Showing papers on "Adaptive filter published in 1994"

A state-space approach to adaptive RLS filtering

Abstract: Adaptive filtering algorithms fall into four main groups: recursive least squares (RLS) algorithms and the corresponding fast versions; QR- and inverse QR-least squares algorithms; least squares lattice (LSL) and QR decomposition-based least squares lattice (QRD-LSL) algorithms; and gradient-based algorithms such as the least-mean square (LMS) algorithm. Our purpose in this article is to present yet another approach, for the sake of achieving two important goals. The first one is to show how several different variants of the recursive least-squares algorithm can be directly related to the widely studied Kalman filtering problem of estimation and control. Our second important goal is to present all the different versions of the RLS algorithm in computationally convenient square-root forms: a prearray of numbers has to be triangularized by a rotation, or a sequence of elementary rotations, in order to yield a postarray of numbers. The quantities needed to form the next prearray can then be read off from the entries of the postarray, and the procedure can be repeated; the explicit forms of the rotation matrices are not needed in most cases. >

Adaptive IIR Filtering in Signal Processing and Control

Abstract: Recursive filter structures the Beurling-Lax theorem, Hankel forms and classical identification adaptive IIR filtering in signal processing and control stability of time-varying recursive filters gradient descent algorithms the Steiglitz-McBride family of algorithms hyperstable algorithms adaptive notch filters perspectives and open problems computations with lattice filters.

Unconstrained correlation filters

Abstract: A mathematical analysis of the distortion tolerance in correlation filters is presented. A good measure for distortion performance is shown to be a generalization of the minimum average correlation energy criterion. To optimize the filter's performance, we remove the usual hard constraints on the outputs in the synthetic discriminant function formulation. The resulting filters exhibit superior distortion tolerance while retaining the attractive features of their predecessors such as the minimum average correlation energy filter and the minimum variance synthetic discriminant function filter. The proposed theory also unifies several existing approaches and examines the relationship between different formulations. The proposed filter design algorithm requires only simple statistical parameters and the inversion of diagonal matrices, which makes it attractive from a computational standpoint. Several properties of these filters are discussed with illustrative examples.

Using recurrent neural networks for adaptive communication channel equalization

Abstract: Nonlinear adaptive filters based on a variety of neural network models have been used successfully for system identification and noise-cancellation in a wide class of applications. An important problem in data communications is that of channel equalization, i.e., the removal of interferences introduced by linear or nonlinear message corrupting mechanisms, so that the originally transmitted symbols can be recovered correctly at the receiver. In this paper we introduce an adaptive recurrent neural network (RNN) based equalizer whose small size and high performance makes it suitable for high-speed channel equalization. We propose RNN based structures for both trained adaptation and blind equalization, and we evaluate their performance via extensive simulations for a variety of signal modulations and communication channel models. It is shown that the RNN equalizers have comparable performance with traditional linear filter based equalizers when the channel interferences are relatively mild, and that they outperform them by several orders of magnitude when either the channel's transfer function has spectral nulls or severe nonlinear distortion is present. In addition, the small-size RNN equalizers, being essentially generalized IIR filters, are shown to outperform multilayer perceptron equalizers of larger computational complexity in linear and nonlinear channel equalization cases. >

Acoustic event localization using a crosspower-spectrum phase based technique

Abstract: Linear microphone arrays can be employed for acoustic event localization in a noisy environment using time delay estimation. Three techniques are investigated that allow delay estimation, namely normalized cross correlation, LMS adaptive filters, crosspower-spectrum phase: they are combined with a bidimensional representation, the coherence measure, in order to emphasize information that can be exploited for estimating position of both non-moving and moving acoustic sources. To compare the given techniques, different acoustic sources were considered, that generated events in different positions in space. Expressing performance in terms of accuracy of the wavefront direction angle, experiments showed that the crosspower-spectrum phase based technique outperforms the other two. This technique provided very promising preliminary results also in terms of source position estimation. >

