Use of trellis diagrams in state estimation in blocks for nonlinear discrete dynamic systems with aKth-order memory

A new suboptimum estimation scheme is proposed for nonlinear discrete dynamic systems with aKth-order memory. These systems are first represented by trellis diagrams, and then states are estimated by the Viterbi algorithm of information theory. The state and observation models of the proposed scheme can be nonlinear functions of the disturbance noise, observation noise, and present and past discrete values of the state, whereas the models of the classical estimation algorithms, such as the extended Kaiman filter, must be linear functions of the disturbance noise and observation noise. States are estimated in blocks, which results in an estimation scheme whose implementation requries a constant memory.     

A design algorithm for optimal low-pass nonlinear phase FIR digital filters

The transfer function of the low-pass nonlinear phase finite impulse response (NLPFIR) digital filter is decomposed into a nonlinear phase part and a linear phase part. An algorithm is proposed to iteratively design the magnitude of the linear phase part and the squared magnitude of the nonlinear phase part by directly calling the Remez algorithm of McClellan, et al. [1]. In the design of the nonlinear phase part, we assume that the linearity constraint on the phase is dropped but the phase response is not specified. A scheme is incorporated into our algorithm so that it can design the filter with the desired ripple ratio. This approach also leads to a method for finding the minimum ripple ratio for the given orders of the two parts and band edges of the filters. The filters with ripple ratio larger than this minimum value can be designed by our algorithm and neither passband nor stopband ripples are required to be prescribed. Analysis of roundoff noise reveals that the cascade filter implementation usually needs higher wordlengths than its direct for counterpart for the same roundoff noise performance.     

Adaptive robust spread-spectrum receivers

We consider the problem of robust detection of a spread-spectrum (SS) signal in the presence of unknown correlated SS interference and additive non-Gaussian noise. The proposed general SS receiver structure is comprised by a vector of adaptive chip-based nonlinearities followed by an adaptive linear tap-weight filter and combines the relative merits of both nonlinear and linear signal processing. The novel characteristics of our approach are as follows. First, the nonlinear receiver front-end adapts itself to the unknown prevailing noise environment providing robust performance for a wide range of underlying noise distributions. Second, the adaptive linear tap-weight filter that follows the nonlinearly processed chip samples results in a receiver that is proven to be effective in combating SS interference as well. To determine the receiver parameters, we propose, develop, and study three adaptive schemes under a joint mean-square error (MSE), or a joint bit-error-rate (BER), or a joint MSE-BER optimization criterion. As a side result, we derive the optimum decision fusion filter for receivers that utilize hard-limiting (sign) chip nonlinearities. Numerical and simulation results demonstrate the performance of the proposed schemes and offer comparisons with the conventional matched-filter (MF), the decorrelator, the conventional minimum-variance-distortionless-response (MVDR) filter, and the sign-majority vote receiver     

过程噪声未知但有界情况下系统最优滤波器设计方法

本文基于模型匹配方法提出了一种极小化误差幅值的线性系统的最优滤波器的设计方法,所考虑的过程噪声和量测噪声均为未知但幅值有界信号.该方法的特点是能够处理无穷观测数据量的最优滤波问题.当系统的初始条件已知时,将滤波器设计问题化为一个标准二块₁优化问题;当系统含有未知但有界初始条件时该问题归结为有限个标准₁优化问题,而标准₁优化问题已有成熟算法求解.仿真实例子说明了所提出方法的有效性和可行性.     

Unbiased estimation of an initial phase

This paper explores the problem of the unbiased estimation of the initial phase of a tone burst. Two types of initial phase estimators are investigated. The first one is based on the modification of a well-known statistically-optimal approach of estimation the phase of a continuous sinusoidal signal in the presence of a noise. The modified version permits nonlinear compensation of a priori unknown bias which is a function of a tone frequency, length of the observation interval, and of an unknown initial phase itself. The second approach employs a notch filter at the burst's ‘steady-state’ frequency. The transient of such a filter resulting from the onset of a burst can be used to deduce the signal's initial phase while the steady-state response is eliminated. Analysis shows that an estimation is unbiased and, therefore, it might be reasonably applied in high SNR environments where an estimate must be made within an extremely short length of an observation interval (less than one period).     

