Yanjuan Geng

Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees

BackgroundElectromyography (EMG) pattern-recognition based control strategies for multifunctional myoelectric prosthesis systems have been studied commonly in a controlled laboratory setting. Before these myoelectric prosthesis systems are clinically viable, it will be necessary to assess the effect of some disparities between the ideal laboratory setting and practical use on the control performance. One important obstacle is the impact of arm position variation that causes the changes of EMG pattern when performing identical motions in different arm positions. This study aimed to investigate the impacts of arm position variation on EMG pattern-recognition based motion classification in upper-limb amputees and the solutions for reducing these impacts.MethodsWith five unilateral transradial (TR) amputees, the EMG signals and tri-axial accelerometer mechanomyography (ACC-MMG) signals were simultaneously collected from both amputated and intact arms when performing six classes of arm and hand movements in each of five arm positions that were considered in the study. The effect of the arm position changes was estimated in terms of motion classification error and compared between amputated and intact arms. Then the performance of three proposed methods in attenuating the impact of arm positions was evaluated.ResultsWith EMG signals, the average intra-position and inter-position classification errors across all five arm positions and five subjects were around 7.3% and 29.9% from amputated arms, respectively, about 1.0% and 10% low in comparison with those from intact arms. While ACC-MMG signals could yield a similar intra-position classification error (9.9%) as EMG, they had much higher inter-position classification error with an average value of 81.1% over the arm positions and the subjects. When the EMG data from all five arm positions were involved in the training set, the average classification error reached a value of around 10.8% for amputated arms. Using a two-stage cascade classifier, the average classification error was around 9.0% over all five arm positions. Reducing ACC-MMG channels from 8 to 2 only increased the average position classification error across all five arm positions from 0.7% to 1.0% in amputated arms.ConclusionsThe performance of EMG pattern-recognition based method in classifying movements strongly depends on arm positions. This dependency is a little stronger in intact arm than in amputated arm, which suggests that the investigations associated with practical use of a myoelectric prosthesis should use the limb amputees as subjects instead of using able-body subjects. The two-stage cascade classifier mode with ACC-MMG for limb position identification and EMG for limb motion classification may be a promising way to reduce the effect of limb position variation on classification performance.

A novel channel selection method for multiple motion classification using high-density electromyography

BackgroundSelecting an appropriate number of surface electromyography (EMG) channels with desired classification performance and determining the optimal placement of EMG electrodes would be necessary and important in practical myoelectric control. In previous studies, several methods such as sequential forward selection (SFS) and Fisher-Markov selector (FMS) have been used to select the appropriate number of EMG channels for a control system. These exiting methods are dependent on either EMG features and/or classification algorithms, which means that when using different channel features or classification algorithm, the selected channels would be changed. In this study, a new method named multi-class common spatial pattern (MCCSP) was proposed for EMG selection in EMG pattern-recognition-based movement classification. Since MCCSP is independent on specific EMG features and classification algorithms, it would be more convenient for channel selection in developing an EMG control system than the exiting methods.MethodsThe performance of the proposed MCCSP method in selecting some optimal EMG channels (designated as a subset) was assessed with high-density EMG recordings from twelve mildly-impaired traumatic brain injury (TBI) patients. With the MCCSP method, a subset of EMG channels was selected and then used for motion classification with pattern recognition technique. In order to justify the performance of the MCCSP method against different electrode configurations, features and classification algorithms, two electrode configurations (unipolar and bipolar) as well as two EMG feature sets and two types of pattern recognition classifiers were considered in the study, respectively. And the performance of the proposed MCCSP method was compared with that of two exiting channel selection methods (SFS and FMS) in EMG control system.ResultsThe results showed that in comparison with the previously used SFS and FMS methods, the newly proposed MCCSP method had better motion classification performance. Moreover, a fixed combination of the selected EMG channels was obtained when using MCCSP.ConclusionsThe proposed MCCSP method would be a practicable means in channel selection and would facilitate the design of practical myoelectric control systems in the active rehabilitation of mildly-impaired TBI patients and in other rehabilitation applications such as the multifunctional myoelectric prostheses for limb amputees.

Performance of electromyography recorded using textile electrodes in classifying arm movements

Electromyography (EMG) signals are commonly recorded using the Ag/AgCl gel electrodes in myoelectric prosthetic control. While a gelled electrode may provide high-quality EMG recordings, it is inconvenient in clinical application of a myoelectric prosthesis. A novel type of signal sensors-textile electrodes should be ideal in control of myoelectric prostheses. However, it is unknown whether the performance of textile electrodes is comparable to commonly used electrodes in classifying arm movements. In this study, the custom-made bipolar textile electrodes were fabricated using copper-based nickel-plated conductive fabric and were used to record EMG signals. The performance of EMG signals recorded with textile electrodes in identifying nine arm and hand movements were investigated. Our pilot results showed that the average classification accuracy across six able-bodied subjects was 94.05% when using textile electrodes and 94.26% when using conventional electrodes, with no significant difference between the two types of electrodes (p=0.81). The pilot results suggest that the textile electrodes could achieve similar performance in classifying arm movements in control of myoelectric prostheses as the gelled metal electrodes.

Selection of sampling rate for EMG pattern recognition based prosthesis control

Most previous studies of electromyography (EMG) pattern recognition control of multifunctional myoelectric prostheses adopted a conventional sampling rate that is commonly used in EMG research fields. However, it is unknown whether using a lower sampling rate in EMG acquisition still preserves sufficient neural control information for accurate classification of user movement intents. This study investigated the effects of EMG sampling rate on the performance of EMG pattern recognition in identifying 11 classes of arm and hand movements. Our results showed that decreasing the sampling rate from 1 kHz to 500 Hz only caused 0.8% reduction of the average classification accuracy over five able-bodied subjects and 2.2% decrease over two transradial amputees. When using a 400 Hz sampling rate, the average classification accuracy decreased 1.3% and 2.8% in able-bodied subjects and amputees, respectively. These results suggest that a sampling rate between 400–500 Hz would be optimal for EMG acquisition in EMG pattern recognition based control of a multifunctional prosthesis.

