The Influence of Training With Visual Biofeedback on the Predictability of Myoelectric Control Usability.

Studies have shown that closed-loop myoelectric control schemes can lead to changes in user performance and behavior compared to open-loop systems. When users are placed within the control loop, such as during real-time use, they must correct for errors made by the controller and learn what behavior is necessary to produce desired outcomes. Augmented feedback, consequently, has been used to incorporate the user throughout the training process and to facilitate learning. This work explores the effect of visual feedback presented during user training on both the performance and predictability of a myoelectric classification-based control system. Our results suggest that properly designed feedback mechanisms and training tasks can influence the quality of the training data and the ability to predict usability using linear combinations of metrics derived from feature space. Furthermore, our results confirm that the most common in-lab training protocol, screen guided training, may yield training data that are less representative of online use than training protocols that incorporate the user in the loop. These results suggest that training protocols should be designed that better parallel the testing environment to more effectively prepare both the algorithms and users for real-time control.

A Multi-Variate Approach to Predicting Myoelectric Control Usability.

Pattern recognition techniques leveraging the use of electromyography signals have become a popular approach to provide intuitive control of myoelectric devices. Performance of these control interfaces is commonly quantified using offline classification accuracy, despite studies having shown that this metric is a poor indicator of usability. Researchers have identified alternative offline metrics that better correlate with online performance; however, the relationship has yet to be fully defined in the literature. This has necessitated the continued trial-and-error-style online testing of algorithms developed using offline approaches. To bridge this information divide, we conducted an exploratory study where thirty-two different metrics from the offline training data were extracted. A correlation analysis and an ordinary least squares regression were implemented to investigate the relationship between the offline metrics and six aspects online use. The results indicate that the current offline standard, classification accuracy, is a poor indicator of usability and that other metrics may hold predictive power. The metrics identified in this work also may constitute more representative evaluation criteria when designing and reporting new control schemes. Furthermore, linear combinations of offline training metrics generate substantially more accurate predictions than using individual metrics. We found that the offline metric feature efficiency generated the best predictions for the usability metric throughput. A combination of two offline metrics (mean semi-principal axes and mean absolute value) significantly outperformed feature efficiency alone, with a 166% increase in the predicted R2 value (i.e., VEcv). These findings suggest that combinations of metrics could provide a more robust framework for predicting usability.

An analytical method reduces noise bias in motor adaptation analysis.

When a person makes a movement, a motor error is typically observed that then drives motor planning corrections on subsequent movements. This error correction, quantified as a trial-by-trial adaptation rate, provides insight into how the nervous system is operating, particularly regarding how much confidence a person places in different sources of information such as sensory feedback or motor command reproducibility. Traditional analysis has required carefully controlled laboratory conditions such as the application of perturbations or error clamping, limiting the usefulness of motor analysis in clinical and everyday environments. Here we focus on error adaptation during unperturbed and naturalistic movements. With increasing motor noise, we show that the conventional estimation of trial-by-trial adaptation increases, a counterintuitive finding that is the consequence of systematic bias in the estimate due to noise masking the learner's intention. We present an analytic solution relying on stochastic signal processing to reduce this effect of noise, producing an estimate of motor adaptation with reduced bias. The result is an improved estimate of trial-by-trial adaptation in a human learner compared to conventional methods. We demonstrate the effectiveness of the new method in analyzing simulated and empirical movement data under different noise conditions.

Optimized control mapping through user-tuned cost of effort, time, and reliability.

Humans consistently coordinate their joints to perform a variety of tasks. Computational motor control theory explains these stereotypical behaviors using optimal control. Several cost functions have been used to explain specific movements, which suggests that the brain optimizes for a combination of costs and just varies their relative weights to perform different tasks. In the case of tunable human-machine interfaces, we hypothesize that the human-machine interface should be optimized according to the costs that the user cares about when making the movement. Here, we study how the relative weights of individual cost functions in a composite movement cost affect the optimal control signal produced by the user and the mapping between the user's control signals and the machine's output, using prosthesis control as a specific example. This framework was tested by building a hierarchical optimization model that independently optimized for the user control signal and the virtual dynamics of the device. Our results indicate the feasibility of the approach and show the potential for using such a model in prosthesis tuning. This method could be used to allow clinicians and users to tune their prosthesis based on costs they actually care about; and allow the platforms to be customized for the unique needs of every patient.

Effects of Confidence-Based Rejection on Usability and Error in Pattern Recognition-Based Myoelectric Control.