Adaptive signal processing algorithms: stability and performance

Abstract: PART I. 1. Introduction. 2. Offline Analysis. 3. Iterative Minimization. 4. Algorithm Construction. 5. Algorithm Analysis: Gaussian White Noise Setting. 6. Algorithm Analysis: Deterministic Global Theory. PART II. 7. Deterministic Averaging: Single Time Scale. 8. Deterministic Averaging: Mixed Time Scale. PART III. 9. Stochastic Averaging: Single Time Scale. 10. Stochastic Averaging: Mixed Time Scale. APPENDICES. A. Matrix Analysis Review. B. Stochastic Signals and Systems Review. C. Deterministic Signals and Systems Review. D. Mathematical Analysis Review. E. Probability Review. Bibliography. Index.

Adaptive detection using low rank approximation to a data matrix

Abstract: Using an accurate formula for the error in approximating a low rank component, we calculate the performance of adaptive detection based on reduced-rank nulling. In this principal component inverse (PCI) method, one temporarily regards the interference as a strong signal to be enhanced. The resulting estimate of the interference waveform is subtracted from the observed data, and matched filtering is used to detect signal components in the residual waveform. We also present a generalized likelihood-ratio test (GLRT) for adaptively detecting a low rank signal in the presence of low rank interference. This approach leads to a test which is closely related to the PCI method and extends the PCI method to the case where strong signal components are present in the data. A major accomplishment of the work is our calculation of the statistics of the output of the matched filter for the case in which interference cancellation and signal detection are carried out on the same observed data matrix. That is, no separate data is used for adaptation. Examples are presented using both simulated data and real, active-sonar reverberation data from the ARSRP, the Acoustic Reverberation Special Research Program of the Office of Naval Research. >

Optimal waveform selection for tracking systems

Abstract: Investigates adaptive waveform selection schemes where selection is based on overall target tracking system performance. Optimal receiver assumptions allow the inclusion of transmitted waveform specification parameters in the tracking subsystem defining equations. The authors give explicit expressions for two one-step ahead optimization problems for a single target in white Gaussian noise when the tracker is a conventional Kalman filter. These problems may be solved to yield the most improvement possible in tracking performance for each new transmitted pulse. In cases where target motion is restricted to one dimension, closed-form solutions to the local (one step ahead) waveform optimization problem have been obtained. The optimal waveform selection algorithms in the paper may be included with conventional Kalman filtering equations to form an enhanced Kalman tracker. Simulation examples are presented to illustrate the potential of the waveform selection schemes for the optimal utilization of the capabilities of modern digital waveform generators, including multiple waveform classes. The extension of the basic waveform optimization scheme to more complex tracking scenarios is also discussed. >

A comparison of digital speckle filters

Abstract: Some of the well-known adaptive speckle reduction filters are evaluated and compared based on objective and practical criteria. The performance of the filters is tested by using both the acquired SAR images and computer simulated patterns. >

Least mean mixed-norm adaptive filtering

Abstract: A new family of stochastic gradient adaptive filter algorithms is proposed which is based on mixed error norms These algorithms combine the advantages of different error norms, for example the conventional, relatively well-behaved, least mean square algorithm and the more sensitive, but better converging, least mean fourth algorithm A mixing parameter is included which controls the proportions of the error norms and offers an extra degree of freedom within the adaptation A system identification simulation is used to demonstrate the performance of a least mean mixed-norm (square and fourth) algorithm

Adaptive digital notch filter design on the unit circle for the removal of powerline noise from biomedical signals

