Showing papers on "Kernel adaptive filter published in 1989"

Multiple-Point Equalization in a Room Using Adaptive Digital Filters

Abstract: A method is presented for designing an equalization filter for a sound-reproduction system by adjusting the filter coefficients to minimize the sum of the squares of the errors between the equalized responses at multiple points in the room and delayed versions of the original electrical signal

Adaptive line enhancement by using an IIR lattice notch filter

Abstract: Two simple methods for retrieving a single sinusoid corrupted with noise are proposed. They are based on the lattice form realization of an adaptive infinite-impulse-response (IIR) notch filter. The IIR filter is a cascade of second-order all-pole and all-zero filters, and the coefficients of the finite-impulse-response (FIR) section are adapted. The proposed algorithms keep the poles of the filter inside the unit circle. The computer simulation results show that the algorithms have considerable potential in adaptive notch filter applications, especially when the input signal-to-noise ratio is low. >

Adaptive beamforming for noise reduction

Abstract: The invention provides an adaptive noise cancelling apparatus which operates to overcome a problem encountered in conventional noise cancelling circuitry when the signal-to-noise ratio at the sensor array is high--to wit, that the target signal is degraded, leading to poorer intelligibility. An apparatus constructed in accord with the invention selectively inhibits the adaptive filter from changing its filter values in these instances and, thereby, prevents it from generating a noise-approximating signal that will degrade the target component of the output signal.

Adaptive IIR filtering using parallel-form realizations

Abstract: Several parallel-form adaptive IIR (infinite impulse response) filters are presented, including a frequency-domain implementation based on the discrete Fourier transform and a recursive frequency-sampling structure. The performance of the frequency-domain adaptive IIR filter is investigated in a system identification application, which includes an analysis of its modeling capabilities and a discussion of the mean-square-error performance surface. Computer simulation results are presented to illustrate the robust convergence properties of the adaptive algorithm and to demonstrate the stability of the filter. >

Statistical Analysis of Median Subtraction Filtering with Application to Point Target Detection in Infrared Backgrounds

Abstract: The nonstationarity of infrared interference backgrounds which prevents the implementation of the usual optimum linear filtering techniques makes clutter suppression signal processing for point target detection in infrared surveillance systems a challenging and difficult problem. Hence, more robust filtering schemes are sought which will perform well in structured backgrounds where the underlying probability distribution defining that structure is not well known or characterized. This paper investigates a promising candidate spatial filter for point-like feature detection in infrared systems. The technique, known as median subtraction filtering, is a robust, nonlinear, order statistic type filter which exhibits highpass filter characteristics without the usual ringing associated with linear highpass filters. A quantitative analysis of the statistical properties of the median subtraction filter is presented, including analytic expressions for the output distribution of the filter (thus analytic expressions for the probability of detection and probability of false alarm), its autocorrelation function and spectral density function. Performance results of a signal processing simulation comparing a median subtraction filter with an adaptive linear filter of the LMS type using actual infrared video as input are also included.

Analysis of an adaptive technique for modeling sparse systems

Abstract: An effective technique for modeling sparse systems has been developed, and the error surface of the system is analyzed with respect to estimation noise. The technique requires a type of adaptive filter which is called an adaptive delay filter. An implementation of the adaptive delay filter is discussed that includes adaptive gains in addition to variable delay taps. The filter is especially applicable to modeling systems with a sparse impulse response. Less computation is required for a sparse system than with the conventional approach. The technique is tested with a variety of unknown systems using both white noise input and autoregressive input. It is shown that it works properly for both sparse and nonsparse systems in noise-free and noisy conditions. The performance of the technique is verified by a careful analysis of the error surface and the techniques for delay determination and corresponding gain adaption. >

Optimal maximum correlation filter for arbitrarily constrained devices

Abstract: Almost all coherent pattern recognition architectures are based on optical correlation of the input with a designed filter. However, the filter can be implemented via many different media, and each medium will impose different realizability constraints on the filter. That is, different media will have different regions of physical realizability. In the past, there has not been much work addressing the problem of designing an optimal filter given an arbitrary region of realizability. This paper presents the theory for just such an optimal filter design. A fast algorithm is presented to implement the theory. The algorithm is demonstrated with two examples.

Efficient algorithm for designing a ternary valued filter yielding maximum signal to noise ratio.

Abstract: An efficient algorithm for designing a ternary valued filter yielding the highest signal to noise ratio (SNR) is utlined. Numerical evaluations using the image of a tank indicate that using such a filter can provide an improvement in SNR of ~5 dB over the conventional binary phase-only filter (BPOF). This is superior to the 1-dB improvement obtained for that image by varying the threshold line angle (TLA) in filter binarization. Simulation results are presented. They agree with the numerically computed SNRs.

