Classification of surface EMG signal with fractal dimension

Instance-based learning with prototype reduction for real-time proportional myocontrol: a randomized user study demonstrating accuracy-preserving data reduction for prosthetic embedded systems

This work presents the design, implementation and validation of learning techniques based on the kNN scheme for gesture detection in prosthetic control. To cope with high computational demands in instance-based prediction, methods of dataset reduction are evaluated considering real-time determinism to allow for the reliable integration into battery-powered portable devices. The influence of parameterization and varying proportionality schemes is analyzed, utilizing an eight-channel-sEMG armband. Besides offline cross-validation accuracy, success rates in real-time pilot experiments (online target achievement tests) are determined. Based on the assessment of specific dataset reduction techniques' adequacy for embedded control applications regarding accuracy and timing behaviour, decision surface mapping (DSM) proves itself promising when applying kNN on the reduced set. A randomized, double-blind user study was conducted to evaluate the respective methods (kNN and kNN with DSM-reduction) against ridge regression (RR) and RR with random Fourier features (RR-RFF). The kNN-based methods performed significantly better ([Formula: see text]) than the regression techniques. Between DSM-kNN and kNN, there was no statistically significant difference (significance level 0.05). This is remarkable in consideration of only one sample per class in the reduced set, thus yielding a reduction rate of over 99% while preserving success rate. The same behaviour could be confirmed in an extended user study. With [Formula: see text], which turned out to be an excellent choice, the runtime complexity of both kNN (in every prediction step) as well as DSM-kNN (in the training phase) becomes linear concerning the number of original samples, favouring dependable wearable prosthesis applications.

Usefulness of Surface Electromyography Complexity Analyses to Assess the Effects of Warm-Up and Stretching during Maximal and Sub-Maximal Hamstring Contractions: A Cross-Over, Randomized, Single-Blind Trial

This study aimed to apply different complexity-based methods to surface electromyography (EMG) in order to detect neuromuscular changes after realistic warm-up procedures that included stretching exercises. Sixteen volunteers conducted two experimental sessions. They were tested before, after a standardized warm-up, and after a stretching exercise (static or neuromuscular nerve gliding technique). Tests included measurements of the knee flexion torque and EMG of biceps femoris (BF) and semitendinosus (ST) muscles. EMG was analyzed using the root mean square (RMS), sample entropy (SampEn), percentage of recurrence and determinism following a recurrence quantification analysis (%Rec and %Det) and a scaling parameter from a detrended fluctuation analysis. Torque was significantly greater after warm-up as compared to baseline and after stretching. RMS was not affected by the experimental procedure. In contrast, SampEn was significantly greater after warm-up and stretching as compared to baseline values. %Rec was not modified but %Det for BF muscle was significantly greater after stretching as compared to baseline. The a scaling parameter was significantly lower after warm-up as compared to baseline for ST muscle. From the present results, complexity-based methods applied to the EMG give additional information than linear-based methods. They appeared sensitive to detect EMG complexity increases following warm-up.

Generating the Visual Biofeedback Signals Applicable to Reduction of Wrist Spasticity: A Pilot Study on Stroke Patients

INTRODUCTION

Application of biofeedback techniques in rehabilitation has turned into an exciting research area during the recent decade. Providing an appropriate visual or auditory biofeedback signal is the most critical requirement of a biofeedback technique. In this regard, changes in Surface Electromyography (SEMG) signals during wrist movement can be used to generate an indictable visual biofeedback signal for wrist movement rehabilitation via SEMG biofeedback. This paper proposes a novel methodology for selecting the most appropriate features out of wrist muscle SEMG signals.

METHODS

To this end, the surface EMG signals from flexor and extensor muscle groups during wrist joint movements were recorded and analyzed. Some linear and nonlinear features in frequency, time, and time-frequency domains were extracted from the recorded surface EMG signals of the flexor and extensor muscles. Experiments and analyses were performed on ten healthy subjects and four stroke patients with wrist muscle spasticity as the movement disorder subjects. Some heuristic feature selection measures were applied. The main motivation behind choosing applied heuristic feature selection measures was meeting. In the first step, the designed visual biofeedback signal should indicate a healthy wrist motion profile as its successful tracking by the patient guarantees rehabilitation. In addition, the visual biofeedback signal should be a smooth curve thus preventing the patient from discomfort while tracking it on a monitor during the biofeedback therapy.