Abstract: Investigates adaptive digital notch filters for the elimination of powerline noise from biomedical signals. Since the distribution of the frequency variation of the powerline noise may or may not be centered at 60 Hz. Three different adaptive digital notch filters are considered. For the first case, an adaptive FIR second-order digital notch filter is designed to track the center frequency variation. For the second case, the zeroes of an adaptive IIR second-order digital notch filter are fixed on the unit circle and the poles are adapted to find an optimum bandwidth to eliminate the noise to a pre-defined attenuation level. In the third case, both the poles and zeroes of the adaptive IIR second-order filter are adapted to track the center frequency variation within an optimum bandwidth. The adaptive process is considerably simplified by designing the notch filters by pole-zero placement on the unit circle using some suggested rules. A constrained least mean-squared algorithm is used for the adaptive process. To evaluate their performance, the three adaptive notch filters are applied to a powerline noise sample and to a noisy EEG as an illustration of a biomedical signal. >

Space-time adaptive processing for airborne radar

Abstract: Advanced airborne radar systems are required to detect targets in the presence of both clutter and jamming. Ground clutter is extended in both angle and range, and is spread in Doppler frequency because of the platform motion. Space-time adaptive processing (STAP) refers to the simultaneous processing of the signals from an array antenna during a multiple pulse coherent waveform. STAP can provide improved detection of targets obscured by mainlobe clutter, defection of targets obscured by sidelobe clutter, and detection in combined clutter and jamming environments. Fully adaptive STAP is impractical for reasons of computational complexity and estimation with limited data, so partially adaptive approaches are required. The paper presents a taxonomy of partially adaptive STAP approaches that are classified according to the type of preprocessor, or equivalently, by the domain in which adaptive weighting occurs. Analysis of the rank of the clutter covariance matrix in each domain provides insight and conditions for preprocessor design.

A recursive multiple model approach to noise identification

Abstract: Correct knowledge of noise statistics is essential for an estimator or controller to have reliable performance. In practice, however, the noise statistics are unknown or not known perfectly and thus need to be identified. Previous work on noise identification is limited to stationary noise and noise with slowly varying statistics only. An approach is presented here that is valid for nonstationary noise with rapidly or slowly varying statistics as well as stationary noise. This approach is based on the estimation with multiple hybrid system models. As one of the most cost-effective estimation schemes for hybrid system, the interacting multiple model (IMM) algorithm is used in this approach. The IMM algorithm has two desirable properties: it is recursive and has fixed computational requirements per cycle. The proposed approach is evaluated via a number of representative examples by both Monte Carlo simulations and a nonsimulation technique of performance prediction developed by the authors recently. The application of the proposed approach to failure detection is also illustrated. >

An efficient recursive total least squares algorithm for FIR adaptive filtering

Abstract: An algorithm for recursively computing the total least squares (TLS) solution to the adaptive filtering problem is described. This algorithm requires O(N) multiplications per iteration to effectively track the N-dimensional eigenvector associated with the minimum eigenvalue of an augmented sample covariance matrix. It is shown that the recursive least squares (RLS) algorithm generates biased adaptive filter coefficients when the filter input vector contains additive noise. The TLS solution on the other hand, is seen to produce unbiased solutions. Examples of standard adaptive filtering applications that result in noise being added to the adaptive filter input vector are cited. Computer simulations comparing the relative performance of RLS and recursive TLS are described. >

