Haoshi Zhang

Pattern recognition of electromyography signals based on novel time domain features for amputees' limb motion classification☆

Abstract Feature extraction is essential in Electromyography pattern recognition (EMG-PR) based prostheses control method. Time-domain features have been shown to have good performance in upper limb movement classification. However, the performance of EMG-PR prostheses driven by the existing time-domain features is still unsatisfactory. Hence, this study proposed three new time-domain features to improve the performance of EMG-PR based strategy in arm movement classification. EMG signals were recorded from the residual arms of eight amputees while performing different upper limb movements. Then, the newly proposed features were extracted and used to classify their limb movements. Experimental results showed that the proposed features could achieved an average classification accuracy of 92.00% ± 3.11% which was 6.49% higher than that of the commonly used time-domain features (p

An adaptation strategy of using LDA classifier for EMG pattern recognition

The time-varying character of myoelectric signal usually causes a low classification accuracy in traditional supervised pattern recognition method. In this work, an unsupervised adaptation strategy of linear discriminant analysis (ALDA) based on probability weighting and cycle substitution was suggested in order to improve the performance of electromyography (EMG)-based motion classification in multifunctional myoelectric prostheses control in changing environment. The adaptation procedure was firstly introduced, and then the proposed ALDA classifier was trained and tested with surface EMG recordings related to multiple motion patterns. The accuracies of the ALDA classifier and traditional LDA classifier were compared when the EMG recordings were added with different degrees of noise. The experimental results showed that compared to the LDA method, the suggested ALDA method had a better performance in improving the classification accuracy of sEMG pattern recognition, in both stable situation and noise added situation.

Towards reducing the impacts of unwanted movements on identification of motion intentions

Surface electromyogram (sEMG) has been extensively used as a control signal in prosthesis devices. However, it is still a great challenge to make multifunctional myoelectric prostheses clinically available due to a number of critical issues associated with existing EMG based control strategy. One such issue would be the effect of unwanted movements (UMs) that are inadvertently done by users on the performance of movement classification in EMG pattern recognition based algorithms. Since UMs are not considered in training a classifier, they would decay the performance of a trained classifier in identifying the target movements (TMs), which would cause some undesired actions in control of multifunctional prostheses. In this study, the impact of UMs was systemically investigated in both able-bodied subjects and transradial amputees. Our results showed that the UMs would be unevenly classified into all classes of the TMs. To reduce the impact of the UMs on the performance of a classifier, a new training strategy that would categorize all possible UMs into a new movement class was proposed and a metric called Reject Ratio that is a measure of how many UMs is rejected by a trained classifier was adopted. The results showed that the average Reject Ratio across all the participants was greater than 91%, meanwhile the average classification accuracy of TMs was above 99% when UMs occurred. This suggests that the proposed training strategy could greatly reduce the impact of UMs on the performance of the trained classifier in identifying the TMs and may enhance the robustness of myoelectric control in clinical applications.

Bioelectric signal detrending using smoothness prior approach.

Bioelectric signals such as electromyogram (EMG) and electrocardiogram (ECG) are often affected by various low-frequency trending interferences. It is critical to remove these interferences from the recordings so that the critical features of the bioelectric signals could be clearly observed. In this study, an advanced method based on smoothness prior approach (SPA) was proposed to solve this problem. EMG and ECG signals from both the MIT-BIH database and the experiments were employed to evaluate the detrending performance of the proposed method. For comparison purposes, a conventional high-pass Butterworth filter was also used for the detrending of the EMG and ECG signals. Two numerical measures, the correlation coefficient (CC) and root mean square error (RMSE) between the clean data and the detrended data, were calculated to evaluate the detrending performance. The results showed that the proposed SPA method outperformed the high-pass filtering method in reducing various kinds of trending interferences and preserving the desired frequency contents of the EMG and ECG signals. The study suggested that the SPA method might be a promising approach in detrending bioelectric signals.

Using textile electrode EMG for prosthetic movement identification in transradial amputees

Wearable systems based on continuously monitoring of vital physiological signals without interfering with users daily life much are desired urgently in health care. Similarly, the limb amputees who need to wear their myoelectric prostheses for a long time daily expect a comfortable and reliable prosthetic system. It is inconvenient in clinical application of a myoelectric prosthesis to use the commonly used gel electrode for electromyography (EMG) recording over all day. Textile electrode with characteristics of ventilation, flexibility, and folding, may be an ideal selection of physiological signal monitoring in clinical applications. In this study, the textile electrodes made using screen printing technology were used for EMG recordings and the real-time performance of the textile-electrode EMG in myoelectric control of multifunctional prostheses was investigated in transradial amputees and able-bodied subjects for comparison purpose. The results over seven able-bodied subjects showed that the textile electrode could achieve similar performance as conventional metal electrodes for both the off-line classification accuracy and the real-time motion completion rate in operating a virtual hand. With the textile electrodes, the average off-line classification accuracy of 73.4% and the real-time motion completion rate of 81.9% within a 5 s time limit were achieved in three transradial amputees. These pilot results suggested that the textile electrodes might be feasible for EMG recordings in control of myoelectric prostheses.