Rejection of movements based on the confidence in the classification decision has previously been demonstrated to improve the usability of pattern recognition based myoelectric control. To this point, however, the optimal rejection threshold has been determined heuristically, and it is not known how different thresholds affect the tradeoff between error mitigation and false rejections in real-time closed-loop control. To answer this question, 24 able-bodied subjects completed a real-time Fitts' law-style virtual cursor control task using a support vector machine classifier. It was found that rejection improved information throughput at all thresholds, with the best performance coming at thresholds between 0.60 and 0.75. Two fundamental types of error were defined and identified: operator error (identifiable, repeatable behaviors, directly attributable to the user), and systemic error (other errors attributable to misclassification or noise). The incidence of both operator and systemic errors were found to decrease as rejection threshold increased. Moreover, while the incidence of all error types correlated strongly with path efficiency, only systemic errors correlated strongly with throughput and trial completion rate. Interestingly, more experienced users were found to commit as many errors as novice users, despite performing better in the Fitts' task, suggesting that there is more to usability than error prevention alone. Nevertheless, these results demonstrate the usability gains possible with rejection across a range of thresholds for both novice and experienced users alike.

Rejection of Systemic and Operator Errors in a Real-Time Myoelectric Control Task.

In myoelectric pattern-recognition control, the rejection of movement decisions based on confidence - the likelihood of a correct classification - has been shown to improve system usability, however it is not known to what extent this is due directly to error mitigation, and to what extent this is due to users having opportunities to change the way they contract. To understand this, 24 subjects participated in a real-time pattern recognition control task with rejection at seven different confidence thresholds, and without rejection. Errors were classified into systemic errors (i.e., those produced by the classifier) and operator errors (i.e., those produced by user behavior). It was found that the error permitted by the rejection controller was reduced by about half at high rejection thresholds, with both systemic and operator errors significantly affected, while the errors produced by the user remained essentially constant throughout. Conversely, correct decisions were filtered out by the rejection controller at significantly greater rates at high rejection thresholds, which may be excessive enough to ultimately impair usability. While some subjects reported being experienced in myoelectric control, no significant differences were observed due to experience level.

A proportional control scheme for high density force myography.

OBJECTIVE: Force myography (FMG) has been shown to be a potentially higher accuracy alternative to electromyography for pattern recognition based prosthetic control. Classification accuracy, however, is just one factor that affects the usability of a control system. Others, like the ability to start and stop, to coordinate dynamic movements, and to control the velocity of the device through some proportional control scheme can be of equal importance. To impart effective fine control using FMG-based pattern recognition, it is important that a method of controlling the velocity of each motion be developed. METHODS: In this work force myography data were collected from 14 able bodied participants and one amputee participant as they performed a set of wrist and hand motions. The offline proportional control performance of a standard mean signal amplitude approach and a proposed regression-based alternative was compared. The impact of providing feedback during training, as well as the use of constrained or unconstrained hand and wrist contractions, were also evaluated. RESULTS: It is shown that the commonly used mean of rectified channel amplitudes approach commonly employed with electromyography does not translate to force myography. The proposed class-based regression proportional control approach is shown significantly outperform this standard approach (ρ < 0.001), yielding a R2 correlation coefficients of 0.837 and 0.830 for constrained and unconstrained forearm contractions, respectively for able bodied participants. No significant difference (ρ = 0.693) was found in R2 performance when feedback was provided during training or not. The amputee subject achieved a classification accuracy of 83.4% ± 3.47% demonstrating the ability to distinguish contractions well with FMG. In proportional control the amputee participant achieved an R2 of of 0.375 for regression based proportional control during unconstrained contractions. This is lower than the unconstrained case for able-bodied subjects for this particular amputee, possibly due to difficultly in visualizing contraction level modulation without feedback. This may be remedied in the use of a prosthetic limb that would provide real-time feedback in the form of device speed. CONCLUSION: A novel class-specific regression-based approach is proposed for multi-class control is described and shown to provide an effective means of providing FMG-based proportional control.

The effects of control signal noise on simultaneous submovements.

