Abstract
In this paper, two contributions are presented. Firstly, a novel variant of the Kalman filter is developed and used to improve the tracking performance of the extended kernel recursive least squares algorithm (Ex-KRLS). Without resorting to the Riccati equation, the proposed formulation of the Kalman filter relies on principles of optimization and convex duality to obtain a stable quadratic form. It allows for performance and stability efficiency by minimizing the estimation error with the manipulation of a single scalar variable. Secondly, the proposed Kalman filter formulation is embedded into the Ex-KRLS-KF algorithm, an extension of the Ex-KRLS, to further improve its tracking performance. For this purpose, the state model of the proposed Ex-KRLS-KF variant is constructed in the original state space, while the hidden state is then estimated using the proposed Kalman filter formulation. The standard KRLS algorithm learns the measurement model used in hidden state estimation. We show through a comprehensive set of computer experiments that the proposed hybrid algorithm has more flexible state and noise models than competing alternative algorithms. We evaluate the proposed algorithm in two benchmarking tasks (nonlinear Rayleigh multipath channel tracking and Lorenz system modeling) and compare its performance with those provided by the state-of-the-art algorithms.
Similar content being viewed by others
Data Availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.
Notes
\(\left[ ({\mathbf {C}}{\mathbf {A}})^{T} \right] ^{+}= \left[ ({\mathbf {C}}{\mathbf {A}})({\mathbf {C}}{\mathbf {A}})^T\right] ^{-1}({\mathbf {C}}{\mathbf {A}})\).
References
I. Arasaratnamand, S. Haykin, Cubature Kalman filters. IEEE Trans. Signal Process. 54(6), 1254–1269 (2009)
A. Berlinet, C. Thomas-Agnan, Reproducing Kernel Hilbert Spaces in Probability and Statistics (Springer, Berlin, 2004)
J.C. Doyle, Guaranteed margins for LQG regulators. IEEE Trans. Autom. Control 23(4), 756–757 (1978)
Y. Engel, S. Mannor, R. Meir, The kernel recursive least-squares algorithm. IEEE Trans. Signal Process. 52(8), 2275–2285 (2004)
M.S. Grewal, P.A. Angus, Kalman Filtering: Theory and Practice with MATLAB, 4th edn. (John, New York, 2014)
S. Haykin, Kalman Filtering and Neural Networks, 1st edn. (Wiley, New York, 2001)
T. Hofmann, B. Scholkopf, A.J. Smola, Kernel methods in machine learning. Ann. Stat. 36(3), 1171–1220 (2008)
Y. Huang, Y. Zhang, P. Shi, Z. Wu, J. Qian, J.A. Chambers, Robust Kalman filters based on Gaussian scale mixture distributions with application to target tracking. IEEE Trans. Syst. Man Cybern. Syst. 49(10), 2082–2096 (2019)
Y. Huang, Y. Zhang, Y. Zhao, J.A. Chambers, A novel robust Gaussian-student t mixture distribution based Kalman filter. IEEE Trans. Signal Process. 67(13), 3606–3620 (2019)
Y. Huang, Y. Zhang, Y. Zhao, L. Mihaylova, J.A. Chambers, A novel robust Rauch–Tung–Striebel smoother based on slash and generalized hyperbolic skew Student’s t-distributions, in Proceedings of the 21st International Conference on Information Fusion (2018). https://doi.org/10.23919/ICIF.2018.8455256
S. Julier, J. Uhlmann, A new extension of the Kalman filter to nonlinear systems, in Proceedings of the SPIE 3068, Signal Processing, Sensor Fusion, and Target Recognition VI (1997). https://doi.org/10.1117/12.280797
R.E. Kalman, A new approach to linear filtering and prediction problems. J. Basic Eng. 82(1), 35–45 (1960)
A.J. Laub, Invariant subspace methods for the numerical solution of Riccati equations, in The Riccati Equation, ed. by S. Bittanti, A.J. Laub, J. Willems (Springer, Berlin, 1991), pp. 163–196
W. Liu, I. Park, Y. Wang, J.C. Principe, Extended kernel recursive least squares algorithm. IEEE Trans. Signal Process. 57(10), 3801–3814 (2009)
E.N. Lorenz, Deterministic nonperiodic flow. J. Atmos. Sci. 20, 130–141 (1963)
M.J.D. Powell, On the global convergence of trust region algorithms for unconstrained minimization. Math. Progr. 29(3), 297–303 (1984)
L. Ralaivola, F. d’Alché-Buc, Nonlinear time series filtering, smoothing and learning using the kernel Kalman filter, in Proceedings of the 2005 IEEE International Joint Conference on Neural Networks (IJCNN’2005), pp. 1449–1454 (2005)
J.D.A. Santos, G.A. Barreto, An outlier-robust kernel RLS algorithm for nonlinear system identification. Nonlinear Dyn. 90(3), 1707–1726 (2017)
A. Sayed, Fundamentals of Adaptive Filtering (Wiley, New York, 2003)
H.W. Sorenson, Least-squares estimation: from Gauss to Kalman. IEEE Spectr 7(7), 63–68 (1970)
E. Todorov, Optimal control theory, in Bayesian Brain: Probabilistic Approaches to Neural Coding, ed. by K. Doya, S. Ishii, A. Pouget, R.P.N. Rao (The MIT Press, Cambridge, 2006), pp. 269–298
E. Todorov, General duality between optimal control and estimation, in Proceedings of the 47th IEEE Conference on Decision and Control, pp. 4286–4292 (2008)
W. Tucker, A rigorous ODE solver and Smale’s 14th problem. Found. Comput. Math. 2(1), 53–117 (2002)
L.J. Urrea, A confidence region method for unconstrained minimization without derivatives. Master’s Dissertation (in Portuguese), University of Campinas (Unicamp), Brazil (2008)
P. Zhu, B. Chen, J.C. Principe, Extended Kalman filter using a kernel recursive least squares observer, in Proceedings of the 2011 IEEE International Joint Conference on Neural Networks (IJCNN’2011), pp. 1402–1408 (2011)
P. Zhu, B. Chen, J.C. Principe, A novel extended kernel recursive least squares algorithm. Neural Netw. 32, 349–357 (2012)
Acknowledgements
This study was financed by the following Brazilian research funding agencies: CAPES (Finance Code 001) and CNPq (Grant No. 309379/2019-9). We also would like to thank the support of from the Laboratory of Technological Innovation (LIT) of the Federal Institute of Ceará (IFCE). We also would like to thank the reviewers for the very pertinent and relevant comments.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest regarding the publication of this paper.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Façanha, T.S., Barreto, G.A. & Costa Filho, J.T. A Novel Kalman Filter Formulation for Improving Tracking Performance of the Extended Kernel RLS. Circuits Syst Signal Process 40, 1397–1419 (2021). https://doi.org/10.1007/s00034-020-01533-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-020-01533-4