Adaptive digital filter having non-recursive and recursive filter elements

Abstract: An adaptive digital filter including a non-recursive part and a recursive part, and which can be updated in a simple and reliable manner. The recursive part of the filter has a plurality of separate, permanently set recursive filters (13-16) with different impulse responses, and a linear combination is formed with adaptive weighting factors (W0-W3) from the output signals of the recursive filters (13-16). The filter is updated by a single (e(n)) being utilized for updating the non-recursive part (11) of the filter and the adaptive weighting factors (W0-W3) in the recursive part of the filter.

Mean-squared error analysis of an adaptive notch filter

Abstract: A mean-square-error analysis of the steady-state coefficient fluctuation of an infinite impulse response (IIR) adaptive notch filter, whose coefficients are estimated by simple gradient and sign gradient algorithms, is presented. Regarding the magnitude and phase responses of the transfer function that is used to realize a second-order IIR adaptive notch filter, it is shown that the filter-coefficient estimation error can be studied by using first-order ordinary difference equations with stochastic input. Simple closed-form results are derived for the mean-square error of the steady-state coefficients. The results of computer experiments are presented to substantiate the analysis. >

Partitioned frequency domain adaptive filters

Abstract: Convergence characteristics of adaptive filters are influenad b y the statistical properties (correlation) of the input signal. In order t o remove this dependency, decordation can be applied which can be performed in fmquency domain by simple power normalisation of each sepamte frequency bin. This leads to the Frequency Domain Adaptive Filter (FDAF), in which the length of the transformation between timeand frequency-domain is choosen to be equal to the length N of the adaptive filter. However the relevant length Of this transformation is determined by the stotieticol properties of the input signal and needs not to be equal to N . By applying different partitioning schemes to the FDAFstructure it is shown that it is possible to decouple the length of the transformation and the length N of the adaptivejlter. -

Simulation Studies of Latency Measures of Components of the Event‐Related Brain Potential

Abstract: We compared the accuracy of P300 latency estimates obtained with different procedures under several simulated signal and noise conditions. Both preparatory and signal detection techniques were used. Preparatory techniques included frequency filters and spatial filters (single electrode selection and Vector filter). Signal detection techniques included peak-picking, cross-correlation, and Woody filter. Accuracy in the latency estimation increased exponentially as a function of the signal-to-noise ratio. Both Woody filter and cross-correlation provided better estimates than peak-picking, although this advantage was reduced by frequency filtering. For all signal detection techniques, Vector filter provided better estimates than single electrode selection. Large component overlap impaired the accuracy of the estimates obtained with both single electrode selection and Vector filter, but with Vector filter impairment occurred only when the overlapping component had a scalp distribution that was similar to the scalp distribution of the signal component. The effects of varying noise characteristics, P300 duration and latency, and the parameters of Vector filter were also investigated.

System and method for providing digital filter coefficients

Abstract: There is disclosed a system and method for generating coefficients for use in a digital filter. The coefficients are generated utilizing an iterative adaptive process employing a least mean square process wherein the filter coefficients are updated by an amount during each iteration dependent upon the stochastic average of the gradient generated during prior iterations. The response of a filter standard to an applied input signal is combined with a response of the adaptive filter coefficients to generate, during each iteration, an error signal. If the error signal is less than a predetermined standard, the iterative process is stopped, and the last used filter coefficients are utilized as the final filter coefficients of the digital filter.

The analysis of the continuous-time LMS algorithm

Abstract: A continuous-time analog adaptive filter is suggested using the digital prototype. The continuous-time LMS (least-mean squares) algorithm is then described by a set of simultaneous first-order equations. The adaptive gain is shown to be unbounded theoretically. >

Echo canceller with means for determining filter coefficients from autocorrelation and cross-correlation coefficients

Abstract: In a data transmission system where a first signal partially leaks as an echo from a first transmission line to a second transmission line through a hybrid circuit to form a mixed signal of the echo and a second signal on the second transmission line, an echo canceller is used for cancelling the echo by producing an echo replica at a transversal filter according to filter coefficients and subtracting the echo replica from the mixed signal. In order to reliably generate the filter coefficient for a reduced time duration, a series of autocorrelation coefficients of the first signal and a series of cross-correlation coefficients between the first and the mixed signals are calculated at calculators and the filter coefficients are determined from both of the autocorrelation and the cross-correlation coefficient series at a coefficient determining circuit. The coefficient determining circuit may be an arithmetic circuit for solving simultaneous linear equations. Another circuit for determining the filter coefficients may be a circuit where a first filter coefficient is determined by detecting the maximum value and the corresponding delay time from the series of cross-correlation coefficients, making a fresh series of cross-correlation coefficients with reference to the maximum values, the delay time and the first filter coefficient, then, determining a second filter coefficient from the fresh series. Then, filter coefficients are determined by repetition of the similar operation.