Toward Capturing Momentary Changes of Heart Rate Variability by a Dynamic Analysis Method.

The analysis of heart rate variability (HRV) has been performed on long-term electrocardiography (ECG) recordings (12~24 hours) and short-term recordings (2~5 minutes), which may not capture momentary change of HRV. In this study, we present a new method to analyze the momentary HRV (mHRV). The ECG recordings were segmented into a series of overlapped HRV analysis windows with a window length of 5 minutes and different time increments. The performance of the proposed method in delineating the dynamics of momentary HRV measurement was evaluated with four commonly used time courses of HRV measures on both synthetic time series and real ECG recordings from human subjects and dogs. Our results showed that a smaller time increment could capture more dynamical information on transient changes. Considering a too short increment such as 10 s would cause the indented time courses of the four measures, a 1-min time increment (4-min overlapping) was suggested in the analysis of mHRV in the study. ECG recordings from human subjects and dogs were used to further assess the effectiveness of the proposed method. The pilot study demonstrated that the proposed analysis of mHRV could provide more accurate assessment of the dynamical changes in cardiac activity than the conventional measures of HRV (without time overlapping). The proposed method may provide an efficient means in delineating the dynamics of momentary HRV and it would be worthy performing more investigations.

Effects of non-training movements on the performance of motion classification in electromyography pattern recognition

In electromyography pattern-recognition-based control of a multifunctional prosthesis, it would be inevitable for the users to unintentionally perform some classes of movements that are excluded from the training motion classes of a classifier, which might decay the performance of a trained classifier. It remains unknown how these untrained movements, designated as non-target movements (NTMs) in the study, would affect the performance of a trained classifier in the control of multifunctional prostheses. The goal of the current study was to evaluate the effects of NTMs on the performance of movement classification. Five classes of target movements (TMs) and four classes of NTMs were considered in this pilot study. A classifier based on a linear discriminant analysis (LDA) was trained with the electromyography (EMG) signals from the five TMs and the effects of the four NTMs were examined by feeding the EMG signals of the four NTMs to the trained classifier. Our results showed that these NTMs were classified into one or more classes of the TMs, which would cause the unexpected movements of prostheses. A method to reduce the effects of NTMs has been proposed in the study and our results showed that the averaged classification accuracies of the corrected classifiers were above 99% for the healthy subjects.

A Robust Feature Set for Wearable Multichannel Myoelectric Devices in Practice

A wearable myoelectric device is essentially a surface electromyography(sEMG) based human machine interaction (HMI) system. The non-stationary property of sEMG could be one of the obstacles that degrade the user experience of wearable myoelectric devices because they need to be put on and taken off frequently, which brings in the time-variation effects specified in this paper. In order to reduce the influence cause by time-variation on wearable myoelectric devices, the common spatial pattern(CSP) was employed to extract relatively robust features from multichannel sEMG signals. As comparation, the conventional time domain(TD) features together with time domain auto regressive(TDAR) features were investigated. To implement the experiment, 16 electrodes were utilized to simulate a wearable myoelectric device, and an absolute value based Teager-Kaiser energy operator(TKEO) strategy was proposed to realize onset detection. The experiment was divided into 2 sessions, corresponding to the situations before and after time-variation happened respectively. The support vector machine (SVM) and linear discrimination analysis(LDA) were used to build the pattern recognition models. In session2, the average classification accuracy of CSP(95.2±2.3%) is superior to TD(90.3±4.4%) and TDAR(92.4±4.2%) under LDA. The result suggests that the CSP feature set is relatively robust against accuracy reduction resulted from time-variation in motion recognition.

Piezoelectrets and their applications as wearable physiological-signal sensors and energy harvesters

Piezoelectrets are polymer-foam based space-charge electrets with strong piezoelectric effect. The piezoelectricity in piezoelectrets occurs due to the elastic heterogeneous cellular structure and the regularly arranged dipolar space charges stored therein. Some polymers have been experimented for piezoelectret preparation, where polypropylene (PP) is the mostly applied material at present. PP piezoelectrets have several promising features, such as large piezoelectric d33 coefficient, small thickness, light weight, low cost, large area scale, as well as flexibility and even stretchability, which would enable them very suitable for applications in signal sensing and energy harvesting. In this work, the electromechanical properties of flexible and stretchable PP piezoelectrets are introduced and some of their possible applications as wearable physiological-signal sensors and micro-energy harvesters are demonstrated by experiments.