Understanding the stereotypical characteristics of human movement can better inform rehabilitation practices by providing a template of healthy and expected human motor control. Multiplicative noise is inherent in goal-directed movement, such as reaching to grasp an object. Multiplicative noise plays an important role in computational motor control models to help support phenomena such as stereotypical kinematic profiles in time-constrained and unconstrained tasks. Most tasks are not carried out along an isolated degree-of-freedom (DOF), and modelling the contribution of noise can be difficult. Here we add a noise term proportional to the degree of simultaneity for multi-DOF tasks to approximate the contribution of system noise. With this approach, we are able to explain previously observed motor phenomena including the presence of submovements in multi-DOF tasks, and the transition from simultaneous to sequential control of joints without the presence of feedback. Inclusion of a simultaneous multiplicative noise term presents a simple theory that expands on previous research in order to describe characteristics of multiple-DOF movements. This model can be used as a guide to compare healthy human motor control to the movements of patients receiving rehabilitation in an effort to improve their motor planning.

On the usability of intramuscular EMG for prosthetic control: a Fitts' Law approach.

Previous studies on intramuscular EMG based control used offline data analysis. The current study investigates the usability of intramuscular EMG in two degree-of-freedom using a Fitts' Law approach by combining classification and proportional control to perform a task, with real time feedback of user performance. Nine able-bodied subjects participated in the study. Intramuscular and surface EMG signals were recorded concurrently from the right forearm. Five performance metrics (Throughput,Path efficiency, Average Speed, Overshoot and Completion Rate) were used for quantification of usability. Intramuscular EMG based control performed significantly better than surface EMG for Path Efficiency (80.5±2.4% vs. 71.5±3.8%, P=0.004) and Overshoot (22.0±3.0% vs. 45.1±6.6%, P=0.01). No difference was found between Throughput and Completion Rate. However the Average Speed was significantly higher for surface (51.8±5.5%) than for intramuscular EMG (35.7±2.7%). The results obtained in this study imply that intramuscular EMG has great potential as control source for advanced myoelectric prosthetic devices.

Support vector regression for improved real-time, simultaneous myoelectric control.

This study describes the first application of a support vector machine (SVM) based scheme for real-time simultaneous and proportional myoelectric control of multiple degrees of freedom (DOFs). Three DOFs including wrist flexion-extension, abduction-adduction and forearm pronation-supination were investigated with 10 able-bodied subjects and two individuals with transradial limb deficiency (LD). A Fitts' law test involving real-time target acquisition tasks was conducted to compare the usability of the SVM-based control system to that of an artificial neural network (ANN) based method. Performance was assessed using the Fitts' law throughput value as well as additional metrics including completion rate, path efficiency and overshoot. The SVM-based approach outperformed the ANN-based system in every performance measure for able-bodied subjects. The SVM outperformed the ANN in path efficiency and throughput with the first LD subject and in throughput with the second LD subject. The superior performance of the SVM-based system appears to be due to its higher estimation accuracy of all DOFs during inactive and low amplitude segments (these periods were frequent during real-time control). Another advantage of the SVM-based method was that it substantially reduced the processing time for both training and real time control.

Real-time, simultaneous myoelectric control using force and position-based training paradigms.

In this paper, the simultaneous real-time control of multiple degrees of freedom (DOF) for myoelectric systems is investigated. The goal of this study, in which ten able-bodied subjects participated, was to directly compare three control paradigms of constrained (force targeted), unconstrained (position targeted) and resisted unconstrained (position targeted) limb contractions. Artificial neural networks (ANNs) were trained for simultaneous myoelectric control of the three degrees of freedom (DOFs) (wrist flexion-extension, abduction-adduction, and pronation-supination) using mirrored bilateral contractions. In the resisted unconstrained experiment, some resistance to movement was provided using flexible wrist braces in order to increase the required level of muscle activation. The force, in constrained experiments, and position, in unconstrained and resisted unconstrained experiments, were measured. The three protocols were compared off-line using estimation accuracies (R2) and online using a real-time computer-based target acquisition test. The constrained control paradigm outperformed the unconstrained method in the abduction-adduction DOF (R(constrained)2 = 90.8 ± 0.6, R(unconstrained)2 = 85.6 ± 1.6) and pronation-supination DOF (R(constrained)2 = 88.5 ± 0.9, R(unconstrained)2 = 82.3 ± 1.6), but no significant difference was found in the flexion-extension DOF. The constrained control method outperformed unconstrained control in two real-time testing metrics including completion time and path efficiency. The constrained method results, however, were not significantly different than those of the resisted unconstrained method (with braces) in both off-line and real-time tests. This suggests that the quality of control using constrained and unconstrained contraction-based myoelectric schemes is not appreciably different when using comparable l- vels of muscle activation.

Surface versus untargeted intramuscular EMG based classification of simultaneous and dynamically changing movements.

