Classification of hand and wrist tasks of unknown force levels using muscle synergies.

Muscle synergies have been proposed as a way for the central nervous system (CNS) to simplify the generation of motor commands and they have been shown to explain a large portion of the variation in the muscle patterns across a variety of conditions. However, whether human subjects are able to control prostheses proportionally with a small set of synergies has not been tested directly. Here we investigated if muscle synergies can be used to identify different wrist and hand motions. We recorded electromyographic (EMG) activity from eight arm muscles while the subjects exerted seven different intensity levels during the motions when performing seven classes of hand and wrist motion. From these data we extracted the muscle synergies and classified the tasks associated to each contraction intensity profile by linear discriminant analysis (LDA). We compared the performance obtained using muscle synergies with the performance of using the mean absolute values (MAV) as a feature. Also, the consistency of extracted muscle synergies was studied across intensity variations. While the synergies showed relative consistency particularly across closer intensity levels, average classification results generated with the synergies were less accurate than MAVs. These results indicate that although the performance of muscle synergies was very close to MAVs, they do not provide additional information for task identification across different exerted intensity levels.

A comparison of classification based confidence metrics for use in the design of myoelectric control systems.

In many pattern recognition applications, confidence scores are used to extract more information than discrete class membership alone, yet they have not traditionally been leveraged in myoelectric control. In this work, the confidence scores of eight common classification schemes were examined. Their role in rejecting inadvertent motions is investigated, and the tradeoffs observed in the design of rejection capable control schemes are demonstrated. It is shown that the distribution of confidences can varying greatly between classifiers, even when classification performance is similar. As a specific example, an ensemble of support vector machines in a one against one configuration (SVM1vs1) outperforms the previously reported LDAR myoelectric pattern recognition rejection scheme in terms of accuracy-rejection curves (ARC) and false acceptance/rejection (FAR) curves.

On the robustness of EMG features for pattern recognition based myoelectric control: a multi-dataset comparison.

The selection of optimal features has long been a subject of debate for pattern recognition based myoelectric control. Studies have compared many features, but have typically used small or constrained data sets. Herein, the performance of various features is evaluated using data from six previously reported data sets. The number of channels, the contraction dynamics (dynamic vs static), and classifier type all yielded significant interactions (p<;0.05) with the feature set. When using 8 channels, the addition of the tested features produced no improvement over a standard time domain (TD) feature set alone (p>0.05). When using fewer channels, however, autoregressive, Cepstral coefficients, Willison amplitude and sample entropy features all provided significant improvement during dynamic contractions (p<;0.05). The simple Willison amplitude is highlighted, showing that it can provide significant improvement when used as a replacement for any one of the standard TD features.

A characterization of the effect of limb position on EMG features to guide the development of effective prosthetic control schemes.

Electromyogram (EMG) pattern recognition has long been used for the control of upper limb prostheses. More recently, it has been shown that variability induced during functional use, such as changes in limb position and dynamic contractions, can have a substantial impact on the robustness of EMG pattern recognition. This work further investigates the reasons for pattern recognition performance degradation due to the limb position variation. The main focus is on the impact of limb position variation on features of the EMG, as measured using separability and repeatability metrics. The results show that when the limb is moved to a position different from the one in which the classifier is trained, both the separability and repeatability of the data decrease. It is shown how two previously proposed classification methods, multiple position training and dual-stage classification, resolve the position effect problem to some extent through increasing either separability or repeatability but not both. A hybrid classification method which exhibits a compromise between separability and repeatability is proposed in this work. It is shown that, when tested with the limb in 16 different positions, this method increases classification accuracy from an average of 70% (single position training) to 89% (hybrid approach). This hybrid method significantly (p<;0.05) outperforms multiple position training (an average of 86%) and dual-stage classification (an average of 85%).

A multi-modal approach for hand motion classification using surface EMG and accelerometers.