Decision-based median filter using local signal statistics

Abstract: Noise removal is important in many applications. When the noise has impulsive characteristics, linear techniquesdo not perform well, and median filter or its derivatives are often used. Although median-based filters preserve edgesreasonably well, they tend to remove some of the finer details in the image. Switching schemes — where the filter isswitched between two or more filters — have been proposed, but they usually lack a decision rule efficient enough toyield good results on different regions of the image. In this paper we present a strategy to overcome this problem. Adecision rule based on the second order local statistics of the signal (within a window) is used to switch between theidentity filter and a median filter. The results on a test image show an improvement of around 4dB over the medianfilter alone, and 2dB over other techniques.Keywords: Median filter; Image enhancement; Noise removal; Impulsive noise. 1. INTRODUCTION Noise reduction is often necessary as a pre-processing step in situations where a signal is contaminated by noise.In cases where the noise can be adequately modeled as additive Gaussian noise, linear filters are normally efficiciitfor noise-reduction. However, in many cases the noise is impulsive, and in this case linear techniques do not usuallyperform well. The median filter and its derivatives are often the filter of choice for these applications.The median filter is a non-linear filter, and it has the useful property of removing (reducing) impulsive noisewithout (severely) smoothing the edges of the signal. The main drawback of the median filter is that it also modifiesthe points not contaminated by noise, therefore removing the finer details in the signal.In the past 20 years, median filters have been generalized and modified in many ways. A good overview of pastwork on generalizations of median filters can be find in the paper by Gabbouj et al.1 Examples include rank orderfilters, weighted median filters, stack filters, and linear combinations of nonlinear filters. A theory for optimal stackfilters has been developed.2 More recently, filters where the rank selected is based on the pixel rank have been alsoproposed .

An adaptive estimation of periodic signals using a Fourier linear combiner

Abstract: Presents an adaptive algorithm for estimating from noisy observations, periodic signals of known period subject to transient disturbances. The estimator is based on the LMS algorithm and works by tracking the Fourier coefficients of the data. The estimator is analyzed for convergence, noise misadjustment and lag misadjustment for signals with both time invariant and time variant parameters. The analysis is greatly facilitated by a change of variable that results in a time invariant difference equation. At sufficiently small values of the LMS step size, the system is shown to exhibit decoupling with each Fourier component converging independently and uniformly. Detection of rapid transients in data with low signal to noise ratio can be improved by using larger step sizes for more prominent components of the estimated signal. An application of the Fourier estimator to estimation of brain evoked responses is included. >

Least mean p-power error criterion for adaptive FIR filter

Abstract: An adaptive FIR filter based on the least mean p-power error (MPE) criterion is investigated. First, some useful properties of MPE function are studied. Three main results are as follows: 1) MPE function is a convex function of filter coefficients; so it has no local minima. 2) When input process and desired process are both Gaussian processes, then MPE function has the same optimum solution as the conventional Wiener solution for any p. 3) When input process and desired process are non-Gaussian processes, then MPE function may have better optimum solution than Wiener solution. Next, a least mean p-power (LMP) error adaptive algorithm is derived and some application examples are presented. Consequently, when the signal is corrupted by an impulsive noise, the adaptive algorithm with p=1 is preferred. Furthermore, when the signal is corrupted by noise or interference, the adaptive algorithm with proper choice of p may be preferred. >

Encoding and decoding video signals using adaptive filter switching criteria

Abstract: Reference frames are generated by selectively filtering blocks of decoded video frames. The decision whether to filter a block is based on a comparison of an energy measure value generated for the block and an energy measure threshold value corresponding to the quantization level used to encode the block. The energy measure threshold value for a given quantization level is selected by analyzing the results of encoding and decoding training video frames using that quantization level. The reference frames are used in encoding and decoding video frames using interframe processing.

Tree-structured nonlinear filters in digital mammography

Abstract: A new class of nonlinear filters with more robust characteristics for noise suppression and detail preservation is proposed for processing digital mammographic images. The new algorithm consists of two major filtering blocks: (a) a multistage tree-structured filter for image enhancement that uses central weighted median filters as basic sub-filtering blocks and (b) a dispersion edge detector. The design of the algorithm also included the use of linear and curved windows to determine whether variable shape windowing could improve detail preservation. First, the noise-suppressing properties of the tree-structured filter were compared to single filters, namely the median and the central weighted median with conventional square and variable shape adaptive windows; simulated images were used for this purpose. Second, the edge detection properties of the tree-structured filter cascaded with the dispersion edge detector were compared to the performance of the dispersion edge detector alone, the Sobel operator, and the single median filter cascaded with the dispersion edge detector. Selected mammographic images with representative biopsy-proven malignancies were processed with all methods and the results were visually evaluated by an expert mammographer. In all applications, the proposed filter suggested better detail preservation, noise suppression, and edge detection than all other approaches and it may prove to be a useful tool for computer-assisted diagnosis in digital mammography. >

