Dynamic characteristics of oxygen consumption

BackgroundPrevious studies have indicated that oxygen uptake ($$VO_2$$VO2) is one of the most accurate indices for assessing the cardiorespiratory response to exercise. In most existing studies, the response of $$VO_2$$VO2 is often roughly modelled as a first-order system due to the inadequate stimulation and low signal to noise ratio. To overcome this difficulty, this paper proposes a novel nonparametric kernel-based method for the dynamic modelling of $$VO_2$$VO2 response to provide a more robust estimation.MethodsTwenty healthy non-athlete participants conducted treadmill exercises with monotonous stimulation (e.g., single step function as input). During the exercise, $$VO_2$$VO2 was measured and recorded by a popular portable gas analyser ($$K4b^2$$K4b2, COSMED). Based on the recorded data, a kernel-based estimation method was proposed to perform the nonparametric modelling of $$VO_2$$VO2. For the proposed method, a properly selected kernel can represent the prior modelling information to reduce the dependence of comprehensive stimulations. Furthermore, due to the special elastic net formed by $$\mathcal {L}_1$$L1 norm and kernelised $$\mathcal {L}_2$$L2 norm, the estimations are smooth and concise. Additionally, the finite impulse response based nonparametric model which estimated by the proposed method can optimally select the order and fit better in terms of goodness-of-fit comparing to classical methods.ResultsSeveral kernels were introduced for the kernel-based $$VO_2$$VO2 modelling method. The results clearly indicated that the stable spline (SS) kernel has the best performance for $$VO_2$$VO2 modelling. Particularly, based on the experimental data from 20 participants, the estimated response from the proposed method with SS kernel was significantly better than the results from the benchmark method [i.e., prediction error method (PEM)] ($$76.0\pm 5.72$$76.0±5.72 vs $$71.4\pm 7.24\%$$71.4±7.24%).ConclusionsThe proposed nonparametric modelling method is an effective method for the estimation of the impulse response of VO2—Speed system. Furthermore, the identified average nonparametric model method can dynamically predict $$VO_2$$VO2 response with acceptable accuracy during treadmill exercise.

[1]  H. Bozdogan.  Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions , 1987 .

[2]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[3]  J. Holloszy,et al.  Faster adjustment to and recovery from submaximal exercise in the trained state. , 1980, Journal of applied physiology: respiratory, environmental and exercise physiology.

[4]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[5]  Thomas W. Parks,et al.  New results in the design of digital interpolators" ieee trans , 1975 .

[6]  A. Nevill,et al.  Modelling Maximum Oxygen Uptake-a Case-study in Non-linear Regression Model Formulation and Comparison , 1994 .

[7]  Henrik Ohlsson,et al.  On the estimation of transfer functions, regularizations and Gaussian processes - Revisited , 2012, Autom..

[8]  Giuseppe De Nicolao,et al.  A new kernel-based approach for linear system identification , 2010, Autom..

[9]  Andrew M Jones,et al.  Oxygen uptake kinetics. , 2012, Comprehensive Physiology.

[10]  S. Ward,et al.  Parameters of ventilatory and gas exchange dynamics during exercise. , 1982, Journal of applied physiology: respiratory, environmental and exercise physiology.

[11]  Tianshi Chen,et al.  On kernel design for regularized LTI system identification , 2016, Autom..

[12]  Bruno Grassi,et al.  Mechanisms responsible for the acceleration of pulmonary V̇O2 on-kinetics in humans after prolonged endurance training. , 2014, American journal of physiology. Regulatory, integrative and comparative physiology.

[13]  Ge Tancred,et al.  Guidelines for Exercise Testing and Prescription , 1991 .

[14]  Stephen P. Boyd,et al.  An Interior-Point Method for Large-Scale $\ell_1$-Regularized Least Squares , 2007, IEEE Journal of Selected Topics in Signal Processing.

[15]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[16]  H T Milhorn,et al.  Dynamic and steady-state respiratory responses to bicycle exercise. , 1977, Journal of applied physiology: respiratory, environmental and exercise physiology.

[17]  B. Celler,et al.  An equivalent circuit model for onset and offset exercise response , 2014, Biomedical engineering online.

[18]  Lennart Ljung,et al.  Implementation of algorithms for tuning parameters in regularized least squares problems in system identification , 2013, Autom..

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

[20]  Lennart Ljung,et al.  Kernel methods in system identification, machine learning and function estimation: A survey , 2014, Autom..

[21]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[22]  N. C. Sharp,et al.  Guidelines for Exercise Testing and Prescription , 1993 .

[23]  H. Rossiter,et al.  Exercise: Kinetic considerations for gas exchange. , 2010, Comprehensive Physiology.

[24]  D. Abe,et al.  Effects of load carriage, load position, and walking speed on energy cost of walking. , 2004, Applied ergonomics.

[25]  Arthur E. Hoerl,et al.  Ridge Regression: Biased Estimation for Nonorthogonal Problems , 2000, Technometrics.

[26]  C. H. Wyndham,et al.  An equation for prediction of energy expenditure of walking and running. , 1973, Journal of applied physiology.

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

[28]  Yi Zhang,et al.  Modelling and regulating of cardio-respiratory response for the enhancement of interval training , 2014, Biomedical engineering online.