For decades, electromyography (EMG) has been used for diagnostics, upper-limb prosthesis control, and recently even for more general human-machine interfaces. Current commercial upper limb prostheses usually have only two electrode sites due to cost and space limitations, while researchers often experiment with multiple sites. Micro-machined inertial sensors are gaining popularity in many commercial and research applications where knowledge of the postures and movements of the body is desired. In the present study, we have investigated whether accelerometers, which are relatively cheap, small, robust to noise, and easily integrated in a prosthetic socket; can reduce the need for adding more electrode sites to the prosthesis control system. This was done by adding accelerometers to a multifunction system and also to a simplified system more similar to current commercially available prosthesis controllers, and assessing the resulting changes in classification accuracy. The accelerometer does not provide information on muscle force like EMG electrodes, but the results show that it provides useful supplementary information. Specifically, if one wants to improve a two-site EMG system, one should add an accelerometer affixed to the forearm rather than a third electrode.

Improving myoelectric pattern recognition positional robustness using advanced training protocols.

The control of powered upper limb prostheses using the surface electromyogram (EMG) is an important clinical option for amputees. There have been considerable recent improvements in prosthetic hands, but these currently lack a control scheme that can decode movement intent from the EMG to exploit their mechanical dexterity. Pattern recognition based control has the potential to decode many classes of movement intent, but is confounded when using the prosthesis in varying positions during activities of daily living. This work describes the degradation that can occur when using pattern recognition in varying positions, during both static positioning tasks and dynamic activities of daily living. It is shown that training with dynamic activities can greatly improve positional robustness for both static and dynamic tasks, without requiring a complex and lengthy training session.

Examining the adverse effects of limb position on pattern recognition based myoelectric control.

Pattern recognition of myoelectric signals for the control of prosthetic devices has been widely reported and debated. A large portion of the literature focuses on offline classification accuracy of pre-recorded signals. Historically, however, there has been a semantic gap between research findings and a clinically viable implementation. Recently, renewed focus on prosthetics research has pushed the field to provide more clinically relevant outcomes. One way to work towards this goal is to examine the differences between research and clinical results. The constrained nature in which offline training and test data is often collected compared to the dynamic nature of prosthetic use is just one example. In this work, we demonstrate that variations in limb position after training can have a substantial impact on the robustness of myoelectric pattern recognition.

A real-time pattern recognition based myoelectric control usability study implemented in a virtual environment.

Pattern recognition based myoelectric control systems have been well researched; however very few systems have been implemented in a clinical environment. Although classification accuracy or classification error is the metric most often reported to describe how well these control systems perform, very little work research has been conducted to relate this measure to the usability of the system. This work presents a virtual clothespin usability test to assess the performance of pattern recognition based myoelectric control systems. The results suggest that users can complete the virtual task in reasonable time frames when using systems with high classification accuracies. Additionally, results indicate that a clinically-supported classifier training approach (inclusion of the transient potion of contraction signals) may reduce classification accuracy but increase real-time performance.

A control system for a powered prosthesis using positional and myoelectric inputs from the shoulder complex.

The integration of multiple input sources within a control strategy for powered upper limb prostheses could provide smoother, more intuitive multi-joint reaching movements based on the user's intended motion. The work presented in this paper presents the results of using myoelectric signals (MES) of the shoulder area in combination with the position of the shoulder as input sources to multiple linear discriminant analysis classifiers. Such an approach may provide users with control signals capable of controlling three degrees of freedom (DOF). This work is another important step in the development of hybrid systems that will enable simultaneous control of multiple degrees of freedom used for reaching tasks in a prosthetic limb.

Principal components analysis preprocessing to reduce controller delays in pattern recognition based myoelectric control.

Information extracted from signals recorded from multi-channel surface myoelectric signal (MES) recording sites can be used as inputs to control systems for powered prostheses. For small, closely spaced muscles, such as the muscles in the forearm, the detected MES often contains contributions from more than one muscle; the contribution from each specific muscle being modified by a tissue filter between the muscle and the detection points. In this work, the measured raw MES signals are rotated by class specific rotation matrices to spatially decorrelate the measured data prior to feature extraction. This tunes the pattern recognition classifier to better discriminate the test motions. Using this preprocessing step, MES analysis windows may be cut from 256 ms to 128 ms without affecting the classification accuracy.

Myoelectric signal processing for control of powered limb prostheses.