Efficient packet demultiplexing for multiple endpoints and large messages

Abstract: This paper describes a new packet filter mechanism that efficiently dispatches incoming network packets to one of multiple endpoints, for example address spaces. Earlier packet filter systems iteratively applied each installed filter against every incoming packet, resulting in high processing overhead whenever multiple filters existed. Our new packet filter provides an associative match function that enables similar but not identical filters to be combined together into a single filter. The filter mechanism, which we call the Mach Packet Filter (MPF), has been implemented for the Mach 3.0 operating system and is being used to support endpoint-based protocol processing, whereby each address space implements its own suite of network protocols. With large numbers of registered endpoints, MPF outperforms the earlier BSD Packet Filter (BPF) by over a factor of four. MPF also allows a filter program to dispatch fragmented packets, which was quite difficult with previous filter mechanisms.

Orthogonal time-varying filter banks and wavelet packets

Abstract: Considers the construction of orthogonal time-varying filter banks. By examining the time domain description of the two-channel orthogonal filter bank the authors find it possible to construct a set of orthogonal boundary filters, which allows to apply the filter bank to one-sided or finite-length signals, without redundancy or distortion. The method is constructive and complete. There is a whole space of orthogonal boundary solutions, and there is considerable freedom for optimization. This may be used to generate subband tree structures where the tree varies over time, and to change between different filter sets. The authors also show that the iteration of discrete-time time-varying filter banks gives continuous-time bases, just as in the stationary case. This gives rise to wavelet, or wavelet packet, bases for half-line and interval regions. >

Optimum loop filter in hybrid coders

Abstract: Examines the role of the loop/interpolation filter in the motion compensation loop of hybrid coders. Using the Wiener filtering concept and the statistical model developed by Chen and Pang (1992), the optimum filter that minimises the prediction error has been found. The result is expressed in an explicit form in terms of a correlation parameter, /spl rho/ and an inaccuracy parameter, /spl alpha/. It explains many current practices in MPEG and H.261 coders, as well as the leakage predictor, 3-tap versus 8-tap filters and other related issues. The analysis shows that minimum bit rate can only be achieved if the loop filter matches the statistical characteristic of the motion-compensated signal. Furthermore, since the motion noise characteristic could be very different in the horizontal and vertical direction for many sequences, the decision to deploy the optimum filter should be made separately in the two directions. The paper also derives the scalar loop filter in DCT domain. The scalar filter is sub-optimal, but it requires less computational load than the spatial domain filter (64 versus 484 multiplications per 8/spl times/8 block). Experiments show that it performs almost as efficiently as the optimum 3-tap spatial domain filter, thus ascertaining that its performance has not been significantly compromised by the scalar requirement. Experimental simulations on test sequences confirm the theoretical optimum results, and indirectly show that the simple statistical model used in the derivation is adequate. >

A low-power, area-efficient digital filter for decimation and interpolation

Abstract: The area and power consumption of oversampled data converters are governed largely by the associated digital decimation and interpolation filters. This paper presents a low-power, area-efficient, mask-programmable digital filter for decimation and interpolation in digital-audio applications. Several architectural and implementation features reduce the complexity of the filter and allow its realization in a die area of only 3670 mils/sup 2/ (2.37 mm/sup 2/) in a 1-/spl mu/m CMOS technology. The use of simple multiplier-free arithmetic logic and a new memory addressing scheme for multi rate digital filters results in a power consumption of only 18.8 mW from a 5-V supply and 6.5 mW from a 3-V supply. The memory addressing scheme and the programmable functionality of the filter are general enough to implement a wide class of FIR and IIR single-rate and multi-rate digital filters. >

Finite impulse response neural networks with applications in time series prediction

