Affiliations 

  • 1 Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. marufibitoye@yahoo.com
  • 2 Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. azah.hamzaid@um.edu.my
  • 3 Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. khairi@um.edu.my
  • 4 Department of Rehabilitation Medicine, Faculty of Medicine, University of Malaya, Kuala Lumpur 50603, Malaysia. nazirah@ummc.edu.my
  • 5 Computer Science Department, College of Computer Science & Information Technology, University of Dammam, Dammam 34212, Saudi Arabia. oluolatunji.aadam@gmail.com
  • 6 Department of Biomedical Engineering, Faculty of Engineering, University of Malaya, Kuala Lumpur 50603, Malaysia. glen.davis@sydney.edu.au
Sensors (Basel), 2016 Jul 19;16(7).
PMID: 27447638 DOI: 10.3390/s16071115

Abstract

The difficulty of real-time muscle force or joint torque estimation during neuromuscular electrical stimulation (NMES) in physical therapy and exercise science has motivated recent research interest in torque estimation from other muscle characteristics. This study investigated the accuracy of a computational intelligence technique for estimating NMES-evoked knee extension torque based on the Mechanomyographic signals (MMG) of contracting muscles that were recorded from eight healthy males. Simulation of the knee torque was modelled via Support Vector Regression (SVR) due to its good generalization ability in related fields. Inputs to the proposed model were MMG amplitude characteristics, the level of electrical stimulation or contraction intensity, and knee angle. Gaussian kernel function, as well as its optimal parameters were identified with the best performance measure and were applied as the SVR kernel function to build an effective knee torque estimation model. To train and test the model, the data were partitioned into training (70%) and testing (30%) subsets, respectively. The SVR estimation accuracy, based on the coefficient of determination (R²) between the actual and the estimated torque values was up to 94% and 89% during the training and testing cases, with root mean square errors (RMSE) of 9.48 and 12.95, respectively. The knee torque estimations obtained using SVR modelling agreed well with the experimental data from an isokinetic dynamometer. These findings support the realization of a closed-loop NMES system for functional tasks using MMG as the feedback signal source and an SVR algorithm for joint torque estimation.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.