Real-time pinch force estimation by surface electromyography using an artificial neural network

Online prediction of sustained muscle force from individual motor unit activities using adaptive surface EMG decomposition

Decoding movement intentions from motor unit (MU) activities to represent neural drive information plays a central role in establishing neural interfaces, but there remains a great challenge for obtaining precise MU activities during sustained muscle contractions. In this paper, we presented an online muscle force prediction method driven by individual MU activities that were decomposed from prolonged surface electromyogram (SEMG) signals in real time. In the training stage of the proposed method, a set of separation vectors was initialized for decomposing MU activities. After transferring each decomposed MU activity into a twitch force train according to its action potential waveform, a neural network was designed and trained for predicting muscle force. In the subsequent online stage, a practical double-thread-parallel algorithm was developed. One frontend thread predicted the muscle force in real time utilizing the trained network and the other backend thread simultaneously updated the separation vectors. To assess the performance of the proposed method, SEMG signals were recorded from the abductor pollicis brevis muscles of eight subjects and the contraction force was simultaneously collected. With the update procedure in the backend thread, the force prediction performance of the proposed method was significantly improved in terms of lower root mean square deviation (RMSD) of around 10% and higher fitness (R2) of around 0.90, outperforming two conventional methods. This study provides a promising technique for real-time myoelectric applications in movement control and health.

Estimation of Muscle Forces of Lower Limbs Based on CNN-LSTM Neural Network and Wearable Sensor System

Estimation of vivo muscle forces during human motion is important for understanding human motion control mechanisms and joint mechanics. This paper combined the advantages of the convolutional neural network (CNN) and long-short-term memory (LSTM) and proposed a novel muscle force estimation method based on CNN-LSTM. A wearable sensor system was also developed to collect the angles and angular velocities of the hip, knee, and ankle joints in the sagittal plane during walking, and the collected kinematic data were used as the input for the neural network model. In this paper, the muscle forces calculated using OpenSim based on the Static Optimization (SO) method were used as the standard value to train the neural network model. Four lower limb muscles of the left leg, including gluteus maximus (GM), rectus femoris (RF), gastrocnemius (GAST), and soleus (SOL), were selected as the studying objects in this paper. The experiment results showed that compared to the standard CNN and the standard LSTM, the CNN-LSTM performed better in muscle forces estimation under slow (1.2 m/s), medium (1.5 m/s), and fast walking speeds (1.8 m/s). The average correlation coefficients between true and estimated values of four muscle forces under slow, medium, and fast walking speeds were 0.9801, 0.9829, and 0.9809, respectively. The average correlation coefficients had smaller fluctuations under different walking speeds, which indicated that the model had good robustness. The external testing experiment showed that the CNN-LSTM also had good generalization. The model performed well when the estimated object was not included in the training sample. This article proposed a convenient method for estimating muscle forces, which could provide theoretical assistance for the quantitative analysis of human motion and muscle injury. The method has established the relationship between joint kinematic signals and muscle forces during walking based on a neural network model; compared to the SO method to calculate muscle forces in OpenSim, it is more convenient and efficient in clinical analysis or engineering applications.

Hand Posture and Force Estimation Using Surface Electromyography and an Artificial Neural Network

OBJECTIVE

The purpose of this study was to develop an approach to predict hand posture (pinch versus grip) and grasp force using forearm surface electromyography (sEMG) and artificial neural networks (ANNs) during tasks that varied repetition rate and duty cycle.

BACKGROUND

Prior studies have used electromyography with machine learning models to predict grip force but relatively few studies have assessed whether both hand posture and force can be predicted, particularly at varying levels of duty cycle and repetition rate.

METHOD

Fourteen individuals participated in this experiment. sEMG data for five forearm muscles and force output data were collected. Calibration data (25, 50, 75, 100% of maximum voluntary contraction (MVC)) were used to train ANN models to predict hand posture (pinch versus grip) and force magnitude while performing tasks that varied load, repetition rate, and duty cycle.

RESULTS

Across all participants, overall hand posture prediction accuracy was 79% (0.79 ± .08), whereas overall hand force prediction accuracy was 73% (0.73 ± .09). Accuracy ranged between 0.65 and 0.93 based on varying repetition rate and duty cycle.

CONCLUSION

Hand posture and force prediction were possible using sEMG and ANNs, though there were important differences in the accuracy of predictions based on task characteristics including duty cycle and repetition rate.

APPLICATION

The results of this study could be applied to the development of a dosimeter used for distal upper extremity biomechanical exposure measurement, risk assessment, job (re)design, and return to work programs.

A real-time and convex model for the estimation of muscle force from surface electromyographic signals in the upper and lower limbs

Surface electromyography (sEMG) is a signal consisting of different motor unit action potential trains and records from the surface of the muscles. One of the applications of sEMG is the estimation of muscle force. We proposed a new real-time convex and interpretable model for solving the sEMG-force estimation. We validated it on the upper limb during isometric voluntary flexions-extensions at 30%, 50%, and 70% Maximum Voluntary Contraction in five subjects, and lower limbs during standing tasks in thirty-three volunteers, without a history of neuromuscular disorders. Moreover, the performance of the proposed method was statistically compared with that of the state-of-the-art (13 methods, including linear-in-the-parameter models, Artificial Neural Networks and Supported Vector Machines, and non-linear models). The envelope of the sEMG signals was estimated, and the representative envelope of each muscle was used in our analysis. The convex form of an exponential EMG-force model was derived, and each muscle's coefficient was estimated using the Least Square method. The goodness-of-fit indices, the residual signal analysis (bias and Bland-Altman plot), and the running time analysis were provided. For the entire model, 30% of the data was used for estimation, while the remaining 20% and 50% were used for validation and testing, respectively. The average R-square (%) of the proposed method was 96.77 ± 1.67 [94.38, 98.06] for the test sets of the upper limb and 91.08 ± 6.84 [62.22, 96.62] for the lower-limb dataset (MEAN ± SD [min, max]). The proposed method was not significantly different from the recorded force signal (p-value = 0.610); that was not the case for the other tested models. The proposed method significantly outperformed the other methods (adj. p-value < 0.05). The average running time of each 250 ms signal of the training and testing of the proposed method was 25.7 ± 4.0 [22.3, 40.8] and 11.0 ± 2.9 [4.7, 17.8] in microseconds for the entire dataset. The proposed convex model is thus a promising method for estimating the force from the joints of the upper and lower limbs, with applications in load sharing, robotics, rehabilitation, and prosthesis control for the upper and lower limbs.

Effect of premodulated interferential current versus diadynamic current on the management of lateral elbow tendinopathy

Study aim: To compare the effect of premodulated interferential current (PREMOD IFC) and diadynamic current (DD) with exercise training on the management of lateral elbow tendinopathy (LET).

Material and methods: One hundred and four patients with unilateral LET from both genders (55 females and 49 males) were randomly allocated into two groups. Group A received PREMOD IFC in addition to the exercises, and group B received DD with the same exercises. The outcomes were maximum grip strength assessed by the hand dynamometer, the pinch strength assessed by the pinch gauge dynamometer, and pain and functional disability of the forearm assessed by a patient-rated tennis elbow evaluation (PRTEE) questionnaire. All participants received electrical stimulation, consisting of three sessions per week for six weeks.

Results: The mean PRTEE score, and grip strength were significantly improved after six weeks in favour of group A, while there was no significant difference between the two groups in pinch strength. (p < 0.05).

Conclusion: The results revealed that the combination of PREMOD IFC with exercises could improve pain, functional disability, and grip strength compared to DD with exercises in LET patients without a significant difference between the two groups in pinch strength.

Joint mechanical properties estimation with a novel EMG-based knee rehabilitation robot: A machine learning approach

Joint dynamic properties play essential roles in a wide range of biomechanical movement control. This paper develops a device with a novel mechatronic design to apply small-amplitude perturbations to the human knee. Surface Electromyography is employed to record such information; at the same time, force and position sensors collect measurements to be sent to identify human joint dynamics. For classification and estimation of force, support vector machine and support vector regression techniques are applied, respectively. We devise a genetic algorithm for parameter optimization and feature extraction within the proposed methods to improve the estimation accuracy. These are then analyzed and compared to the output of our estimation model to provide a reliable comparison. Our extensive experimental results reveal a high estimation accuracy for lower limb muscles to regulate robot impedance parameters. Although the identification method sounds similar to traditional ones, knee joint properties can be estimated by the machine learning approach from the surface Electromyography without perturbations.