RESULTS

In this pilot study, after using the introduced feature selection measures, quantitative and qualitative analyses of the extracted features indicated that Shannon entropy is the most appropriate feature for generating a visual biofeedback signal as a healthy wrist motion profile to improve the ability of stroke patients in controlling wrist joint motion. In addition, it was shown that when the wrist joint moves between a flexed and rest position, the flexor muscle EMG signal should be used for generating a visual biofeedback signal. However when the wrist joint moves between a rest position and an extended position, the extensor muscle EMG signal is appropriate for providing a visual biofeedback signal. It is worth noting that the achieved pilot study results should be confirmed by the future studies with larger samples.

CONCLUSION

According to the obtained results, it can be concluded that among the analyzed features, the Shannon entropy was the most appropriate feature. It can be employed for generating a visual biofeedback signal for reduction of spasticity in patients with stroke.

Myoelectric control of prosthetic hands: state-of-the-art review

Myoelectric signals (MES) have been used in various applications, in particular, for identification of user intention to potentially control assistive devices for amputees, orthotic devices, and exoskeleton in order to augment capability of the user. MES are also used to estimate force and, hence, torque to actuate the assistive device. The application of MES is not limited to assistive devices, and they also find potential applications in teleoperation of robots, haptic devices, virtual reality, and so on. The myoelectric control-based prosthetic hand aids to restore activities of daily living of amputees in order to improve the self-esteem of the user. All myoelectric control-based prosthetic hands may not have similar operations and exhibit variation in sensing input, deciphering the signals, and actuating prosthetic hand. Researchers are focusing on improving the functionality of prosthetic hand in order to suit the user requirement with the different operating features. The myoelectric control differs in operation to accommodate various external factors. This article reviews the state of the art of myoelectric prosthetic hand, giving description of each control strategy.

Myoelectric control of prosthetic hands: state-of-the-art review

Myoelectric signals (MES) have been used in various applications, in particular, for identification of user intention to potentially control assistive devices for amputees, orthotic devices, and exoskeleton in order to augment capability of the user. MES are also used to estimate force and, hence, torque to actuate the assistive device. The application of MES is not limited to assistive devices, and they also find potential applications in teleoperation of robots, haptic devices, virtual reality, and so on. The myoelectric control-based prosthetic hand aids to restore activities of daily living of amputees in order to improve the self-esteem of the user. All myoelectric control-based prosthetic hands may not have similar operations and exhibit variation in sensing input, deciphering the signals, and actuating prosthetic hand. Researchers are focusing on improving the functionality of prosthetic hand in order to suit the user requirement with the different operating features. The myoelectric control differs in operation to accommodate various external factors. This article reviews the state of the art of myoelectric prosthetic hand, giving description of each control strategy.

Classification of surface electromyographic signals by means of multifractal singularity spectrum

In order to effectively control a prosthetic system, considerable attempts have been made in recent years to improve the classification accuracy of surface electromyographic (SEMG) signals. However, the extraction of effective features is still a primary challenge for the classification of SEMG signals. This study tried to solve the problem by applying the multifractal analysis. It was found that the SEMG signals were characterized by multifractality during forearm movements and different types of forearm movements were related to different multifractal singularity spectra. To quantitatively evaluate the multifractal singularity spectra of the SEMG signals, the areas of the singularity spectrum curves were calculated by integrating the spectrum curves with respect to the singularity strengths. Our results showed that there were several separate clusters resulting from singularity spectrum areas of different forearm movements when two channels of SEMG signals were used in this experimental research, which demonstrated that the multifractal analysis approach was suitable for identifying different types of forearm movements. By comparing with other feature extraction techniques, the multifractal singularity spectrum approach provided higher classification accuracy in terms of the classification of SEMG signals.

