Abstract
System identification has been applied in diverse areas over past decades. In particular, parametric modelling approaches such as linear and nonlinear autoregressive with exogenous inputs models have been extensively used due to the transparency of the model structure. Model structure detection aims to identify parsimonious models by ranking a set of candidate model terms using some dependency metrics, which evaluate how the inclusion of an individual candidate model term affects the prediction of the desired output signal. The commonly used dependency metrics such as correlation function and mutual information may not work well in some cases, and therefore, there are always uncertainties in model parameter estimates. Thus, there is a need to introduce a new model structure detection scheme to deal with uncertainties in parameter estimation. In this work, a distance correlation metric is implemented and incorporated with a bagging method. The combination of these two implementations enhances the performance of existing forward selection approaches in that it provides the interpretability of nonlinear dependency and an insightful uncertainty analysis for model parameter estimates. The new scheme is referred as bagging forward orthogonal regression using distance correlation (BFOR-dCor) algorithm. A comparison of the performance of the new BFOR-dCor algorithm with benchmark algorithms using metrics like error reduction ratio, mutual information, or the Reversible Jump Markov Chain Monte Carlo method has been carried out in dealing with several numerical case studies. For ease of analysis, the discussion is restricted to polynomial models that can be expressed in a linear-in-the-parameters form.
Similar content being viewed by others
References
Billings, S.A.: Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains. Wiley, London (2013)
Pope, K.J., Rayner, P.J.W.: Non-linear system identification using Bayesian inference. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-94, 1994 vol. IV, pp. 457–460 (1994)
Haber, R., Unbehauen, H.: Structure identification of nonlinear dynamic systems–a survey on input/output approaches. Automatica 26(4), 651–677 (1990)
Aguirre, L.A., Letellier, C.: Modeling nonlinear dynamics and chaos: a review. Mathe. Prob. Eng. 2009, 35 (2009). doi:10.1155/2009/238960
Billings, S.A., Coca, D.: Identification of NARMAX and related models. tech. rep., Department of Automatic Control and Systems Engineering, The University of Sheffield, UK, (2001)
Guo, L.Z., Billings, S.A., Zhu, D.Q.: An extended orthogonal forward regression algorithm for system identification using entropy. Int. J. Control 81(4), 690–699 (2008)
Koller, D., Sahami, M.: Toward optimal feature selection. In: In 13th International Conference on Machine Learning (1995)
Billings, S.A., Wei, H.-L.: Sparse model identification using a forward orthogonal regression algorithm aided by mutual information. IEEE Trans. Neural Netw. 18(1), 306–310 (2007)
Wei, H.-L., Billings, S.A.: Model structure selection using an integrated forward orthogonal search algorithm assisted by squared correlation and mutual information. Int. J. Model. Identif. Control 3(4), 341–356 (2008)
Wang, S., Wei, H.-L., Coca, D., Billings, S.A.: Model term selection for spatio-temporal system identification using mutual information. Int. J. Syst. Sci. 44(2), 223–231 (2013)
Han, M., Liu, X.: Forward Feature Selection Based on Approximate Markov Blanket. In: Advances in Neural Networks-ISNN 2012, pp. 64–72, Springer, Berlin (2012)
Baldacchino, T., Anderson, S.R., Kadirkamanathan, V.: Computational system identification for Bayesian NARMAX modelling. Automatica 49, 2641–2651 (2013)
Ninness, B., Brinsmead, T.: A Bayesian Approach to System Identification using Markov Chain Methods. Tech. Rep. EE02009, University of Newcastle, Australia, NSW (2003)
Székely, G.J., Rizzo, M.L., Bakirov, N.K.: Measuring and testing dependence by correlation of distances. Annals Stat. 35(6), 2769–2794 (2007)
Székely, G.J., Rizzo, M.L.: Energy statistics: a class of statistics based on distances. J. Stat. Plan. Inf. 143(8), 1249–1272 (2013)
Chen, S., Billings, S., Luo, W.: Orthogonal least squares methods and their application to non-linear system identification. Int. J. Control 50(5), 1873–1896 (1989)
Söderström, T., Stoica, P.: System Identification. Prentice Hall, New Jersey (1989)
Wei, H.-L., Balikhin, M.A., Billings, S.A.: Nonlinear time-varying system identification using the NARMAX model and multiresolution wavelet expansions. Tech. Rep. 829, The University of Sheffield, United Kingdom (2003)
Wei, H.-L., Billings, S.A., Liu, J.: Term and variable selection for non-linear system identification. Int. J. Control 77(1), 86–110 (2004)
Wei, H.-L., Billings, S.A., Zhao, Y., Guo, L.: Lattice dynamical wavelet neural networks implemented using particle swarm optimization for spatio-temporal system identification. IEEE Trans. Neural Netw. 20(1), 181–185 (2009)
Rashid, M.T., Frasca, M., Ali, A.A., Ali, R.S., Fortuna, L., Xibilia, M.G.: Nonlinear model identification for Artemia population motion. Nonlinear Dyn. 69(4), 2237–2243 (2012)
Haynes, B.R., Billings, S.A.: Global analysis and model validation in nonlinear system identification. Nonlinear Dyn. 5(1), 93–130 (1994)