Robust muscle force prediction using NMFSEMD denoising and FOS identification

In this paper, an aliasing noise restraint technique and a system identification-based surface electromyography (sEMG)-force prediction model are proposed to realize a type of robust sEMG and muscle force prediction. For signal denoising, a novel non-negative matrix factorization screening empirical mode decomposition (NMFSEMD) and a fast orthogonal search (FOS)-based muscle force prediction model are developed. First, the NMFSEMD model is used to screen the empirical mode decomposition (EMD) results into the noisy intrinsic mode functions (IMF). Then, the noise matrix is computed using IMF translation and superposition, and the matrix is used as the input of NMF to obtain the denoised IMF. Furthermore, the reconstruction outcome of the NMFSEMD method can be used to estimate the denoised sEMG. Finally, a new sEMG muscle force prediction model, which considers a kind of candidate function in derivative form, is constructed, and a data-training-based linear weighted model is obtained. Extensive experimental results validate the suggested method's correction: after the NMFSEMD denoising of raw sEMG signal, the signal-noise ratio (SNR) can be improved by about 15.0 dB, and the energy percentage (EP) can be greater than 90.0%. Comparing with the muscle force prediction models using the traditional pretreatment and LSSVM, and the NMFSEMD plus LSSVM-based method, the mean square error (MSE) of our approach can be reduced by at least 1.2%.

An EMG-Based Constitutive Law for Force Generation in Skeletal Muscle - Part I: Model Development

PURPOSE

This paper proposes a new method for estimating skeletal muscle forces using a model derived from dimensional analysis. It incorporates electromyography signals and muscle force-length, force-velocity, and force frequency relationships as inputs. The purpose of this model is to provide more accurate estimates of individualized muscle forces to better predict surrounding musculoskeletal tissue and joint contact loading.

THEORY

The derivation begins with dimensional analysis and a selection of critical parameters that define muscle force generation. The resulting constitutive equation gives way to a unique application of inverse-dynamics, one which avoids the issue of indeterminacy when reaction moments and ligament loading are minimized in a joint. The ankle joint is used as an example for developing the equations that culminate into a system of linear equations.

DISCUSSION

A muscle force model capable of being calibrated and then used to predict joint contact and surrounding tissue loading is critical in advancing biomechanics research areas like injury prevention, performance optimization, and tissue engineering, among others. This model's foundation in dimensional analysis, along with its inclusion of electromyography signals, gives promise that it will be physiologically relevant and suitable for application-based studies.

Effect of Muscle Fatigue on Surface Electromyography-Based Hand Grasp Force Estimation

Surface electromyography- (sEMG-) based hand grasp force estimation plays an important role with a promising accuracy in a laboratory environment, yet hardly clinically applicable because of physiological changes and other factors. One of the critical factors is the muscle fatigue concomitant with daily activities which degrades the accuracy and reliability of force estimation from sEMG signals. Conventional qualitative measurements of muscle fatigue contribute to an improved force estimation model with limited progress. This paper proposes an easy-to-implement method to evaluate the muscle fatigue quantitatively and demonstrates that the proposed metrics can have a substantial impact on improving the performance of hand grasp force estimation. Specifically, the reduction in the maximal capacity to generate force is used as the metric of muscle fatigue in combination with a back-propagation neural network (BPNN) is adopted to build a sEMG-hand grasp force estimation model. Experiments are conducted in the three cases: (1) pooling training data from all muscle fatigue states with time-domain feature only, (2) employing frequency domain feature for expression of muscle fatigue information based on case 1, and 3) incorporating the quantitative metric of muscle fatigue value as an additional input for estimation model based on case 1. The results show that the degree of muscle fatigue and task intensity can be easily distinguished, and the additional input of muscle fatigue in BPNN greatly improves the performance of hand grasp force estimation, which is reflected by the 6.3797% increase in R² (coefficient of determination) value.

Electromyogram in Cigarette Smoking Activity Recognition

In this study, information from surface electromyogram (sEMG) signals was used to recognize cigarette smoking. The sEMG signals collected from lower arm were used in two different ways: (1) as an individual predictor of smoking activity and (2) as an additional sensor/modality along with the inertial measurement unit (IMU) to augment recognition performance. A convolutional and a recurrent neural network were utilized to recognize smoking-related hand gestures. The model was developed and evaluated with leave-one-subject-out (LOSO) cross-validation on a dataset from 16 subjects who performed ten activities of daily living including smoking. The results show that smoking detection using only sEMG signal achieved an F1-score of 75% in person-independent cross-validation. The combination of sEMG and IMU improved reached the F1-score of 84%, while IMU alone sensor modality was 81%. The study showed that using only sEMG signals would not provide superior cigarette smoking detection performance relative to IMU signals. However, sEMG improved smoking detection results when combined with IMU signals without using an additional device.