Robust and efficient recovery of a signal passed through a filterand then contaminated by non-Gaussian noise

Consider a channel where a continuous periodic input signal is passed through a linear filter and then is contaminated by an additive noise. The problem is to recover this signal when we observe n repeated realizations of the output signal. Adaptive efficient procedures, that are asymptotically minimax over all possible procedures, are known for channels with Gaussian noise and no filter (the case of direct observation). Efficient procedures, based on the smoothness of a recovered signal, are known for the case of Gaussian noise. Robust rate-optimal procedures are known as well. However, there are no results on robust and efficient data-driven procedures; moreover, the known results for the case of direct observation indicate that even a small deviation from Gaussian noise may lead to a drastic change. We show that for the considered case of indirect data and a particular class of so-called supersmooth filters there exists a procedure of recovery of an input signal that possesses the desired properties; namely, it is: adaptive to the smoothness of the input signal; robust to the distribution of the noise; globally and pointwise-efficient, that is, its minimax global and pointwise risks converge with the best constant and rate over all possible estimators as n→∞; and universal in the sense that for a wide class of linear (not necessarily bounded) operators the efficient estimator is a plug-in one. Furthermore, we explain how to employ the obtained asymptotic results for the practically important case of small n (large noise)     

A multichannel hierarchical approach to adaptive Volterra filters employing filtered-X affine projection algorithms

It is shown in this paper how the use of a recently introduced algebra, called V-vector algebra, can directly lead to the implementation of Volterra filters of any order P in the form of a multichannel filterbank. Each channel in this approach is modeled as a finite impulse response (FIR) filter, and the channels are hierarchically arranged according to the number of the filter coefficients. In such a way, it is also possible to devise models of reduced complexity by cutting the less relevant channels. This model is then used to derive efficient adaptation algorithms in the context of nonlinear active noise control. In particular, it is shown how the affine projection (AP) algorithms used in the linear case can be extended to a Volterra filter of any order P. The derivation of the so-called Filtered-X AP algorithms for nonlinear active noise controllers is easily obtained using the elements of the V-vector algebra. These algorithms can efficiently replace the standard LMS and NLMS algorithms usually applied in this field, especially when, in practical applications, a reduced-complexity multichannel structure can be exploited.     

Iterative and sequential algorithms for multisensor signalenhancement

In problems of enhancing a desired signal in the presence of noise, multiple sensor measurements will typically have components from both the signal and the noise sources. When the systems that couple the signal and the noise to the sensors are unknown, the problem becomes one of joint signal estimation and system identification. The authors specifically consider the two-sensor signal enhancement problem in which the desired signal is modeled as a Gaussian autoregressive (AR) process, the noise is modeled as a white Gaussian process, and the coupling systems are modeled as linear time-invariant finite impulse response (FIR) filters. The main approach consists of modeling the observed signals as outputs of a stochastic dynamic linear system, and the authors apply the estimate-maximize (EM) algorithm for jointly estimating the desired signal, the coupling systems, and the unknown signal and noise spectral parameters. The resulting algorithm can be viewed as the time-domain version of the frequency-domain approach of Feder et al. (1989), where instead of the noncausal frequency-domain Wiener filter, the Kalman smoother is used. This approach leads naturally to a sequential/adaptive algorithm by replacing the Kalman smoother with the Kalman filter, and in place of successive iterations on each data block, the algorithm proceeds sequentially through the data with exponential weighting applied to allow adaption to nonstationary changes in the structure of the data. A computationally efficient implementation of the algorithm is developed. An expression for the log-likelihood gradient based on the Kalman smoother/filter output is also developed and used to incorporate efficient gradient-based algorithms in the estimation process     

Asymptotic stability of the MMSE linear filter for systems with uncertain observations (Corresp.)

Sufficient conditions for uniform asymptotic stability in the large of the optimal minimum mean-square error (MMSE) linear filter are developed for discrete linear systems whose observations may contain noise alone and where only the probability of occurrence of such cases is known to the estimator. Conditions for existence, uniqueness, and stability of the steady-state optimal filter are also considered for the case when the system is time-invariant.     

Robust Kalman Filter Design for Markovian Jump Linear Systems with Norm-Bounded Unknown Nonlinearities

This paper considers the problems of stability and filtering for a class of linear hybrid systems with nonlinear uncertainties and Markovian jump parameters. The hybrid system under study involves a continuous-valued system state vector and a discretevalued system mode. The unknown nonlinearities in the system are time varying and norm bounded. The Markovian jump parameters are modeled by a Markov process with a finite number of states. First, we show the equivalence of the sets of norm-bounded linear and nonlinear uncertainties. Then, instead of the original hybrid linear system with nonlinear uncertainties, we consider the same system with linear uncertainties. By using a Riccati equation approach for this new system, a robust filter is designed using two sets of coupled Riccati-like equations such that the estimation error is guaranteed to have an upper bound.     

