Optimizing Heart Rate Regulation for Safe Exercise

Safe exercise protocols are critical for effective rehabilitation programs. This paper aims to develop a novel control strategy for an automated treadmill system to reduce the danger of injury during cardiac rehabilitation. We have developed a control-oriented nonparametric Hammerstein model for the control of heart rate during exercises by using support vector regression and correlation analysis. Based on this nonparametric model, a model predictive controller has been built. In order to guarantee the safety of treadmill exercise during rehabilitation, this new automated treadmill system is capable of optimizing system performance over predefined ranges of speed and acceleration. The effectiveness of the proposed approach was demonstrated with six subjects by having their heart rate track successfully a predetermined heart rate.

[1]  Y L Chen,et al.  Effect of combined dynamic and static workload on heart rate recovery cost. , 1998, Ergonomics.

[2]  Howard J. Chizeck,et al.  Design and Evaluation of a Digital Closed-Loop Controller for the Regulation of Muscle Force by Recruitment Modulation , 1985, IEEE Transactions on Biomedical Engineering.

[3]  Er-Wei Bai,et al.  Decoupling the linear and nonlinear parts in Hammerstein model identification , 2004, Autom..

[4]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[5]  R. Kearney,et al.  Nonparametric Block-Structured Modeling of Lung Tissue Strip Mechanics , 1998, Annals of Biomedical Engineering.

[6]  Andrey V. Savkin,et al.  Oxygen Uptake Estimation in Humans During Exercise Using a Hammerstein Model , 2007, Annals of Biomedical Engineering.

[7]  Manfred Morari,et al.  Model predictive control: Theory and practice - A survey , 1989, Autom..

[8]  B. Chang,et al.  Treadmill Injuries to the Upper Extremity in Pediatric Patients , 2001, Annals of plastic surgery.

[9]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[10]  John Shawe-Taylor,et al.  Covering numbers for support vector machines , 1999, COLT '99.

[11]  R. Cleland,et al.  WEIGHT-LOSS ADVERTISING: An Analysis of Current Trends , 2002 .

[12]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[13]  P. Ades.  Cardiac rehabilitation and secondary prevention of coronary heart disease. , 2001, The New England journal of medicine.

[14]  Ivan Kneppo,et al.  An iterative method for the identification of nonlinear systems , 1969, Kybernetika.

[15]  A. Liuzzi,et al.  A simple tool to predict exercise capacity of obese patients with ischaemic heart disease , 2005, Heart.

[16]  V Brodan,et al.  An analog model of pulse rate during physical load and recovery. , 1971, Physiologia Bohemoslovaca.

[17]  L. A. Bernotas,et al.  A Discrete-Time Model of Electrcally Stimulated Muscle , 1986, IEEE Transactions on Biomedical Engineering.

[18]  John Anthony Rossiter.  Model-Based Predictive Control , 2003 .

[19]  M. Lauer,et al.  Cardiac rehabilitation and secondary prevention of coronary heart disease: an American Heart Association scientific statement from the Council on Clinical Cardiology (Subcommittee on Exercise, Cardiac Rehabilitation, and Prevention) and the Council on Nutrition, Physical Activity, and Metabolism (Su , 2005, Circulation.

[20]  Michel Kinnaert,et al.  Diagnosis and Fault-Tolerant Control , 2004, IEEE Transactions on Automatic Control.

[21]  Andrey V. Savkin,et al.  Nonlinear Modeling and Control of Human Heart Rate Response During Exercise With Various Work Load Intensities , 2008, IEEE Transactions on Biomedical Engineering.

[22]  Matthew A. Franchek,et al.  Robust SISO H 8 controller design for nonlinear systems , 2005 .

[23]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[24]  Stanley H. Johnson,et al.  Use of Hammerstein Models in Identification of Nonlinear Systems , 1991 .

[25]  M. Munih,et al.  Investigation of the Hammerstein hypothesis in the modeling of electrically stimulated muscle , 1998, IEEE Transactions on Biomedical Engineering.

[26]  Johan A. K. Suykens,et al.  Identification of MIMO Hammerstein models using least squares support vector machines , 2005, Autom..

[27]  Lu Wang,et al.  Identification and Control for Heart Rate Regulation During Treadmill Exercise , 2007, IEEE Transactions on Biomedical Engineering.

[28]  Wlodzimierz Greblicki,et al.  Stochastic approximation in nonparametric identification of Hammerstein systems , 2002, IEEE Trans. Autom. Control..

[29]  W. D. T. Davies,et al.  System identification for self-adaptive control , 1970 .

[30]  Lu Wang,et al.  Nonparametric Hammerstein Model Based Model Predictive Control for Heart Rate Regulation , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[31]  Richard Casaburi,et al.  Pulmonary Rehabilitation: Joint ACCP/AACVPR Evidence-Based Clinical Practice Guidelines. , 2007, Chest.