Upper Limb End-Effector Force Estimation During Multi-Muscle Isometric Contraction Tasks Using HD-sEMG and Deep Belief Network

In this study, research was carried out on the end-effector force estimation of two representative multi-muscle contraction tasks: elbow flexion and palm-pressing. The aim was to ascertain whether an individual muscle or a combination of muscles is more suitable for the end-effector force estimation. High-density surface electromyography (HD-sEMG) signals were collected from four primary muscle areas of the upper arm and forearm: the biceps brachii (BB), brachialis (BR), triceps brachii (TB), brachioradialis (BRD), and extensor digitorum communis (EDC). The wrist pulling and palm-pressing forces were measured in elbow flexion and palm-pressing tasks, respectively. The deep belief network (DBN) was adopted to establish the relation between HD-sEMG and the measured force. The representative signals of the four primary areas, which were considered as the input signal of the force estimation model, were extracted by HD-sEMG using the principle component analysis (PCA) algorithm, and fed separately or together into the DBN. An index termed mean impact value (MIV) was proposed to describe the priority of different muscle groups for estimating the end-effector force. The experimental results demonstrated that, in multi-muscle isometric contraction tasks, the dominant muscles with the highest activation degree could track variations in the end-effector force more effectively, and are more suitable than a combination of muscles. The main contributions of this research are as follows: (1) To fuse the activation information from different muscles effectively, DBN was adopted to establish the relationship between HD-sEMG and the generated force, and achieved highly accurate force estimation. (2) Based on the well-trained DBN force estimation model, an index termed MIV was presented to evaluate the priority of muscles for estimating the generated force.

Logistic regression analysis of multiple interosseous hand-muscle activities using surface electromyography during finger-oriented tasks

Intrinsic hand muscles are densely located in the hand, and the myoelectric observation from the surface is sometimes unreliable because of some outside influences that may interfere with the signals. In the present study, we evaluated the activities of multiple interosseous hand-muscles which densely located in the hand, through analyzing the surface electromyographic signals during finger-oriented tasks using univariate and multivariate logistic regression models. Ten healthy subjects participated in our experiment, and isometrically exercised each finger one by one in flexed form. The result of a univariate analysis with the power and amplitude domain predictor variables of the surface electromyographic signals showed significant consistency between the activated finger and the inserted finger of the dorsal interosseous muscles to the proximal phalanx (P < 0.001). Meanwhile, the results of a multivariate analysis showed a higher correlation of the regression model of the fourth dorsal interosseous muscle during the action of the ring finger using frequency-domain variables (the Nagelkerke R² = 0.716 when the median frequency was used), compared to the model without the frequency-domain variables (the Nagelkerke R² = 0.583). Our result showed that the logistic regression models have a particular possibility for the analysis of the surface electromyographic signals of densely located hand-muscle activities related to the finger-oriented tasks.

Feasibility Study of Advanced Neural Networks Applied to sEMG-Based Force Estimation

To find out the feasibility of different neural networks in sEMG-based force estimation, in this paper, three types of networks, namely convolutional neural network (CNN), long short-term memory (LSTM) network and their combination (C-LSTM) were applied to predict muscle force generated in static isometric elbow flexion across three different circumstances (multi-subject, subject-dependent and subject-independent). Eight healthy men were recruited for the experiments, and the results demonstrated that all the three models were applicable for force estimation, and LSTM and C-LSTM achieved better performances. Even under subject-independent situation, they maintained mean RMSE% of as low as 9.07 ± 1.29 and 8.67 ± 1.14. CNN turned out to be a worse choice, yielding a mean RMSE% of 12.13 ± 1.98. To our knowledge, this work was the first to employ CNN, LSTM and C-LSTM in sEMG-based force estimation, and the results not only prove the strength of the proposed networks, but also pointed out a potential way of achieving high accuracy in real-time, subject-independent force estimation.

