Model-Based Robust Filtering and Experimental Design for Stochastic Differential Equation Systems

We derive robust linear filtering and experimental design for systems governed by stochastic differential equations (SDEs) under model uncertainty. Given a model of signal and observation processes, an optimal linear filter is found by solving the Wiener-Hopf equation; with model uncertainty, it is desirable to derive a corresponding robust filter. This article assumes that the physical process is modeled via a SDE system with unknown parameters; the signals are degraded by blurring and additive noise. Due to time-dependent stochasticity in SDE systems, the system is nonstationary; and the resulting Wiener-Hopf equation is difficult to solve in closed form. Hence, we discretize the problem to obtain a matrix system to carry out the overall procedure. We further derive an intrinsically Bayesian robust (IBR) linear filter together with an optimal experimental design framework to determine the importance of SDE parameter(s). We apply the theory to an SDE-based pharmacokinetic two-compartment model to estimate drug concentration levels.

[1]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[2]  Edward R. Dougherty,et al.  Quantifying the Objective Cost of Uncertainty in Complex Dynamical Systems , 2013, IEEE Transactions on Signal Processing.

[3]  Warren B. Powell,et al.  A Knowledge-Gradient Policy for Sequential Information Collection , 2008, SIAM J. Control. Optim..

[4]  Edward R. Dougherty,et al.  Experimental Design via Generalized Mean Objective Cost of Uncertainty , 2018, IEEE Access.

[5]  D. Williams.  STOCHASTIC DIFFERENTIAL EQUATIONS: THEORY AND APPLICATIONS , 1976 .

[6]  Ali H. Sayed,et al.  A framework for state-space estimation with uncertain models , 2001, IEEE Trans. Autom. Control..

[7]  Edward R. Dougherty,et al.  Optimal Objective-Based Experimental Design for Uncertain Dynamical Gene Networks with Experimental Error , 2018, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[8]  K. Vastola,et al.  Robust Wiener-Kolmogorov theory , 1984, IEEE Trans. Inf. Theory.

[9]  Wook Hyun Kwon,et al.  FIR filters and recursive forms for discrete-time state-space models , 1987, Autom..

[10]  Byung-Jun Yoon,et al.  Efficient experimental design for uncertainty reduction in gene regulatory networks , 2015, BMC Bioinformatics.

[11]  Edward R. Dougherty,et al.  Optimal experimental design in the context of canonical expansions , 2017, IET Signal Process..

[12]  Yonina C. Eldar.  Minimax estimation of deterministic parameters in linear models with a random model matrix , 2006, IEEE Transactions on Signal Processing.

[13]  Yonina C. Eldar,et al.  Minimax MSE-ratio estimation with signal covariance uncertainties , 2005, IEEE Transactions on Signal Processing.

[14]  Edward R. Dougherty,et al.  Incorporating prior knowledge induced from stochastic differential equations in the classification of stochastic observations , 2016, EURASIP J. Bioinform. Syst. Biol..

[15]  Yuriy S. Shmaliy,et al.  Linear Optimal FIR Estimation of Discrete Time-Invariant State-Space Models , 2010, IEEE Transactions on Signal Processing.

[16]  Liangjian Hu,et al.  A Stochastic Differential Equation SIS Epidemic Model , 2011, SIAM J. Appl. Math..

[17]  Yasuo Sugiyama,et al.  An algorithm for solving discrete-time Wiener-Hopf equations based upon Euclid's algorithm , 1986, IEEE Trans. Inf. Theory.

[18]  Edward R. Dougherty,et al.  Bayesian Regression With Network Prior: Optimal Bayesian Filtering Perspective , 2016, IEEE Transactions on Signal Processing.

[19]  Edward R. Dougherty,et al.  Intrinsically Optimal Bayesian Robust Filtering , 2014, IEEE Transactions on Signal Processing.

[20]  Edward R. Dougherty,et al.  Design and Analysis of Robust Binary Filters in the Context of a Prior Distribution for the States of Nature , 2004, Journal of Mathematical Imaging and Vision.

[21]  Michael Prange,et al.  Toward efficient computation of the expected relative entropy for nonlinear experimental design , 2012 .

[22]  Edward R. Dougherty,et al.  Optimal classifiers with minimum expected error within a Bayesian framework - Part I: Discrete and Gaussian models , 2013, Pattern Recognit..

[23]  Werner Kozek,et al.  Time-frequency formulation and design of nonstationary Wiener filters , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[24]  Mattia Zorzi,et al.  On the robustness of the Bayes and Wiener estimators under model uncertainty , 2015, Autom..

[25]  Roozbeh Dehghannasiri,et al.  Intrinsically Bayesian Robust Kalman Filter: An Innovation Process Approach , 2017, IEEE Transactions on Signal Processing.

[26]  Edward R. Dougherty,et al.  Optimal Experimental Design for Gene Regulatory Networks in the Presence of Uncertainty , 2015, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[27]  Simo Särkkä,et al.  Recursive Noise Adaptive Kalman Filtering by Variational Bayesian Approximations , 2009, IEEE Transactions on Automatic Control.

[28]  R. Mehra.  On the identification of variances and adaptive Kalman filtering , 1970 .

[29]  H. Poor.  On robust wiener filtering , 1980 .

[30]  Tong Zhou,et al.  Robust Recursive State Estimation With Random Measurement Droppings , 2014, IEEE Transactions on Automatic Control.

[31]  T. Kailath.  Lectures on Wiener and Kalman Filtering , 2003 .

[32]  Xiao Lin,et al.  Parameter Estimation of Population Pharmacokinetic Models with Stochastic Differential Equations: Implementation of an Estimation Algorithm , 2014 .

[33]  Anton Thalmaier,et al.  Stochastic Calculus of Variations in Mathematical Finance , 2005 .

[34]  C. Braumann,et al.  Itô versus Stratonovich calculus in random population growth. , 2007, Mathematical biosciences.

[35]  Edward R. Dougherty.  Optimal Signal Processing Under Uncertainty , 2018 .

[36]  Saleem A. Kassam,et al.  Robust Wiener filters , 1977 .

[37]  Azadeh Vosoughi,et al.  On Distributed Linear Estimation With Observation Model Uncertainties , 2017, IEEE Transactions on Signal Processing.

[38]  Masao Kasahara,et al.  Efficient bit-serial multiplication and the discrete-time Wiener-Hopf equation over finite fields , 1989, IEEE Trans. Inf. Theory.

[39]  Tong Zhou,et al.  Sensitivity Penalization Based Robust State Estimation for Uncertain Linear Systems , 2010, IEEE Transactions on Automatic Control.