FRACTAL PROPERTIES OF SURFACE ELECTROMYOGRAM FOR CLASSIFICATION OF LOW-LEVEL HAND MOVEMENTS FROM SINGLE-CHANNEL FOREARM MUSCLE ACTIVITY

Surface electromyogram (sEMG) has been used in the identification of various hand movements which can lead to a number of rehabilitation, medical, and human computer interface applications. These applications are currently in need of higher accuracy and become challenging because of its unreliability in the classification of sEMG when the level of muscle contraction is low and when there are multiple active muscles. The presence of noise and cross-talk from closely located and simultaneously active muscles is exaggerated when muscles are weakly active such as during sustained wrist and finger flexion. This study reports the use of fractal properties of sEMG to identify the small changes in strength of muscle contraction and the location of the active muscles. It is observed that the fractal dimension (FD) of the signal is related to the complexity of the muscle contraction while maximum fractal length (MFL) is related to the strength of contraction of the associated muscle. The results show that the MFL and FD of a single-channel sEMG from the forearm can be used to accurately identify a set of finger-and-wrist flexion-based actions even when the muscle activity is very weak. It is proposed that such a system could be used to control a prosthetic hand or for a human computer interface.

Fractal feature of sEMG from Flexor digitorum superficialis muscle correlated with levels of contraction during low-level finger flexions

This research paper reports an experimental study on identification of the changes in fractal properties of surface Electromyogram (sEMG) with the changes in the force levels during low-level finger flexions. In the previous study, the authors have identified a novel fractal feature, Maximum fractal length (MFL) as a measure of strength of low-level contractions and has used this feature to identify various wrist and finger movements. This study has tested the relationship between the MFL and force of contraction. The results suggest that changes in MFL is correlated with the changes in contraction levels (20%, 50% and 80% maximum voluntary contraction (MVC)) during low-level muscle activation such as finger flexions. From the statistical analysis and by visualisation using box-plot, it is observed that MFL (p ≈ 0.001) is a more correlated to force of contraction compared to RMS (p≈0.05), even when the muscle contraction is less than 50% MVC during low-level finger flexions. This work has established that this fractal feature will be useful in providing information about changes in levels of force during low-level finger movements for prosthetic control or human computer interface.

Decoding subtle forearm flexions using fractal features of surface electromyogram from single and multiple sensors

Background

Identifying finger and wrist flexion based actions using a single channel surface electromyogram (sEMG) can lead to a number of applications such as sEMG based controllers for near elbow amputees, human computer interface (HCI) devices for elderly and for defence personnel. These are currently infeasible because classification of sEMG is unreliable when the level of muscle contraction is low and there are multiple active muscles. The presence of noise and cross-talk from closely located and simultaneously active muscles is exaggerated when muscles are weakly active such as during sustained wrist and finger flexion. This paper reports the use of fractal properties of sEMG to reliably identify individual wrist and finger flexion, overcoming the earlier shortcomings.

Methods

SEMG signal was recorded when the participant maintained pre-specified wrist and finger flexion movements for a period of time. Various established sEMG signal parameters such as root mean square (RMS), Mean absolute value (MAV), Variance (VAR) and Waveform length (WL) and the proposed fractal features: fractal dimension (FD) and maximum fractal length (MFL) were computed. Multi-variant analysis of variance (MANOVA) was conducted to determine the p value, indicative of the significance of the relationships between each of these parameters with the wrist and finger flexions. Classification accuracy was also computed using the trained artificial neural network (ANN) classifier to decode the desired subtle movements.

Results

The results indicate that the p value for the proposed feature set consisting of FD and MFL of single channel sEMG was 0.0001 while that of various combinations of the five established features ranged between 0.009 - 0.0172. From the accuracy of classification by the ANN, the average accuracy in identifying the wrist and finger flexions using the proposed feature set of single channel sEMG was 90%, while the average accuracy when using a combination of other features ranged between 58% and 73%.

Conclusions

The results show that the MFL and FD of a single channel sEMG recorded from the forearm can be used to accurately identify a set of finger and wrist flexions even when the muscle activity is very weak. A comparison with other features demonstrates that this feature set offers a dramatic improvement in the accuracy of identification of the wrist and finger movements. It is proposed that such a system could be used to control a prosthetic hand or for a human computer interface.

