Risk Sensitive Filtering with Poisson Process Observations

In this paper we consider risk sensitive filtering for Poisson process observations. Risk sensitive filtering is a type of robust filtering which offers performance benefits in the presence of uncertainties. We derive a risk sensitive filter for a stochastic system where the signal variable has dynamics described by a diffusion equation and determines the rate function for an observation process. The filtering equations are stochastic integral equations. Computer simulations are presented to demonstrate the performance gain for the risk sensitive filter compared with the risk neutral filter. Accepted 23 July 1999     

Self-triggered filter design for a class of nonlinear stochastic systems with Markovian jumping parameters

This paper is concerned with the self-triggered filtering problem for a class of Markovian jumping nonlinear stochastic systems. The event-triggered mechanism (ETM) is employed between the sensor and the filter to reduce unnecessary measurement transmission. Governed by the ETM, the measurement is transmitted to the filter as long as a predefined condition is satisfied. The purpose of the addressed problem is to synthesize a filter such that the dynamics of the filtering error is bounded in probability (BIP). A sufficient condition is first given to ensure the boundedness in probability of the filtering error dynamics, and the characterization of the desired filter gains is then realized by means of the feasibility of certain matrix inequalities. Furthermore, a self-triggered mechanism is designed to guarantee the filtering error dynamics to be BSP with excluded Zeno phenomenon. In the end, numerical simulation is carried out to illustrate the usefulness of the proposed self-triggered filtering algorithm.     

On a class of SGS filters for LES with shape preserving concatenation properties

We develop a class of filter functions for large-eddy simulation which have the key property that multiple successive application even with different filter widths is equal to a single filtering employing filters from the same class but at an extended or equal filter width. In the context of the filter class development we obtain a functional delay equation which for special cases may be solved completely general. The presently developed class of filters may be used in conjunction with certain sub-grid scale models such as the approximate deconvolution model [3] where explicit multiple filtering is needed. Hence utilizing filters from the present class computational cost of filter evaluation may be considerably reduced.     

Particle Filters with Nudging in Multiscale Chaotic Systems: With Application to the Lorenz ’96 Atmospheric Model

This paper presents reduced-order nonlinear filtering schemes based on a theoretical framework that combines stochastic dimensional reduction and nonlinear filtering. Here, dimensional reduction is achieved for estimating the slow-scale process in a multiscale environment by constructing a filter using stochastic averaging results. The nonlinear filter is approximated numerically using the ensemble Kalman filter and particle filter. The particle filter is further adapted to the complexities of inherently chaotic signals. In particle filters, an ensemble of particles is used to represent the distribution of the state of the hidden signal. The ensemble is updated using observation data to obtain the best representation of the conditional density of the true state variables given observations. Particle methods suffer from the “curse of dimensionality,” an issue of particle degeneracy within a sample, which increases exponentially with system dimension. Hence, particle filtering in high dimensions can benefit from some form of dimensional reduction. A control is superimposed on particle dynamics to drive particles to locations most representative of observations, in other words, to construct a better prior density. The control is determined by solving a classical stochastic optimization problem and implemented in the particle filter using importance sampling techniques.

     

On the Reference Probability Approach to the Equations of Non-Linear Filtering

The filtering of diffusions from their noisy observations is considered in this paper. The introduction of various reference probability measures and the use of a stochastic Feynman-Kac formula is shown to lead to new and already known filtering equations. In some cases, which include extensions of the Benes filtering problem, the new equations we propose possess a nice Gaussian solution, yielding an explicit finite dimensional filter     

The Influence of Rainflow Filtering on the Distributions of Characteristic Wave Parameters

A problem when filtering measurements of the sea-surface level is that the highest values, which are also the most interesting, might get lost. The rainflow filter is an alternative to the band-pass filters traditionally used. In this paper we investigate the properties of rainflow filtering by examining the distributions of some characteristic wave parameters. These distributions are calculated by means of the regression-approximation method which requires as input a spectral density. An approximation of the rainflow filter in the frequency domain, obtained by spectral simulation, is therefore used. The rainflow filter yields results which are closer to the distributions obtained from the original spectrum with high-frequency contents.     

Newton and Quasi-Newton Methods for Normal Maps with Polyhedral Sets

This paper is devoted to a search for a guaranteed counterpart of the stochastic Kalman filter. We study the guaranteed filtering of a linear system such that the phase state and external disturbance form a vector subject to an ellipsoidal bound. This seemingly exotic setup can be justified by an analogy with the observation of Gaussian processes. Unfortunately, the resulting guaranteed filtering supplies us an ellipsoid approximating the localization domain for the state vector, but not the localization domain itself, and turns out to be more difficult compared to the Kalman filter. Our main results consist of an explicit evaluation of the Hamiltonians. In principle, this permits us to write explicitly the equations of the guaranteed filter.     

Approximate filter for a two-dimensional nonlinear diffusion observed in a correlated low noise channel

The purpose of this article is to study a nonlinear filtering problem when the signal is a two-dimensional process from which only the second component is noisy and when only its first (and unnoisy) component is observed in a correlated low noise channel. We propose an approximate finite-dimensional filter and we prove that the filtering error converges to zero. The order of magnitude of the error between the approximate filter and the optimal filter, as the observation noise vanishes, is computed.     

Generalized H ∞-optimal filtering under external and initial perturbations

We consider the problem of optimal filtering of unmeasured variables of a linear dynamical system by linear stationary filters. The filtering performance functional to be minimized is given by the maximum relative integral filtering error over all external perturbations as well as initial perturbations caused by the unknown initial conditions of the system. We show that the optimal filter implements a trade-off between an H _∞-optimal filter and a minimax observer.     

Asymptotic stability, ergodicity and other asymptotic properties of the nonlinear filter

In this work we study connections between various asymptotic properties of the nonlinear filter. It is assumed that the signal has a unique invariant probability measure. The key property of interest is expressed in terms of a relationship between the observation σ field and the tail σ field of the signal, in the stationary filtering problem. This property can be viewed as the permissibility of the interchange of the order of the operations of maximum and countable intersection for certain σ-fields. Under suitable conditions, it is shown that the above property is equivalent to various desirable properties of the filter such as

(a) uniqueness of invariant measure for the signal,

(b) uniqueness of invariant measure for the pair (signal, filter),

(c) a finite memory property of the filter,

(d) a property of finite time dependence between the signal and observation σ fields and

(e) asymptotic stability of the filter.

Previous works on the asymptotic stability of the filter for a variety of filtering models then identify a rich class of filtering problems for which the above equivalent properties hold.     

Extension of the Kalman–Bucy Filter to Elementary Linear Systems with Fractional Brownian Noises

We investigate the optimal filtering problem in the simplest Gaussian linear system driven by fractional Brownian motions. At first we extend to this setting the Kalman–Bucy filtering equations which are well-known in the specific case of usual Brownian motions. Closed form Volterra type integral equations are derived both for the mean of the optimal filter and the variance of the filtering error. Then the asymptotic stability of the filter is analyzed. It is shown that the variance of the filtering error converges to a finite limit as the observation time tends to infinity. This revised version was published online in August 2006 with corrections to the Cover Date.     

Linear Matrix Inequality Optimization Approach to Exponential Robust Filtering for Switched Hopfield Neural Networks

This paper is concerned with the delay-dependent exponential robust filtering problem for switched Hopfield neural networks with time-delay. A new delay-dependent switched exponential robust filter is proposed that results in an exponentially stable filtering error system with a guaranteed robust performance. The design of the switched exponential robust filter for these types of neural networks can be achieved by solving a linear matrix inequality (LMI), which can be easily facilitated using standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed filter.     

Filtering and Control with Information Increasing

In this paper, we consider a filtering problem where the observation filtration is enlarged with a future information. In the linear case, we obtain the filter equations and study the associated linear regulator problem.     

Imprecise expectations for imprecise linear filtering

In most sensor measure based applications, the raw sensor signal has to be processed by an appropriate filter to increase the signal-to-noise ratio or simply to recover the signal to be measured. In both cases, the filter output is obtained by convoluting the sensor signal with a supposedly known appropriate impulse response. However, in many real life situations, this impulse response cannot be precisely specified. The filtered value can thus be considered as biased by this arbitrary choice of one impulse response among all possible impulse responses considered in this specific context. In this paper, we propose a new approach to perform filtering that aims at computing an interval valued signal containing all outputs of filtering processes involving a coherent family of conventional linear filters. This approach is based on a very straightforward extension of the expectation operator involving appropriate concave capacities.     