Abstract: Traditional feedforward neural networks are static structures which simply map input to output. Motivated from biological considerations, a dynamic network is proposed which uses Finite Impulse Response (FIR) linear filters to model the processes of axonal transport, synaptic modulation, and membrane charge dissipation. Effectively all weights in the static feedforward network are replaced by adaptive FIR filters. A training algorithm based on gradient descent is derived for the FIR structure. The algorithm, termed temporal backpropagation, is shown to be a direct temporal and vectorial extension of the popular backpropagation algorithm. Various properties including computational complexity and learning characteristics are explored. The FIR network can be viewed as an adaptive nonlinear filter with applications encompassing those of traditional adaptive filters and systems. In this dissertation, we concentrate on the FIR network for use in nonlinear time series prediction. Various examples including laboratory data, chaotic time series, and financial data are studied. Iterated predictions and reconstruction of underlying chaotic attractors are used to demonstrate the capabilities of the network and methodology. The theoretical motivations for using networks in prediction are also addressed. In looking for a more direct method to derive temporal backpropagation, we introduce and prove a unifying principle called Network Reciprocity. The method, based on simple rules of block diagram manipulation, allows for an almost effortless formulation of neural network algorithms. The approach is illustrated by deriving a variety of algorithms including standard and temporal backpropagation, backpropagation-through-time for recurrent networks and control structures, an efficient method for training cascaded nonlinear filters, and algorithms for networks composed of Infinite Impulse Response (IIR) and lattice filters.

A constrained anti-Hebbian learning algorithm for total least-squares estimation with applications to adaptive FIR and IIR filtering

Abstract: In this paper, a new Hebbian-type learning algorithm for the total least-squares parameter estimation is presented. The algorithm is derived from the classical Hebbian rule. An asymptotic analysis is carried out to show that the algorithm allows the weight vector of a linear neuron unit to converge to the eigenvector associated with the smallest eigenvalue of the correlation matrix of the input signal. When the algorithm is applied to solve parameter estimation problems, the converged weights directly yield the total least-squares solution. Since the process of obtaining the estimate is optimal in the total least-squares sense, its noise rejection capability is superior to those of the least-squares-based algorithms. It is shown that the implementations of the proposed algorithm have the simplicity of those of the LMS algorithm. The applicability and performance of the algorithm are demonstrated through computer simulations of adaptive FIR and IIR parameter estimation problems. >

Adaptive model architecture and extended Kalman-Bucy filters

Abstract: In radar systems, extended Kalman-Bucy filters (EKBFs) are used to estimate state vectors of objects in track. Filter models accounting for fundamental aerodynamic forces on reentry vehicles are well known. A general model structure accommodating the dynamics of reentry vehicles in both exoatmospheric and endoatmospheric flight is presented. The associated EKBFs for these various models are described and the resulting associated parameter estimation and identification problems are discussed. The effects of position, velocity, drag, and aerodynamic lift are described within a nested set of EKBF models. >

DPLL bit synchronizer with rapid acquisition using adaptive Kalman filtering techniques

Abstract: A second-order DPLL with time-varying loop gains is applied to the symbol synchronization of burst mode data signals. An algorithm to control the DPLL loop gains is derived from adaptive Kalman filtering theory. Simulation results for the variable gain DPLL compared to a fixed gain DPLL demonstrate the improved acquisition performance. >

Multiple adaptive filter active noise canceller

Abstract: An active adaptive noise canceller (100) that does not require a training mode and operates over an extended noise bandwidth. The canceller partitions the noise bandwidth into frequency sub-bands, and multiple adaptive filter channels (120, 140) are employed, one for each sub-band, to cancel noise energy in the respective sub-bands. Each channel includes bandpass filters (121, 130) to restrict the channel to operation over only the particular sub-band, and delays are inserted in the operation of the filter weight updating. Because each channel is stable over its sub-band, the canceller operates over the extended noise bandwidth of all the sub-bands.