H �� Filtering for Markovian Switching Genetic Regulatory Networks with Time-Delays and?Stochastic?Disturbances

This paper is concerned with the H _∞ filtering problem for a class of nonlinear Markovian switching genetic regulatory networks (GRNs) with time-delays, intrinsic fluctuation and extrinsic noise. The delays, which exist in both the translation process and feedback regulation process, are not dependent on the system model. The intrinsic fluctuation is described as a state-dependent stochastic process, while the extrinsic noise is modeled as an arbitrary signal with bounded energy, and no exact statistics about the noise are required to be known. The aim of the problem addressed is to design a Markovian jump linear filter to estimate the true concentrations of mRNA and protein through available measurement outputs. By resorting to the Lyapunov functional method and some stochastic analysis tools, it is shown that if a set of linear matrix inequalities (LMIs) is feasible, then the desired linear filter exists. The designed filter ensures asymptotic mean-square stability of the filtering error system and two prescribed L ₂-induced gains from the noise signals to the estimation errors. Finally, an illustrative example is given to demonstrate the effectiveness of the approach proposed.     

Statistical analysis of neural network modeling and identificationof nonlinear systems with memory

The paper presents a statistical analysis of neural network modeling and identification of nonlinear systems with memory. The nonlinear system model is comprised of a discrete-time linear filter H followed by a zero-memory nonlinear function g(.). The system is corrupted by input and output independent Gaussian noise. The neural network is used to identify and model the unknown linear filter H and the unknown nonlinearity g(.). The network architecture is composed of a linear adaptive filter and a two-layer nonlinear neural network (with an arbitrary number of neurons). The network is trained using the backpropagation algorithm. The paper studies the MSE surface and the stationary points of the adaptive system. Recursions are derived for the mean transient behavior of the adaptive filter coefficients and neural network weights for slow learning. It is shown that the Wiener solution for the adaptive filter is a scaled version of the unknown filter H. Computer simulations show good agreement between theory and Monte Carlo estimations     

Dual H∞ Algorithms for Signal Processing— Application to Speech Enhancement

This paper deals with the joint signal and parameter estimation for linear state-space models. An efficient solution to this problem can be obtained by using a recursive instrumental variable technique based on two dual Kalman filters. In that case, the driving process and the observation noise in the state-space representation for each filter must be white with known variances. These conditions, however, are too strong to be always satisfied in real cases. To relax them, we propose a new approach based on two dual H_infin filters. Once a new observation of the disturbed signal is available, the first H_infin algorithm uses the latest estimated parameters to estimate the signal, while the second H_infin algorithm uses the estimated signal to update the parameters. In addition, as the H_infin filter behavior depends on the choice of various weights, we present a way to recursively tune them. This approach is then studied in the following cases: (1) consistent estimation of the AR parameters from noisy observations and (2) speech enhancement, where no a priori model of the additive noise is required for the proposed approach. In each case, a comparative study with existing methods is carried out to analyze the relevance of our solution.     

An EM Algorithm for Nonlinear State Estimation With Model Uncertainties

In most solutions to state estimation problems, e.g., target tracking, it is generally assumed that the state transition and measurement models are known a priori. However, there are situations where the model parameters or the model structure itself are not known a priori or are known only partially. In these scenarios, standard estimation algorithms like the Kalman filter and the extended Kalman Filter (EKF), which assume perfect knowledge of the model parameters, are not accurate. In this paper, the nonlinear state estimation problem with possibly non-Gaussian process noise in the presence of a certain class of measurement model uncertainty is considered. It is shown that the problem can be considered as a special case of maximum-likelihood estimation with incomplete data. Thus, in this paper, we propose an EM-type algorithm that casts the problem in a joint state estimation and model parameter identification framework. The expectation (E) step is implemented by a particle filter that is initialized by a Monte Carlo Markov chain algorithm. Within this step, the posterior distribution of the states given the measurements, as well as the state vector itself, are estimated. Consequently, in the maximization (M) step, we approximate the nonlinear observation equation as a mixture of Gaussians (MoG) model. During the M-step, the MoG model is fit to the observed data by estimating a set of MoG parameters. The proposed procedure, called EM-PF (expectation-maximization particle filter) algorithm, is used to solve a highly nonlinear bearing-only tracking problem, where the model structure is assumed unknown a priori. It is shown that the algorithm is capable of modeling the observations and accurately tracking the state vector. In addition, the algorithm is also applied to the sensor registration problem in a multi-sensor fusion scenario. It is again shown that the algorithm is successful in accommodating an unknown nonlinear model for a target tracking scenario.     