Pattern recognition based forearm motion classification for patients with chronic hemiparesis

To make full use of electromyography (EMG) that contains rich information of muscular activities in active rehabilitation for motor hemiparetic patients, a couple of recent studies have explored the feasibility of applying pattern recognition technique to the classification of multiple motion classes for stroke survivors and reported some promising results. However, it still remains unclear if kinematics signals could also bring good motion classification performance, particularly for patients after traumatic brain damage. In this study, the kinematics signals was used for motion classification analysis in three stroke survivors and two patients after traumatic brain injury, and compared with EMG. The results showed that an average classification error of 7.9±6.8% for the affected arm over all subjects could be achieved with a linear classifier when they performed multiple fine movements, 7.9% lower than that when using EMG. With either kind of signals, the motor control ability of the affected arm degraded significantly in comparison to the intact side. The preliminary results suggested the great promise of kinematics information as well as the biological signals in detecting users conscious effort for robot-aided active rehabilitation.

New Control Strategies for Multifunctional Prostheses that Combine Electromyographic and Speech Signals

The control of multifunctional myoelectric prostheses is commonly limited due to the lack of sufficient electromyography (EMG) signals after amputation. With a goal of developing easy-to-use and flexibly controlled multifunctional prostheses, the authors propose two control strategies that fuse EMG and speech signals. In the first, speech signals switch the joint-mode, and EMG signals determine a motion class to actuate the target movement. In the second, speech signals select a motion class directly, and EMG signals actuated the movement. Experimental results showed that the proposed strategies could improve control performance and enhance the operational efficiency significantly, suggesting that signal fusion is a feasible way to effectively strengthen interactions between humans and machines.

Recognition of Combined Arm Motions Using Support Vector Machine

To investigate the classification performance of combined arm motions only using surface electromyography (EMG) signal, six different feature sets were adopted to match support vector machine (SVM) classifier respectively. Four unilateral transradial amputees participated in multi-channel surface EMG signal collection. The results show that the wavelet features outperforms others with average classification accuracy 98%±2% for intact arm and 89%±6% for amputated arm across all subjects. And the classification performance of intact arm motions was significantly better than that of amputated arm motions.

Improving the Robustness of Real-Time Myoelectric Pattern Recognition against Arm Position Changes in Transradial Amputees

Previous studies have showed that arm position variations would significantly degrade the classification performance of myoelectric pattern-recognition-based prosthetic control, and the cascade classifier (CC) and multiposition classifier (MPC) have been proposed to minimize such degradation in offline scenarios. However, it remains unknown whether these proposed approaches could also perform well in the clinical use of a multifunctional prosthesis control. In this study, the online effect of arm position variation on motion identification was evaluated by using a motion-test environment (MTE) developed to mimic the real-time control of myoelectric prostheses. The performance of different classifier configurations in reducing the impact of arm position variation was investigated using four real-time metrics based on dataset obtained from transradial amputees. The results of this study showed that, compared to the commonly used motion classification method, the CC and MPC configurations improved the real-time performance across seven classes of movements in five different arm positions (8.7% and 12.7% increments of motion completion rate, resp.). The results also indicated that high offline classification accuracy might not ensure good real-time performance under variable arm positions, which necessitated the investigation of the real-time control performance to gain proper insight on the clinical implementation of EMG-pattern-recognition-based controllers for limb amputees.

Using speech for mode selection in control of multifunctional myoelectric prostheses

Electromyogram (EMG) recorded from residual muscles of limbs is considered as suitable control information for motorized prostheses. However, in case of high-level amputations, the residual muscles are usually limited, which may not provide enough EMG for flexible control of myoelectric prostheses with multiple degrees of freedom of movements. Here, we proposed a control strategy, where the speech signals were used as additional information and combined with the EMG signals to realize more flexible control of multifunctional prostheses. By replacing the traditional “sequential mode-switching (joint-switching)”, the speech signals were used to select a mode (joint) of the prosthetic arm, and then the EMG signals were applied to determine a motion class involved in the selected joint and to execute the motion. Preliminary results from three able-bodied subjects and one transhumeral amputee demonstrated the proposed strategy could achieve a high mode-selection rate and enhance the operation efficiency, suggesting the strategy may improve the control performance of commercial myoelectric prostheses.

Reduction of the effect of arm position variation on real-time performance of motion classification

A couple of studies have been conducted with able-bodied subjects and/or arm amputees to investigate the impact of arm position changes in the practical use of a multifunctional myoelectric prosthesis. The classification accuracy calculated offline from electromyography (EMG) recordings was used as a performance metric in these studies, which is not a true measure of real-time control performance. In this study, the influence of arm position changes on the real-time performance of EMG pattern recognition (EMG-PR) control was quantitatively evaluated with four real-time metrics including motion response time, motion completion time, motion completion rate, and dynamic efficiency. Ten able-bodied subjects participated in the study and a cascade classifier built with both EMG and mechanomyogram (MMG) recordings was proposed to reduce the impact of arm position variation. The pilot results showed that arm position changes would substantially affect the real-time performance of EMG pattern-recognition based prosthesis control. Using a cascade classifier could significantly increase the average real-time completion rate (p-value<;0.01). This suggests that the proposed cascade classifier may have potential to reduce the influence of arm position variation on the real-time control performance of a prosthesis.