolute value, average signal length and normalized zero crossing rate) was significantly reduced due to whitening. When using these features along with autoregressive power spectrum coefficients, whitening added approximately five percentage points to classification accuracy when small window lengths were considered.

Estimation of Upper Limb Joint Angle Using Surface EMG Signal

In the development of robot-assisted rehabilitation systems for upper limb rehabilitation therapy, human electromyogram (EMG) is widely used due to its ability to detect the user intended motion. EMG is one kind of biological signal that can be recorded to evaluate the performance of skeletal muscles by means of a sensor electrode. Based on recorded EMG signals, user intended motion could be extracted via estimation of joint torque, force or angle. Therefore, this estimation becomes one of the most important factors to achieve accurate user intended motion. In this paper, an upper limb joint angle estimation methodology is proposed. A back propagation neural network (BPNN) is developed to estimate the shoulder and elbow joint angles from the recorded EMG signals. A Virtual Human Model (VHM) is also developed and integrated with BPNN to perform the simulation of the estimated angle. The relationships between sEMG signals and upper limb movements are observed in this paper. The effectiveness of our developments is evaluated with four healthy subjects and a VHM simulation. The results show that the methodology can be used in the estimation of joint angles based on EMG.