A machine learning based method for classification of fractal features of forearm sEMG using Twin Support vector machines

Classification of surface electromyogram (sEMG) signal is important for various applications such as prosthetic control and human computer interface. Surface EMG provides a better insight into the strength of muscle contraction which can be used as control signal for different applications. Due to the various interference between different muscle activities, it is difficult to identify movements using sEMG during low-level flexions. A new set of fractal features - fractal dimension and Maximum fractal length of sEMG has been previously reported by the authors. These features measure the complexity and strength of the muscle contraction during the low-level finger flexions. In order to classify and identify the low-level finger flexions using these features based on the fractal properties, a recently developed machine learning based classifier, Twin Support vector machines (TSVM) has been proposed. TSVM works on basic learning methodology and solves the classification tasks as two SVMs for each classes. This paper reports the novel method on the machine learning based classification of fractal features of sEMG using the Twin Support vector machines. The training and testing was performed using two different kernel functions - Linear and Radial Basis Function (RBF).

Denoising of surface EMG with a modified Wiener filtering approach

The correlation dimension D(2) yields good results in several biomedical fields. Nonetheless, no clinical application to electromyography has been developed yet. One reason is the high electromagnetic noise typical of clinical environments. This noise is characterized by sharp spectral lines of variable intensity and frequency. The filtering techniques commonly implemented in electromyographs can efficiently deal with this kind of noise. They allow a safe estimate of linear quantities like the root mean square (r.m.s.) or the median frequency (MF). Their performance is not as good for nonlinear purposes. The filters may modify the nonlinear properties of the signal, leading to unacceptable estimates of D(2). We consider a simple procedure based on a modified Wiener filter. Its performance is compared with that from a bandpass followed by multiple notch filters. Our procedure leads to a gain in precision and accuracy when estimating D(2). The two filtering approaches are also compared with respect to a biomedical application proposed by others. Using data from 12 healthy subjects, the modified Wiener procedure raises the percentage of successes in that application from 17% to 83%. New experimental data suggest D(2) carries information not carried by r.m.s. or MF.

Fractal analysis of surface electromyography signals: a novel power spectrum-based method

This paper presents a novel power spectrum-based method for fractal analysis of surface electromyography signals. This method, named the bi-phase power spectrum method, provides a bi-phase power-law which represents a multi-scale statistically self-affine signal. This form of statistical self-affinity provides an accurate approximation for stochastic signals originating from a strong non-linear combination of a number of similar distributions, such as surface electromyography signals which are formed by the summation of a number of single muscle fiber action potentials. This power-law is characterized by a set of spectral indicators, which are related to distributional and geometrical characteristics of the electromyography signal's interference pattern. These novel spectral indicators are capable of sensing the effects of motor units' recruitment and shape separately by exploiting the geometry of the interference pattern. The bi-phase power spectrum method is compared to geometrical techniques and the 1/f(alpha) approach for fractal analysis of electromyography signals. The extracted indicators using the bi-phase power spectrum method are evaluated in the context of force and joint angle and the results of a human study are presented. Results demonstrate that the bi-phase power spectrum method provides reliable information, consisting of components capable of sensing force and joint angle effects separately, which could be used as complementary information for confounded conventional measures.

Fractal based modelling and analysis of electromyography (EMG) to identify subtle actions

The paper reports the use of fractal theory and fractal dimension to study the non-linear properties of surface electromyogram (sEMG) and to use these properties to classify subtle hand actions. The paper reports identifying a new feature of the fractal dimension, the bias that has been found to be useful in modelling the muscle activity and of sEMG. Experimental results demonstrate that the feature set consisting of bias values and fractal dimension of the recordings is suitable for classification of sEMG against the different hand gestures. The scatter plots demonstrate the presence of simple relationships of these features against the four hand gestures. The results indicate that there is small inter-experimental variation but large inter-subject variation. This may be due to differences in the size and shape of muscles for different subjects. The possible applications of this research include use in developing prosthetic hands, controlling machines and computers.

Characterization of surface EMG signals using improved approximate entropy

An improved approximate entropy (ApEn) is presented and applied to characterize surface electromyography (sEMG) signals. In most previous experiments using nonlinear dynamic analysis, this certain processing was often confronted with the problem of insufficient data points and noisy circumstances, which led to unsatisfactory results. Compared with fractal dimension as well as the standard ApEn, the improved ApEn can extract information underlying sEMG signals more efficiently and accurately. The method introduced here can also be applied to other medium-sized and noisy physiological signals.