Transient and steady-state analysis of filtered-x affine projection algorithms

This paper provides an analysis of transient and steady-state behavior of different filtered-x affine projection algorithms. Algorithms suitable for single-channel and for multichannel active noise controllers are treated within a unified framework. Very mild assumptions are posed on the active noise control system model, which is only required to have a linear dependence of the output from the filter coefficients. Therefore, the analysis applies not only to the linear finite impulse response models but also to nonlinear Volterra filters, i.e., polynomial filters, and other nonlinear filter structures. The convergence analysis presented in this paper relies on energy conservation arguments and does not apply the independence theory, nor does it impose any restriction to the signal distributions. It is shown in the paper that filtered-x affine projection algorithms always provide a biased estimate of the minimum mean square solution. Nevertheless, in many cases, the bias is small and therefore these algorithms can be profitably applied to active noise control.     

Optimal and self-tuning deconvolution in time domain

This paper is concerned with both the optimal (minimum mean square error variance) and self-tuning deconvolution problems for discrete-time systems. When the signal model, measurement model, and noise statistics are known, a novel approach for the design of the optimal deconvolution filter, predictor, and smoother is proposed based on projection theory and innovation analysis in the time domain. The estimators are given in terms of an autoregressive moving average (ARMA) innovation model and one unilateral linear polynomial equation, where the ARMA innovation model is obtained by performing one spectral factorization. A self-tuning scheme can be incorporated when the noise statistics, the input model, and/or colored noise model are unknown. The self-tuning estimator is designed by identifying two ARMA innovation models     

The structure and design of realizable decision feedback equalizers for IIR channels with colored noise

A simple algorithm for optimizing decision feedback equalizers (DFEs) by minimizing the mean-square error (MSE) is presented. A complex baseband channel and correct past decisions are assumed. The dispersive channel may have infinite impulse response, and the noise may be colored. Consideration is given to optimal realizable (stable and finite-lag smoothing) forward and feedback filters in discrete time. They are parameterized as recursive filters. In the special case of transmission channels with finite impulse response and autoregressive noise, the minimum MSE can be attained with transversal feedback and forward filters. In general, the forward part should include a noise-whitening filter (the inverse noise model). The finite realizations of the filters are calculated using a polynomial equation approach to the linear quadratic optimization problem. The equalizer is optimized essentially by solving a system of linear equations Ax=B, where A contains transfer function coefficients from the channel and noise model. No calculation of correlations is required with this method. A simple expression for the minimal MSE is presented. The DFE is compared to MSE-optimal linear recursive equalizers. Expressions for the equalizer in the limiting case of infinite smoothing lags are also discussed.<>     

Robust adaptive recovery of spread-spectrum signals with short data records

The problem under consideration is the adaptive reception of a multipath direct-sequence spread-spectrum (SS) signal in the presence of unknown correlated SS interference and additive impulsive noise. An SS receiver structure is proposed that consists of a vector of adaptive chip-based Hampel nonlinearities followed by an adaptive auxiliary-vector linear tap-weight filter. The nonlinear receiver front end adapts itself to the unknown prevailing noise environment providing robust performance over a wide range of underlying noise distributions. The adaptive auxiliary-vector linear tap-weight filter allows rapid SS interference suppression with a limited data record. Numerical and simulation studies under finite-data-record system adaptation show significant improvement in bit-error-rate performance over the conventional linear minimum variance-distortionless-response (MVDR) SS receiver or conventional MVDR filtering preceded by vector adaptive chip-based nonlinear processing.     

Polyspectrum modeling using linear or quadratic filters

The polyspectrum modeling problem using linear or quadratic filters is investigated. In the linear case, it is shown that, if the output pth-order cumulant function of a filter, driven by a white noise, is of finite extent, then the filter necessarily has a finite-extent impulse response. It is proved that every factorable polyspectrum with a non-Gaussian white noise can also be modeled with a quadratic filter driven by a Gaussian white noise. It is shown that, if the quadratic filter has a finite-extent impulse response, then the output pth-order cumulant function is of finite extent; and if the output pth-order cumulant function of a quadratic filter is of finite extent, then the impulse response may or may not be of finite extent. It is shown that there exist finite and infinite extent p th-order cumulant functions that are not factorable but can be modeled with quadratic filters     

Global identification of continuous-time-systems with unknown noise covariance (Corresp.)

Global convergence pf the maximum likelihood estimates of unknown parameters of a continuous-time stochastic linear dynamical system is investigated when the observation noise covariance is unknown. The unknown parameter set is assumed to be finite. The situation where the true parameter does not belong to the unknown parameter set is considered as well as the situation where the true model is included in the unknown parameter set. Convergence is proved under a certain sufficient condition called the identifiability condition.