Progress in myoelectric control technology has over the years been incremental, due in part to the alternating focus of the R&D between control methodology and device hardware. The technology has over the past 50 years or so moved from single muscle control of a single prosthesis function to muscle group activity control of multifunction prostheses. Central to these changes have been developments in the means of extracting information from the myoelectric signal. This paper gives an overview of the myoelectric signal processing challenge, a brief look at the challenge from an historical perspective, the state-of-the-art in myoelectric signal processing for prosthesis control, and an indication of where this field is heading. The paper demonstrates that considerable progress has been made in providing clients with useful and reliable myoelectric communication channels, and that exciting work and developments are on the horizon.

The effect of electrode displacements on pattern recognition based myoelectric control.

Pattern recognition based myoelectric controllers rely on a fundamental assumption that the patterns detected under a given electrode are repeatable for a given state of muscle activation. Consequently, electrode displacements on the skins surface affect the classification accuracy of the pattern based myoelectric controller. The effects of electrode displacement can be mitigated by using a training set of data which consists of patterns detected over a range of plausible displacement locations to train the control system.

Pattern recognition of single and combined motions from the shoulder complex.

Much research has been done towards developing control systems for artificial hands, elbows, and wrists based on the myoelectric signal (MES). While great effort has gone into developing pattern recognition based control systems for these devices, very little attention has been devoted to the shoulder. This is in part because the majority of amputees are either below elbow or mid-humeral, and true shoulder disarticulations are rare. However, as the level of limb loss increases so does the need for functional replacement. This study investigates pattern recognition concepts for independent control of an artificial shoulder.

Optimized Gaussian mixture models for upper limb motion classification.

This paper introduces the use of Gaussian mixture models (GMM) for discriminating multiple classes of limb motions using continuous myoelectric signals (MES). The purpose of this work is to investigate an optimum configuration of a GMM-based limb motion classification scheme. For this effort, a complete experimental evaluation of the Gaussian mixture motion model is conducted on a 12-subject database. The experiments examine algorithmic issues of the GMM including the model order selection and variance limiting. The final classification performance of this GMM system has been compared with that of three other classifiers (a linear discriminant analysis (LDA), a linear perceptron neural network (LP) and a multilayer perceptron (MLP) neural network) . The Gaussian mixture motion model attains 96.3% classification accuracy using four channel MES for distinguishing six limb motions and is shown to outperform the other motion modeling techniques on an identical six limb motion task.

Myo-electric signals to augment speech recognition.

It is proposed that myo-electric signals can be used to augment conventional speech-recognition systems to improve their performance under acoustically noisy conditions (e.g. in an aircraft cockpit). A preliminary study is performed to ascertain the presence of speech information within myo-electric signals from facial muscles. Five surface myo-electric signals are recorded during speech, using Ag-AgCl button electrodes embedded in a pilot oxygen mask. An acoustic channel is also recorded to enable segmentation of the recorded myo-electric signal. These segments are processed off-line, using a wavelet transform feature set, and classified with linear discriminant analysis. Two experiments are performed, using a ten-word vocabulary consisting of the numbers 'zero' to 'nine'. Five subjects are tested in the first experiment, where the vocabulary is not randomised. Subjects repeat each word continuously for 1 min; classification errors range from 0.0% to 6.1%. Two of the subjects perform the second experiment, saying words from the vocabulary randomly; classification errors are 2.7% and 10.4%. The results demonstrate that there is excellent potential for using surface myo-electric signals to enhance the performance of a conventional speech-recognition system.

A wavelet-based continuous classification scheme for multifunction myoelectric control.

This work represents an ongoing investigation of dexterous and natural control of powered upper limbs using the myoelectric signal. When approached as a pattern recognition problem, the success of a myoelectric control scheme depends largely on the classification accuracy. A novel approach is described that demonstrates greater accuracy than in previous work. Fundamental to the success of this method is the use of a wavelet-based feature set, reduced in dimension by principal components analysis. Further, it is shown that four channels of myoelectric data greatly improve the classification accuracy, as compared to one or two channels. It is demonstrated that exceptionally accurate performance is possible using the steady-state myoelectric signal. Exploiting these successes, a robust online classifier is constructed, which produces class decisions on a continuous stream of data. Although in its preliminary stages of development, this scheme promises a more natural and efficient means of myoelectric control than one based on discrete, transient bursts of activity.