Surface EMG Pattern Recognition for Real-Time Control of a Wrist Exoskeleton

Peer reviewed: 
Yes, item is peer reviewed.
Scholarly level: 
Faculty/Staff
Final version published as: 

Khokhar et al. BioMedical Engineering OnLine 2010, 9:41
http://www.biomedical-engineering-online.com/content/9/1/41

Date created: 
2010
Abstract: 

Background: Surface electromyography (sEMG) signals have been used in numerousstudies for the classification of hand gestures and movements and successfullyimplemented in the position control of different prosthetic hands for amputees.sEMG could also potentially be used for controlling wearable devices which couldassist persons with reduced muscle mass, such as those suffering from sarcopenia.While using sEMG for position control, estimation of the intended torque of the usercould also provide sufficient information for an effective force control of the handprosthesis or assistive device. This paper presents the use of pattern recognition toestimate the torque applied by a human wrist and its real-time implementation tocontrol a novel two degree of freedom wrist exoskeleton prototype (WEP), whichwas specifically developed for this work.Methods: Both sEMG data from four muscles of the forearm and wrist torque werecollected from eight volunteers by using a custom-made testing rig. The featuresthat were extracted from the sEMG signals included root mean square (rms) EMGamplitude, autoregressive (AR) model coefficients and waveform length. SupportVector Machines (SVM) was employed to extract classes of different force intensityfrom the sEMG signals. After assessing the off-line performance of the usedclassification technique, the WEP was used to validate in real-time the proposedclassification scheme.Results: The data gathered from the volunteers were divided into two sets, one withnineteen classes and the second with thirteen classes. Each set of data was furtherdivided into training and testing data. It was observed that the average testingaccuracy in the case of nineteen classes was about 88% whereas the averageaccuracy in the case of thirteen classes reached about 96%. Classification and controlalgorithm implemented in the WEP was executed in less than 125 ms.Conclusions: The results of this study showed that classification of EMG signals byseparating different levels of torque is possible for wrist motion and the use of onlyfour EMG channels is suitable. The study also showed that SVM classificationtechnique is suitable for real-time classification of sEMG signals and can be effectivelyimplemented for controlling an exoskeleton device for assisting the wrist.

Language: 
English
Document type: 
Article
Rights: 
You are free to copy, distribute and transmit this work under the following conditions: You must give attribution to the work (but not in any way that suggests that the author endorses you or your use of the work); You may not use this work for commercial purposes; You may not alter, transform, or build upon this work. Any further uses require the permission of the rights holder (or author if no rights holder is listed). These rights are based on the Creative Commons Attribution-NonCommercial-NoDerivatives License.
Statistics: