Adaptive Recursive Algorithm Research Articles

Extension of the schur-cohn stability test for 2-d ar quarter-plane model

The Schur-Cohn test plays an essential role in checking the stability of one-dimensional (1D) random processes such as autoregressive (AR) models, via the so-called reflection coefficients, partial correlations, or Schur-Szego coefficients. In the context of two-dimensional (2D) random field modeling, one of the authors recently proposed a 2D AR quarter-plane model representation using 2D reflection coefficients estimated by a fast recursive adaptive algorithm. Based on such 2D reflection coefficients, we can therefore derive two necessary stability conditions for a 2D AR quarter-plane model. One of these conditions can be considered as an extension of the Schur-Cohn stability criterion based on the 2D reflection coefficients.

Recursive adaptive algorithms for fast and rapidly time-varying systems

In this paper, some new schemes are developed to improve the tracking performance for fast and rapidly time-varying systems. A generalized recursive least-squares (RLS) algorithm called the trend RLS (T-RLS) algorithm is derived which takes into account the effect of local and global trend variations of system parameters. A bank of adaptive filters implemented with T-RLS algorithms are then used for tracking an arbitrarily fast varying system without knowing a priori the changing rates of system parameters. The optimal tracking performance is attained by Bayesian a posteriori combination of the multiple filter outputs, and the optimal number of parallel filters needed is determined by extended Akaike's Information Criterion and Minimum Description Length information criteria. An RLS algorithm with modification of the system estimation covariance matrix is employed to track a time-varying system with rare but abrupt (jump) changes. A new online wavelet detector is designed for accurately identifying the changing locations and the branches of changing parameters. The optimal increments of the covariance matrix at the detected changing locations are also estimated. Thus, for a general time-varying system, the proposed methods can optimally track its slowly, fast and rapidly changing components simultaneously.

Adaptive recursive algorithm for complementary subspace-based blind multiuser detection

A novel blind adaptive multiuser detection scheme, the linear decorrelating detector (LDD), based on a concept of the complementary subspace is proposed. Under this scheme, the information bits can be estimated from the received signal with the prior knowledge of the desired user's signature waveform and its timing. The technique has two key elements: a geometric notion of the LDD and the subspace-based concept to estimate the orthogonal complement of the interfering space. It is then shown that the LDD can be formulated in terms of the interference space constructed from the received signal, and the desired user's signature waveform. The interference space components can be adaptively estimated using the modified power-based methods with only O((K-1) N) flops of computation at each iteration, where N is the processing gain, and K is the number of active users in the channel. The novel blind adaptive detector offers lower computational complexity. The proposed blind multiuser detection offers the optimal near-far resistance, low computational complexity, and resistance against the orthogonality error of the estimated interference space.

A fast adaptive recursive filter

A fast adaptive recursive filtering algorithm is proposed. The algorithm is based on the minimization of the cumulative error squares cost function iteratively using the steepest descent gradient technique. This algorithm exhibits a higher convergence rate and less sensitivity to the dispersions of the input–output observations than the well-known LMS algorithm. Moreover, the proposed algorithm requires only the same computational complexity as the LMS algorithm.

“Polarized‐x” algorithm for use in fixed‐point processing

AbstractUsing the operation by fixed‐point processing, cheap and fast processors can be realized, which helps to reduce the production cost. This paper uses a newly defined cost function. It discusses also the convergence of the “polarized‐x” method. This method updates the coefficient of the nonrecursive filter based on the product with the reference signal polarity, which is an operation suited to fixed‐point processing. A normalized recursive adaptation algorithm is derived from the new cost function, which is useful in the application to the system with the reference signal with a rapidly varying power. It is shown that the stability condition is given as 0 < K < 4/π, and the estimation error increases only by approximately 2 dB compared to the conventional normalized least mean square (NLMS) algorithm. the obtained structure is modified to construct an adaptive algorithm so that the normalization is applied individually to the coefficients and the convergence is deteriorated little for the operation by the fixed‐point processing.

Block adaptive recursive algorithm for video conference coding

This paper presents a new motion estimation algorithm for video conference signal coding. This type of algorithm is called block adaptive recursive algorithm (BARA). Simulation results show that this new algorithm has better performance than conventional ones.

Mean-Convergence behavior of Adaptive Identification Algorithms for Pole-Zero Systems

Adaptive methods for the estimation of unknown system parameters has the advantage of tracking time-varying systems. Identification algorithms for recursive systems produce nonquadratic performance functions. In such problems it is very difficult to estimate the nature of convergence in a stochastic frame work. Recently, it has been shown that the ensemble mean parameter updating equations of IIR adaptive algorithm can be represened by associated ordinary differential equations (ODEs). A method of solving the ODEs in order to analyze the mean- convergence behavior of these algorithms, given the mean description of the input in the form of power spectral density, has been presented recently. In this paper, this procedure is applied to study the convergence behavior of recursive adaptive algorithms applied for the identification of pole-zero systems. Effectiveness of this method is shown through analytical and simulation results.

On digital resonance estimation of a magnetically perturbed microwave cavity

This paper shows a new digital frequency control system for a microwave spectrometer to investigate ferromagnetic resonance spectra at 11.5 GHz. In order to fulfil the measurement conditions, the measuring frequency and resonance frequency of the cavity must be equal. However, the determination of the cavity's resonance frequency containing a ferromagnetic sample with field variant characteristics is not possible directly within acceptable measuring times. For the digital control system the model of the cavity is a static and nonlinear channel with unknown and timevariant transmission characteristics. A narrow frequency modulation (/spl Delta/f<50 kHz) causes an output sequence used for an adaptive recursive algorithm. The resonance frequency of the cavity is regulated by a parameter estimator which uses a least-squares fit performed on a digital signal processor. The transient behavior and the characteristics of the digital control system are excellent. Approximately, the deviation from resonance is less than 2 kHz. As an example, the real part of the susceptibility of a small, diluted, and single-domain hexaferrite sample could be detected for the first time with signal amplitude equal to 220 kHz peak to peak.

On the identification of non-minimum phase non-gaussian MA and ARM A models using a third-order cumulant

As higher-order cumulants preserve both the magnitude and the phase information of received signals, a higher-order cumulant has been considered as a powerful signal processing tool for a non-minimum phase system. This paper describes the development of a third-order cumulant-based adaptive recursive least-square algorithm for the identification of a time-invariant non-minimum phase system and a time-variant non-minimum phase with non-gaussian input. The third-order cumulant-based algorithm has its basis in a cost function defined in the third-order cumulant and the third-order cross cumulant. The algorithm is applied to non-minimum phase ARM A and MA models system identification. The experimental results indicate that the third-order cumulant-based adaptive algorithm is capable of identifying the non-minimum phase and time-varying system. In addition, because of the third-order cumulant properties, the algorithm can suppress the gaussian noise and is capable of providing an unbiased estimate under a nois...

Travel time predictions under dynamic route guidance with a recursive adaptive algorithm: Stamatiadis, Chronis, Ph.D. Michigan State University, 1992. 227 pp

Travel time predictions under dynamic route guidance with a recursive adaptive algorithm: Stamatiadis, Chronis, Ph.D. Michigan State University, 1992. 227 pp

A Self-Tuning Type Neural Net Controller For Robotic Manipulators

ABSTRACTThis article presents a self-tuning type neural net controller for robotic manipulators. A parallel recursive adaptation algorithm is described for on-line implementation of the neural net controller. The proposed control scheme does not require any information about the system dynamics. The control system was implemented for a cylindrical robot by computer simulation. The simulation result shows the effectiveness of the neural net controller and its adaptation and learning capability for nonlinear time-varying robot systems.

High-Order Local Approximation Adaptive Control of Rapidly Time-Varying Dynamics

A linear dynamical system with unknown rapidly time-varying parameters is considered. New off-line and recursive adaptive control algorithms are suggested and justified. "High order" has here a double meaning. Firstly, it means that the orders of the control algorithms are higher than the number of adjustable parameters. Secondly, the algorithms are effective for rapidly time-varying parameters and the control errors are proportional to the higher order derivatives of these parameters.

System identification techniques for adaptive recursive filtering

Many problems in adaptive filtering can be approached from the point of view of system identification. For an adaptive filter with N adjustable coefficients or weights, the mean-squared value of the output error is a plot, in N + 1 dimensions, of the mean-squared error versus the N coefficient values. If the adaptive filter is non-recursive, the mean-squared value of the output error is a quadratic function of the coefficients. With recursive adaptive filters, the output error is not quadratic and may even have local minima. This paper introduces a new class of adaptive recursive algorithm, which offer a much reduced computational load for basically the same performance, and has a non-vanishing gain which enables the algorithm to remain active and to track time-varying systems. A simplified version of the algorithm, called the steepest descent recursive algorithm, which retains provable convergence at low convergence rates, is well suited to system identification.

An overview of manifold and its implementation

AbstractManagement of the communications among a set of concurrent processes arises in many applications and is a central concern in parallel computing. In this paper we introduce MANIFOLD: a co‐ordination language whose sole purpose is to describe and manage complex interconnections among independent, concurrent processes. In the underlying paradigm of this language the primary concern is not with what functionality the individual processes in a parallel system provide. Instead, the emphasis is on how these processes are interconnected and how their interaction patterns change during the execution life of the system. This paper also includes an overview of our implementation of MANIFOLD.As an example of the application of MANIFOLD, we present a series of small manifold programs which describe the skeletons of some adaptive recursive algorithms that are of particular interest in computer graphics. Our concern in this paper is to show the expressiveness of MANIFOLD, the feasibility of its implementation and its usefulness in practice. Issues regarding performance and optimization are beyond the scope of this paper.

Comparison of pitch prediction and adaptation algorithms in forward and backward adaptive CELP systems

The paper examines several pitch estimation and adaptation algorithms in forward and backward adaptive CELP systems. The authors compare open-loop and closed-loop pitch estimation structures, the use of integer and non-integer delay pitch prediction, and the implementation of block adaptive and sample recursive pitch tracking algorithms. Forward adaptive systems are found to perform better with a closed-loop structure in conjunction of non-integer delay pitch prediction. However, temporal and noise feedback problems suggest that open-loop structures with hybrid pitch tracking are better suited for backward adaptive systems

Application of Recursive Adaptive Algorithms for System Identification and Vibration Control

This paper describes advances in the identification and control of flexible structures by consequent application of recursive adaptive algorithms on controllers with load path-considering design. Control of large structures requires powerful algorithms that are able to influence certain modes of a system with high modal densities. The stabil ity of the adaptation process must be maintained. This paper describes theoretical and simulational investigations within the framework of the DLR program ARES (Actively Reacting Flexible Structures), showing the performance of the modal controllers that are based on recursive digital filters.

Recursive least-squares identification algorithms with incomplete excitation: convergence analysis and application to adaptive control

The convergence properties of a fairly general class of adaptive recursive least-squares algorithms are studied under the assumption that the data generation mechanism is deterministic and time invariant. First, the (open-loop) identification case is considered. By a suitable notion of excitation subspace, the convergence analysis of the identification algorithm is carried out with no persistent excitation hypothesis, i.e. it is proven that the projection of the parameter error on the excitation subspace tends to zero, while the orthogonal component of the error remains bounded. The convergence of an adaptive control scheme based on the minimum variance control law is then dealt with. It is shown that under the standard minimum-phase assumption, the tracking error converges to zero whenever the reference signal is bounded. Furthermore, the control variable turns out to be bounded.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Thorough Use of Information in Deterministic Adaptive Control

A new model reference adaptive control structure and recursive adaptation algorithm are presented. It is proven that the excitation requirements for asymptotic model transfer function matching are strictly weaker than those required by earlier stable adaptive systems. The conditions for convergence are obtained either in terms of certain internal signals or in terms of external command inputs to the system. These results help clarify the issue of information content in a deterministic adaptive control setting, proving that persistent excitation is sufficient for convergence but not necessary. The results also show conclusively that there is merit in the use of past information in a parameter update law.

Arbitrarily high sampling rate adaptive filters

Adaptive filters have an inherent feedback from error signal back to the adaptation of the coefficients. This represents a problem in high sampling rate realizations. We demonstrate a realization of adaptive filters for which there is no theoretical limit on sampling rate in a given speed of hardware, at the expense of additional hardware and latency. Our realization does not change the input-output characteristics aside from finite precision effects, and hence does not degrade the filter tracking capability. The basis for our realization is the adaptive lattice filter, which uses only local feedback in adapting reflection coefficients at each stage, and for which the recursive portion of the adaptation algorithms in each stage is linear. Our realization is based on these two properties and the basic technique of look-ahead computation. Several forms of our realization applying to different recursive least-squares and stochastic-gradient adaptation algorithms are described.

Identification of ARI Model with Applications to On-Line Trend Detections

This paper investigates the recursive adaptive algorithms for rapidly detecting various stochastic trends in signals by modeling them as the autoregressive mtegrated(ARI) process. In order to determine the degree of differencing which represents the changing rate of nonstationary trend components, we derive a new criterion on a basis of the concept of the AIC. The generalized gradient(GG) algorithm and the normalized least squares lattice(NLSL) filter are utilized to identify coefficient parameters in the ARI model in an on-line manner. The effectiveness of the algorithms is examined through numerical simulation using actual data.