Title: Nonlinear modelling and control for heart rate response to exercise

Authors: Y. Zhang; W. Chen; S.W. Su; B. Celler

Addresses: Centre for Health Technologies, Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia ' Department of Automation, Shanghai Jiao Tong University, Shanghai, China ' Centre for Health Technologies, Faculty of Engineering and Information Technology, University of Technology, Sydney, Australia; Human Performance Group, Biomedical Systems Lab, School of Electrical Engineering and Telecommunications, University of New South Wales, UNSW Sydney NSW 2052 Australia ' Human Performance Group, Biomedical Systems Lab, School of Electrical Engineering and Telecommunications, University of New South Wales, UNSW, Sydney, NSW 2052, Australia

Abstract: In order to accurately regulate cardiovascular response to exercise for individual exerciser, this study proposes a modelling and control integrated approach based on ε-insensitive Support Vector Regression (SVR) and switching control strategy. Firstly, a control oriented modelling approach is proposed to depict nonlinear behaviours of cardiovascular response at both onset and offset of treadmill exercises by using support vector machine regression. Then, based on the established nonlinear time-variant model, a novel switching Model Predictive Control (MPC) algorithm has been proposed for the optimisation of exercise efforts. The designed controller can take into account both coefficient drifting and parameter jump by embedding the identified model coefficient into the optimiser and adopting switching strategy during the transfer between onset and offset of exercises. The effectiveness of the proposed modelling and control approach was shown from the regulation of dynamical heart rate response to exercise through simulation using MATLAB.

Keywords: control oriented modelling; support vector machine; SVM regression; model predictive control; switching MPC; dynamic matrix control; heart rate response; nonlinear modelling; nonliner control; cardiovascular response; exercise responses; treadmill exercises; controller design.

DOI: 10.1504/IJBRA.2012.049624

International Journal of Bioinformatics Research and Applications, 2012 Vol.8 No.5/6, pp.397 - 416

Published online: 10 Oct 2012 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article