External biomechanical constraints impair maximal voluntary grip force stability post-stroke

BACKGROUND

Grip strength is frequently measured as a global indicator of motor function. In clinical populations, such as hemiparesis post-stroke, grip strength is associated with upper-extremity motor impairment, function, and ability to execute activities of daily living. However, biomechanical configuration of the distal arm and hand may influence the magnitude and stability of maximal voluntary grip force and varies across studies. The influence of distal arm/hand biomechanical configuration on grip force remains unclear. Here we investigated how biomechanical configuration of the distal arm/hand influence the magnitude and trial-to-trial variability of maximal grip force performed in similar positions with variations in external constraint.

METHODS

We studied three groups of 20 individuals: healthy young, healthy older, and individuals post-stroke. We tested maximal voluntary grip force in 4 conditions: 1: self-determined/"free"; 2: standard; 3: fixed arm-rest; 4: gripper fixed to arm-rest, using an instrumented grip dynamometer in both dominant/non-dominant and non-paretic/paretic hands.

FINDINGS

Regardless of hand or group, maximal voluntary grip force was highest when the distal limb was most constrained (i.e., Condition 4), followed by the least constrained (i.e., Condition 1) (Cohen's f = 0.52, P's < 0.001). Coefficient of variation among three trials was greater in the paretic hand compared with healthy individuals, particularly in more (Conditions 3 and 4) compared to less (Conditions 1 and 2) constrained conditions (Cohen's f = 0.29, P's < 0.05).

INTERPRETATION

These findings have important implications for design of rehabilitation interventions and devices. Particularly in individuals post-stroke, external biomechanical constraints increase maximal voluntary grip force variability while fewer biomechanical constraints yield more stable performance.

Hand Rehabilitation Robotics on Poststroke Motor Recovery

The recovery of hand function is one of the most challenging topics in stroke rehabilitation. Although the robot-assisted therapy has got some good results in the latest decades, the development of hand rehabilitation robotics is left behind. Existing reviews of hand rehabilitation robotics focus either on the mechanical design on designers' view or on the training paradigms on the clinicians' view, while these two parts are interconnected and both important for designers and clinicians. In this review, we explore the current literature surrounding hand rehabilitation robots, to help designers make better choices among varied components and thus promoting the application of hand rehabilitation robots. An overview of hand rehabilitation robotics is provided in this paper firstly, to give a general view of the relationship between subjects, rehabilitation theories, hand rehabilitation robots, and its evaluation. Secondly, the state of the art hand rehabilitation robotics is introduced in detail according to the classification of the hardware system and the training paradigm. As a result, the discussion gives available arguments behind the classification and comprehensive overview of hand rehabilitation robotics.

Dynamic Elbow Flexion Force Estimation Through a Muscle Twitch Model and sEMG in a Fatigue Condition

We propose a joint force estimation method to compute elbow flexion force using surface electromyogram (sEMG) considering time-varying effects in a fatigue condition. Muscle fatigue is a major cause inducing sEMG changes with respect to time over long periods and repetitive contractions. The proposed method composed the muscle-twitch model representing the force generated by a single spike and the spikes extracted from sEMG. In this study, isometric contractions at six different joint angles (10 subjects) and dynamic contractions with constant velocity (six subjects) were performed under non-fatigue and fatigue conditions. Performance of the proposed method was evaluated and compared with that of previous methods using mean absolute value (MAV). The proposed method achieved average 6.7 ± 2.8 %RMSE for isometric contraction and 15.6 ± 24.7%RMSE for isokinetic contraction under fatigue condition with more accurate results than the previous methods.

An attempt to bridge muscle architecture dynamics and its instantaneous rate of force development using ultrasonography

Muscle force output is an essential index in rehabilitation assessment or physical exams, and could provide considerable insights for various applications such as load monitoring and muscle assessment in sports science or rehabilitation therapy. Besides direct measurement of force output using a dynamometer, electromyography has earlier been used in several studies to quantify muscle force as an indirect means. However, its spatial resolution is easily compromised as a summation of the action potentials from neighboring motor units of electrode site. To explore an alternative method to indirectly estimate the muscle force output, and with better muscle specificity, we started with an investigation on the relationship between architecture dynamics and force output of triceps surae. The muscular architecture dynamics is captured in ultrasonography sequences and estimated using a previously reported motion estimation method. Then an indicator named as the dorsoventrally averaged motion profile (DAMP) is employed. The performance of force output is represented by an instantaneous version of the rate of force development (RFD), namely I-RFD. From experimental results on ten normal subjects, there were significant correlations between the I-RFD and DAMP for triceps surae, both normalized between 0 and 1, with the sum of squares error at 0.0516±0.0224, R-square at 0.7929±0.0931 and root mean squared error at 0.0159±0.0033. The statistical significance results were less than 0.01. The present study suggested that muscle architecture dynamics extracted from ultrasonography during contraction is well correlated to the I-RFD and it can be a promising option for indirect estimation of muscle force output.

Joint force estimation using time-varying SEMG feature in fatiguing contraction

Many studies have estimated joint force using surface electromyography (SEMG), however, the time-variant characteristic of SEMG is not considered. The change of SEMG amplitude is one of manifestations of muscle fatigue. This study proposes a force estimation method using SEMG in fatiguing contraction. The SEMG amplitude is used to determine the signal states by k-means clustering method. According to the signal state changes, the corresponding gain is used to estimate the force. The target contraction is an isometric abduction of an index finger in static and dynamic force conditions for 5 healthy subjects. The estimation performance was evaluated by percentage of root mean squared error (RMSE). The RMSE for the proposed method is 2.5 ± 1.0% under static condition and 8.8 ± 1.2% under dynamic condition. The accuracy using a constant gain calculated at initial time was used to compare with the proposed method. The RMSE are 8.9 ± 2.2% under static condition and 10.1 ± 2.4% under dynamic condition. The proposed method had better performance in both conditions.

The effect of two different hand exercises on grip strength, forearm circumference, and vascular maturation in patients who underwent arteriovenous fistula surgery

Objective

To compare the effect of two different hand exercises on hand strength and vascular maturation in patients who underwent arteriovenous fistula surgery.

Methods

We recruited 18 patients who had chronic kidney disease and had undergone arteriovenous fistula surgery for hemodialysis. After the surgery, 10 subjects performed hand-squeezing exercise with GD Grip, and other 8 subjects used Soft Ball. The subjects continued the exercises for 4 weeks. The hand grip strength, pinch strength (tip, palmar and lateral pinch), and forearm circumference of the subjects were assessed before and after the hand-squeezing exercise. The cephalic vein size, blood flow velocity and volume were also measured by ultrasonography in the operated limb.

Results

All of the 3 types of pinch strengths, grip strength, and forearm circumference were significantly increased in the group using GD Grip. Cephalic vein size and blood flow volume were also significantly increased. However, blood flow velocity showed no difference after the exercise. The group using Soft Ball showed a significant increase in the tip and lateral pinch strength and forearm circumference. The cephalic vein size and blood flow volume were also significantly increased. On comparing the effect of the two different hand exercises, hand-squeezing exercise with GD Grip had a significantly better effect on the tip and palmar pinch strength than hand-squeezing exercise with Soft Ball. The effect on cephalic vein size was not significantly different between the two groups.

Conclusion

The results showed that hand squeezing exercise with GD Grip was more effective in increasing the tip and palmar pinch strength compared to hand squeezing exercise with soft ball.

The effect of high pass filtering and non-linear normalization on the EMG-force relationship during sub-maximal finger exertions

Muscle force estimates are important for full understanding of the musculoskeletal system and EMG is a modeling method used to estimate muscle force. The purpose of this investigation was to examine the effect of high pass filtering and non-linear normalization on the EMG-force relationship of sub-maximal finger exertions. Sub-maximal isometric ramp exertions were performed under three conditions (i) extension with restraint at the mid-proximal phalanx, (ii) flexion at the proximal phalanx and (iii) flexion at the distal phalanx. Thirty high pass filter designs were compared to a standardized processing procedure and an exponential fit equation was used for non-linear normalization. High pass filtering significantly reduced the %RMS error and increased the peak cross correlation between EMG and force in the distal flexion condition and in the other two conditions there was a trend towards improving force predictions with high pass filtering. The degree of linearity differed between the three contraction conditions and high pass filtering improved the linearity in all conditions. Non-linear normalization had greater impact on the EMG-force relationship than high pass filtering. The difference in optimal processing parameters suggests that high pass filtering and linearity are dependent on contraction mode as well as the muscle analyzed.

