Surface EMG Pattern Recognition for Real-Time Control of a Wrist ExoskeletonBy Khokhar, Zeeshan O.; Xiao, Zhen G.; Menon, Carlo; BioMedical Engineering OnLine, Volume 9, Number 41
Publication Date: 2010
Paper presents the use of surface electromyography (sEMG) pattern recognition to estimate the torque applied by a human wrist and its real time implementation to control a wrist exoskeleton. The feasibility of the use of sEMG signals to control wearable devices assisting persons with reduced upper limb muscle strength was explored in light of these signals having been successfully implemented in the control of prosthetic hands for amputees. The orthotic used was a two degree of freedom wrist exoskeleton prototype (WEP) specifically developed for this study. Both sEMG data from 4 muscles of the forearm and wrist torque were collected from 8 volunteers by using a custom made testing rig. The features that were extracted from the sEMG signals included root mean square (rms) EMG amplitude, autoregressive (AR) model coefficients, and waveform length. Support Vector Machines (SVM) technique was employed to extract classes of different force intensity from the sEMG signals. After assessing the offline performance of the used classification technique, the WEP was used to validate in real time the proposed classification theme. Data gathered from the volunteers were divided into two sets, one with 19, and one with 13 classes. Each data set was further divided into training and testing data. The average testing accuracy in the 19 class set was about 88 percent, whereas the average accuracy in the 13 class set reached about 96 percent. Classification and control algorithm implemented in the WEP was executed in less than 125 milliseconds.
Published by: BioMed Central Ltd (Website:http://www.biomedcentral.com)
Link to text: http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2936372/?tool=pmcentrez