The pattern recognition-based myoelectric control scheme is in the process of being implemented in clinical settings, but it has been mainly tested on sequential and steady state data. This paper investigates the ability of pattern recognition to resolve movements that are simultaneous and dynamically changing and compares the use of surface and untargeted intramuscular EMG signals for this purpose. Ten able-bodied subjects participated in the study. Both EMG types were recorded concurrently from the right forearm. The subjects were instructed to track dynamic contraction profiles using single and combined degrees of freedom in three trials. During trials one and two, the amplitude and the frequency of the profile were kept constant (nonmodulated data), and during trial three, the two parameters were modulated (modulated data). The results showed that the performance was up to 93% for nonmodulated tasks, but highly depended on the nature of the data used. Surface and untargeted intramuscular EMG had equal performance for data of similar nature (nonmodulated), but the performance of intramuscular EMG decreased, compared to surface, when tested on modulated data. However, the results of intramuscular recordings obtained in this study are promising for future use of implantable electrodes, because, besides the value added in terms of potential chronic implantation, the performance is theoretically the same as for surface EMG provided that enough information is captured in the recordings. Nevertheless, care should be taken when training the system since data obtained from selective recordings probably need more training data to generalize to new signals.

Wrist torque estimation during simultaneous and continuously changing movements: surface vs. untargeted intramuscular EMG.

In this paper, the predictive capability of surface and untargeted intramuscular electromyography (EMG) was compared with respect to wrist-joint torque to quantify which type of measurement better represents joint torque during multiple degrees-of-freedom (DoF) movements for possible application in prosthetic control. Ten able-bodied subjects participated in the study. Surface and intramuscular EMG was recorded concurrently from the right forearm. The subjects were instructed to track continuous contraction profiles using single and combined DoF in two trials. The association between torque and EMG was assessed using an artificial neural network. Results showed a significant difference between the two types of EMG (P < 0.007) for all performance metrics: coefficient of determination (R(2)), Pearson correlation coefficient (PCC), and root mean square error (RMSE). The performance of surface EMG (R(2) = 0.93 ± 0.03; PCC = 0.98 ± 0.01; RMSE = 8.7 ± 2.1%) was found to be superior compared with intramuscular EMG (R(2) = 0.80 ± 0.07; PCC = 0.93 ± 0.03; RMSE = 14.5 ± 2.9%). The higher values of PCC compared with R(2) indicate that both methods are able to track the torque profile well but have some trouble (particularly intramuscular EMG) in estimating the exact amplitude. The possible cause for the difference, thus the low performance of intramuscular EMG, may be attributed to the very high selectivity of the recordings used in this study.

Confidence-based rejection for improved pattern recognition myoelectric control.

This study describes a novel myoelectric control scheme that is capable of motion rejection. As an extension of the commonly used linear discriminant analysis (LDA), this system generates a confidence score for each decision, providing the ability to reject those with a score below a selected threshold. The thresholds are class-specific and affect only the rejection characteristics of the associated class. Furthermore, because the rejection stage is implemented using the outputs of the LDA, the active motion classification accuracy of the proposed system is shown to outperform that of the LDA for all values of rejection threshold. The proposed scheme was compared to a baseline LDA-based pattern recognition system using a real-time Fitts' law-based target acquisition task. The use of velocity-based myoelectric control using the rejection classifier is shown to obey Fitts' law, producing linear regression fittings with high coefficients of determination (R(2) > 0.943). Significantly higher (p < 0.001) throughput, path efficiency, and completion rates were observed with the rejection-capable system for both able-bodied and amputee subjects.

Validation of a selective ensemble-based classification scheme for myoelectric control using a three-dimensional Fitts' Law test.

When controlling a powered upper limb prosthesis it is important not only to know how to move the device, but also when not to move. A novel approach to pattern recognition control, using a selective multiclass one-versus-one classification scheme has been shown to be capable of rejecting unintended motions. This method was shown to outperform other popular classification schemes when presented with muscle contractions that did not correspond to desired actions. In this work, a 3-D Fitts' Law test is proposed as a suitable alternative to using virtual limb environments for evaluating real-time myoelectric control performance. The test is used to compare the selective approach to a state-of-the-art linear discriminant analysis classification based scheme. The framework is shown to obey Fitts' Law for both control schemes, producing linear regression fittings with high coefficients of determination (R(2) > 0.936). Additional performance metrics focused on quality of control are discussed and incorporated in the evaluation. Using this framework the selective classification based scheme is shown to produce significantly higher efficiency and completion rates, and significantly lower overshoot and stopping distances, with no significant difference in throughput.

Simultaneous and proportional force estimation in multiple degrees of freedom from intramuscular EMG.

This letter investigates simultaneous and proportional estimation of force in 2 degree-of-freedoms (DoFs) from intramuscular electromyography (EMG). Intramuscular EMG signals from three able-bodied subjects were recorded along with isometric forces in multiple DoF from the right arm. The association between five EMG features and force profiles was modeled using an artificial neural network. Correlation coefficients between the measured and the estimated forces were 0.85 ± 0.056 and 0.88 ± 0.05 without and with post processing, respectively. The results showed that force can be estimated in 2 DoFs with high accuracy and that the degree of performance depended on the force function (task) to be estimated.

A comparison between force and position control strategies in myoelectric prostheses.

This work studies the simultaneous and proportional myoelectric force and position estimation of multiple degrees of freedom (DOFs) for unilateral transradial amputees. Two experiments were conducted to compare force and position control paradigms. In the first, a force experiment, subjects performed isometric contractions, while the force applied by the limb and EMG were recorded. In the second, a position experiment, dynamic contractions were permitted during which position of the limb and EMG were measured. Artificial neural networks (ANNs) were trained to estimate force/position from EMG of the contralateral limb during mirrored bilateral contractions. This study involved contractions with combined activations of three DOFs including wrist: flexion/extension, radial/ulnar deviation and forearm supination/pronation. For the given data set, while force estimation demonstrated high accuracy (R(2)=0.84±0.02), position estimation performance was relatively poor (R(2)=0.57±0.05). Two healthy subjects participated in this work.

Whitening of the electromyogram for improved classification accuracy in prosthesis control.

The electromyogram (EMG) signal has been used as the command input to myoelectric prostheses. A common control scheme is based on classifying the EMG signals from multiple electrodes into one of several distinct classes of user intent/function. In this work, we investigated the use of EMG whitening as a preprocessing step to EMG pattern recognition. Whitening is known to decorrelate the EMG signal, with improved performance shown in the related applications of EMG amplitude estimation and EMG-torque processing. We reanalyzed the EMG signals recorded from 10 electrodes placed circumferentially around the forearm of 10 intact subjects and 5 amputees. The coefficient of variation of two time-domain features--mean absolute value and signal length--was significantly reduced after whitening. Pre-whitened classification models using these features, along with autoregressive power spectrum coefficients, added approximately five percentage points to their classification accuracy. Improvement was best using smaller window durations (<100 ms).

Continuous locomotion-mode identification for prosthetic legs based on neuromuscular-mechanical fusion.

In this study, we developed an algorithm based on neuromuscular-mechanical fusion to continuously recognize a variety of locomotion modes performed by patients with transfemoral (TF) amputations. Electromyographic (EMG) signals recorded from gluteal and residual thigh muscles and ground reaction forces/moments measured from the prosthetic pylon were used as inputs to a phase-dependent pattern classifier for continuous locomotion-mode identification. The algorithm was evaluated using data collected from five patients with TF amputations. The results showed that neuromuscular-mechanical fusion outperformed methods that used only EMG signals or mechanical information. For continuous performance of one walking mode (i.e., static state), the interface based on neuromuscular-mechanical fusion and a support vector machine (SVM) algorithm produced 99% or higher accuracy in the stance phase and 95% accuracy in the swing phase for locomotion-mode recognition. During mode transitions, the fusion-based SVM method correctly recognized all transitions with a sufficient predication time. These promising results demonstrate the potential of the continuous locomotion-mode classifier based on neuromuscular-mechanical fusion for neural control of prosthetic legs.

Selective classification for improved robustness of myoelectric control under nonideal conditions.

Recent literature in pattern recognition-based myoelectric control has highlighted a disparity between classification accuracy and the usability of upper limb prostheses. This paper suggests that the conventionally defined classification accuracy may be idealistic and may not reflect true clinical performance. Herein, a novel myoelectric control system based on a selective multiclass one-versus-one classification scheme, capable of rejecting unknown data patterns, is introduced. This scheme is shown to outperform nine other popular classifiers when compared using conventional classification accuracy as well as a form of leave-one-out analysis that may be more representative of real prosthetic use. Additionally, the classification scheme allows for real-time, independent adjustment of individual class-pair boundaries making it flexible and intuitive for clinical use.