Muscle force estimation with surface EMG during dynamic muscle contractions: a wavelet and ANN based approach

Human muscle force estimation is important in biomechanics studies, sports and assistive devices fields. Therefore, it is essential to develop an efficient algorithm to estimate force exerted by muscles. The purpose of this study is to predict force/torque exerted by muscles under dynamic muscle contractions based on continuous wavelet transform (CWT) and artificial neural networks (ANN) approaches. Mean frequency (MF) of the surface electromyography (EMG) signals power spectrum was calculated from CWT. ANN models were trained to derive the MF-force relationships from the subset of EMG signals and the measured forces. Then we use the networks to predict the individual muscle forces for different muscle groups. Fourteen healthy subjects (10 males and 4 females) were voluntarily recruited in this study. EMG signals were collected from the biceps brachii, triceps, hamstring and quadriceps femoris muscles to evaluate the proposed method. Root mean square errors (RMSE) and correlation coefficients between the predicted forces and measured actual forces were calculated.

Neuro-Based Thumb-Tip Force and Joint Angle Modelling for Development of Prosthetic Thumb Control

Human fingers have a specific role that contributes to different hand functions. Among these fingers, the thumb plays the most special function as an anchor to many hand activities. As a result, the loss of the thumb due to traumatic accidents can be catastrophic as proper hand function will be severely limited. In order to solve this problem, a prosthetic thumb is developed to be worn in complementing the function of the rest of the fingers. The movement of the prosthetic device can be naturally controlled by using electromyogram (EMG) signals. In this work, the EMG signals from the human muscles were measured in different thumb configurations and thumb-tip forces in flexion movement. The muscles involved are the Adductor Pollicis (AP), Flexor Pollicis Brevis (FPB), Abductor Pollicis Brevis (APB) and First Dorsal Interosseous (FDI). The classification of the EMG signals based on different force and thumb configurations is performed using an Artificial Neural Network (ANN). From a series of experiments, the results show that the neural network efficiently classified the signals and a unique set of EMG signals was generated for each thumb movement and force. Therefore, EMG signals were used to control the prosthetic movement with aid from the developed neural network.

EMG and EPP-integrated human-machine interface between the paralyzed and rehabilitation exoskeleton

Although a lower extremity exoskeleton shows great prospect in the rehabilitation of the lower limb, it has not yet been widely applied to the clinical rehabilitation of the paralyzed. This is partly caused by insufficient information interactions between the paralyzed and existing exoskeleton that cannot meet the requirements of harmonious control. In this research, a bidirectional human-machine interface including a neurofuzzy controller and an extended physiological proprioception (EPP) feedback system is developed by imitating the biological closed-loop control system of human body. The neurofuzzy controller is built to decode human motion in advance by the fusion of the fuzzy electromyographic signals reflecting human motion intention and the precise proprioception providing joint angular feedback information. It transmits control information from human to exoskeleton, while the EPP feedback system based on haptic stimuli transmits motion information of the exoskeleton back to the human. Joint angle and torque information are transmitted in the form of air pressure to the human body. The real-time bidirectional human-machine interface can help a patient with lower limb paralysis to control the exoskeleton with his/her healthy side and simultaneously perceive motion on the paralyzed side by EPP. The interface rebuilds a closed-loop motion control system for paralyzed patients and realizes harmonious control of the human-machine system.

A physiologically and biomechanically approximate model for surface electromyography amplitude estimation

Surface electromygraphy (sEMG) provides information of the neural drive to the muscle, so muscle force estimation by sEMG is of high relevance in biomechanical studies and in bionic applications. Even though mean absolute value (MAV) has been widely used for sEMG amplitude estimation due to the probabilistic nature of sEMG, but it has been used without any comprehensive physiological justification. A physiologically and biomechanically approximate model for the force estimation would enable a clear understanding of the relationships between sEMG and the force, and it can be used as sEMG amplitude estimation method. We proposed a new sEMG amplitude estimation method comprising two procedures: MUAP (motor unit action potential) event detection and muscle force indication using a biomechanical muscle model. The estimation performances were evaluated with nine subjects and compared with MAV. The performance (R(2)) of the proposed method (0.94 ± 0.03) outperformed it of MAV (0.90 ± 0.02). The method we proposed should be widely applicable to quantitatively analysis muscle activities by sEMG.