Billings, S.A., Wei, H.-L.: An adaptive orthogonal search algorithm for model subset selection and non-linear system identification. Int. J. Control 81(5), 714–724 (2008)
Aguirre, L.A., Jácôme, C.: Cluster analysis of NARMAX models for signal-dependent systems. In: IEE Proceedings Control Theory and Applications, vol. 145, pp. 409–414, IET, July (1998)
Feil, B., Abonyi, J., Szeifert, F.: Model order selection of nonlinear input-output models–a clustering based approach. J. Process Control 14(6), 593–602 (2004)
Kukreja, S.L., Lofberg, J., Brenner, M.J.: A least absolute shrinkage and selection operator (LASSO) for nonlinear system identification. Syst. Identif. 14, 814–819 (2006)
Qin, P., Nishii, R., Yang, Z.-J.: Selection of NARX models estimated using weighted least squares method via GIC-based method and l 1-norm regularization methods. Nonlinear Dyn. 70(3), 1831–1846 (2012)
Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. R. Stat. Soc. B 67(2), 301–320 (2005). (Statistical Methodology)
Hong, X., Chen, S.: An elastic net orthogonal forward regression algorithm. In: 16th IFAC Symposium on System Identification, pp. 1814–1819, July (2012)
Sette, S., Boullart, L.: Genetic programming: principles and applications. Eng. Appl. Artif. Intell. 14(6), 727–736 (2001)
Madár, J., Abonyi, J., Szeifert, F.: Genetic programming for the identification of nonlinear input-output models. Ind. Eng. Chem. Res. 44(9), 3178–3186 (2005)
Martins, S.A.M., Nepomuceno, E.G., Barroso, M.F.S.: Improved structure detection for polynomial NARX models using a multiobjective error reduction ratio. J. Control Autom. Electr. Syst. 24(6), 764–772 (2013)
Baldacchino, T., Anderson, S.R., Kadirkamanathan, V.: Structure detection and parameter estimation for NARX models in a unified EM framework. Automatica 48(5), 857–865 (2012)
Teixeira, B.O., Aguirre, L.A.: Using uncertain prior knowledge to improve identified nonlinear dynamic models. J. Process Control 21(1), 82–91 (2011)
Billings, S.A., Voon, W.S.F.: Correlation based model validity tests for nonlinear models. Tech. Rep. 285, The University of Sheffield, United Kingdom, October (1985)
Billings, S.A., Wei, H.-L.: The wavelet-NARMAX representation: a hybrid model structure combining polynomial models with multiresolution wavelet decompositions. Int. J. Syst. Sci. 36(3), 137–152 (2005)
Guo, Y., Guo, L., Billings, S., Wei, H.-L.: An iterative orthogonal forward regression algorithm. Int. J. Syst. Sci. 46(5), 776–789 (2015)
Billings, S.A., Chen, S., Backhouse, R.J.: The identification of linear and non-linear models of a turbocharged automotive diesel engine. Mech. Syst. Signal Process. 3(2), 123–142 (1989)
Dietterich, T.G.: Machine Learning for Sequential Data: A Review. In: Structural, Syntactic, and Statistical Pattern Recognition, pp. 15–30, Springer, Berlin (2002)
Efron, B.: Computers and the theory of statistics: thinking the unthinkable. SIAM Rev. 21, 460–480 (1979)
Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap, vol. 57 of Monographs on Statistics and Applied Probability. Chapman & Hall, London (1993)
Davison, A.C.: Bootstrap Methods and their Application. Cambridge University Press, Cambridge (1997)
Kukreja, S.L., Galiana, H., Kearney, R.: Structure detection of NARMAX models using bootstrap methods. In: Proceedings of the 38th IEEE Conference on Decision and Control, 1999. vol. 1, pp. 1071–1076 (1999)
Kukreja,: A suboptimal bootstrap method for structure detection of NARMAX models. Tech. Rep. LiTH-ISY-R-2452, Linköpings universitet, Linköping, Sweden (2002)
Wei, H.-L., Billings, S.A.: Improved parameter estimates for non-linear dynamical models using a bootstrap method. Int. J. Control 82(11), 1991–2001 (2009)
Breiman, L.: Bagging predictors. Tech. Rep. 421, University of California, Berkeley, California, USA, September (1994)
Hyndman, R.J., Athanasopoulos, G.: Forecasting: Principles and Practice. OTexts (2014). https://www.otexts.org/book/fpp
James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning with Application in R, vol. 103 of Springer Texts in Statistics. Springer, Berlin (2013)
Sunspot Data, (2003)
Kampstra, P.: Beanplot: A boxplot alternative for visual comparison of distributions. J. Stati. Softw. 28, 1–9 (2008)
Lin, H., Varsik, J., Zirin, H.: High-resolution observations of the polar magnetic fields of the Sun. Solar Phys. 155(2), 243–256 (1994)
Billings, S.A., Tao, Q.H.: Model validity tests for non-linear signal processing applications. Int. J. Control 54(1), 157–194 (1991)
Acknowledgments
The authors acknowledge the support for J. R. Ayala Solares from a University of Sheffield Full Departmental Fee Scholarship and a scholarship from the Mexican National Council of Science and Technology (CONACYT). The authors also gratefully acknowledge that this work was partly supported by EPSRC.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ayala Solares, J.R., Wei, HL. Nonlinear model structure detection and parameter estimation using a novel bagging method based on distance correlation metric. Nonlinear Dyn 82, 201–215 (2015). https://doi.org/10.1007/s11071-015-2149-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11071-015-2149-3