Ergodicity and Accuracy of Optimal Particle Filters for Bayesian Data Assimilation

Data assimilation refers to the methodology of combining dynamical models and observed data with the objective of improving state estimation. Most data assimilation algorithms are viewed as approximations of the Bayesian posterior (filtering distribution) on the signal given the observations. Some of these approximations are controlled, such as particle filters which may be refined to produce the true filtering distribution in the large particle number limit, and some are uncontrolled, such as ensemble Kalman filter methods which do not recover the true filtering distribution in the large ensemble limit. Other data assimilation algorithms, such as cycled 3DVAR methods, may be thought of as controlled estimators of the state, in the small observational noise scenario, but are also uncontrolled in general in relation to the true filtering distribution. For particle filters and ensemble Kalman filters it is of practical importance to understand how and why data assimilation methods can be effective when used with a fixed small number of particles, since for many large-scale applications it is not practical to deploy algorithms close to the large particle limit asymptotic. In this paper, the authors address this question for particle filters and, in particular, study their accuracy (in the small noise limit) and ergodicity (for noisy signal and observation) without appealing to the large particle number limit. The authors first overview the accuracy and minorization properties for the true filtering distribution, working in the setting of conditional Gaussianity for the dynamics-observation model. They then show that these properties are inherited by optimal particle filters for any fixed number of particles, and use the minorization to establish ergodicity of the filters. For completeness we also prove large particle number consistency results for the optimal particle filters, by writing the update equations for the underlying distributions as recursions. In addition to looking at the optimal particle filter with standard resampling, they derive all the above results for (what they term) the Gaussianized optimal particle filter and show that the theoretical properties are favorable for this method, when compared to the standard optimal particle filter.     

Mean-Square Filtering Problem for Discrete Volterra Equations

Abstract

The mean-square filtering problem for the discrete Volterra equations is a nontrivial task due to an enormous amount of operations required for the implementation of optimal filter. A difference equation of a moderate dimension is chosen as an approximate model for the original system. Then the reduced Kalman filter can be used as an approximate but efficient estimator. Using the duality theory of convex variational problems, a level of nonoptimality for the chosen filter is obtained. This level can be efficiently computed without exactly solving the full filtering problem.     

Continuity of the Filter with Unbounded Observation Coefficients

In this article, we study the continuity with respect to the trajectories of the observation process for the filter associated with nonlinear filtering problems when the coefficients depend on both the signal and the observation and the observation coefficient is unbounded.

To achieve this task we define a formal unnormalized filter and prove by limiting arguments that it is related to the original filter through a generalized Bayes formula, and is locally Lipschitz continuous with respect to the uniform norm.     

On the matrix Fourier filtering problem for a class of models of nonlinear optical systems with a feedback

A novel statement of the Fourier filtering problem based on the use of matrix Fourier filters instead of conventional multiplier filters is considered. The basic properties of the matrix Fourier filtering for the filters in the Hilbert–Schmidt class are established. It is proved that the solutions with a finite energy to the periodic initial boundary value problem for the quasi-linear functional differential diffusion equation with the matrix Fourier filtering Lipschitz continuously depend on the filter. The problem of optimal matrix Fourier filtering is formulated, and its solvability for various classes of matrix Fourier filters is proved. It is proved that the objective functional is differentiable with respect to the matrix Fourier filter, and the convergence of a version of the gradient projection method is also proved.     

Optimal finite-dimensional solution for a class of nonlinear observation problems

The filtering problem in a differential system with linear dynamics and observations described by an implicit equation linear in the state is solved in finite-dimensional recursive form. The original problem is posed as a deterministic fixed-interval optimization problem (FIOP) on a finite time interval. No stochastic concepts are used. Via Pontryagin's principle, the FIOP is converted into a linear, two-point boundary-value problem. The boundary-value problem is separated by using a linear Riccati transformation into two initial-value problems which give the equations for the optimal filter and filter gain. The optimal filter is linear in the state, but nonlinear with respect to the observation. Stability of the filter is considered on the basis of a related properly linear system. Three filtering examples are given.     

具时变时滞和 Markovian转换的不确定奇异随机系统的鲁棒 H_∞ 滤波(英文)

本文处理了一类具与模式有关的时变时滞和 Markovian转换的不确定奇异随机系统的鲁棒H∞滤波问题.所考虑的系统包含参数不确定性,Markovian参数,随机扰动和与模式有关的时变时滞.本文的目的是设计一个滤波器以保证滤波错误系统是正则的、无脉冲的、鲁棒指数均方稳定的和可达到一个给定的 H∞扰动衰减水平.文章首先得到所求鲁棒指数H∞滤波器存在的充分条件,然后给出所求滤波器参数的显示表示.