Method and filter for enhancing a noisy speech signal

Abstract: A filter for filtering a speech signal to reduce acoustic noise is disclosed. In accordance with the inventive filter, the parameters of an all-pole vocal tract model are first estimated from the noisy signal using a least mean square algorithm as if no noise were present, and then the speech signal is filtered using an approximate limiting Kalman filter constructed according to the estimated parameters.

Adaptive filter with coefficient averaging and method

Abstract: An adaptive transversal filter is characterized by a first adaptive filter for generating a plurality of estimated impulse response coefficients representing an impulse response of a transmission path. An averaging circuit is coupled with the first adaptive filter, and generates a plurality of average estimated impulse response coefficients having values in accordance with the average values over a most recent time interval of associated ones of the estimated impulse response coefficients, and a second adaptive filter receives the average estimated coefficients. The average estimated impulse response coefficients more closely represent and have less variance with respect to the actual impulse response of the transmission path than do the estimated coefficients, and the second filter generates an estimate of an echo signal through a process including convolution of the average estimated coefficients and an input signal. The adaptive transversal filter is particularly suited for use in an adaptive hybrid circuit.

Dual optimality of the phase-only filter.

Abstract: A measure of the peak-to-sidelobe performance for correlation filters is defined. The phase-only filter is then shown to be optimum with respect to the peak-to-sidelobe criterion. The phase-only filter has been previously shown to give optimum signal-to-noise performance. Thus, under the assumption of a unit modulus phase device, optimum peak-to-sidelobe and signal-to-noise performance can be obtained simultaneously.

Double-window Hodges-Lehman (D) filter and hybrid D-median filter for robust image smoothing

Abstract: The double window Hodges-Lehman filter (DWD-filter) and a hybrid D-median filter (HDM-filter) for robust image smoothing are proposed. An adaptive mixture of the median and the D-filter, the HDM filter first makes decisions about the presence of edges on the basis of a two-way classification of pixels near and around the pixel to be filtered. Subsequently, straightforward D-filtering is used in the absence of edges, and median filtering is used in the presence of edges. The DWD filter uses two windows and D-filtering. The smaller window is used to preserve the details, then the larger window to provide for sufficient smoothing. Detailed simulation results show that the HDM-filter, while retaining all the good properties of the DWD filter, consistently performs better, in terms of signal-to-noise ratio, than the DWD filter and a number of other filters, including the median filter. The DWD filter is shown to have simpler structure, although not necessarily lesser computational complexity. >

A tight upper bound of the average absolute error in a constant step-size sign algorithm

Abstract: A direct performance index of the adaptive filtering sign algorithm (SA) is the average absolute error (AAE) at the output of the filter. Adopting this performance index, an easy analysis of SA is achieved under a weak assumption. It is proved, for both deterministic and random inputs to the filter, that the AAE has a tight upper bound that exceeds the minimum AAE by half the product of the step size and power of the filter input. The assumption used is existence of average squared and average absolute values of filter input signals. A practical interest of the result is that it provides a formula for the biggest step size as a function of tolerable adaptation-noise-to-desired-signal ratio. >

Comparison between median filtering and vertical edge controlled interpolation for flicker reduction

Abstract: A vertical-temporal median filter and adaptive vertical-edge-controlled interpolation are described, using a field frequency doubled to 100 Hz (120 Hz). The filter is found to have good properties for flicker reduction in TV systems, but it produces additional disturbing alias components and movement defects in the vertical direction. A major advantage of the adaptive filter over the median filter is the ease with which alias components are suppressed. Furthermore, vertical-edge-controlled interpolation is insensitive to noise and the subcarrier in standard TV receivers, since these disturbances can be prevented by pre- and postfiltering within the edge detector. The filter and interpolation hardware is limited to one field memory for a noninterlace conversion, or two field memories when the field frequency is doubled. By comparison, a satisfactory motion-adaptive filter using frame delays needs three field memories and an additional one for converting the field frequency. >

A new connectionist model based on a non-linear adaptive filter

Abstract: A connectionist model that is introduced based on the nonlinear extension of adaptive filter theory is introduced It is shown that the model converges in the learning process to a global optimum Experimental results indicate that the rate of convergence is considerably faster than has been reported for other models It is concluded that the extended space approach leads to networks that can, with sufficient extension, synthesize any nonlinear discriminant function while maintaining unimodality The adaptive filter knowledge also allows analytical solutions to the vital problem of parameter tuning, thus allowing good first-run performance on practical data >

Adaptive digital filter which is responsive to the rate of change of an input signal

Abstract: The time constant of an adaptive digital filter is regulated as a function of the magnitude of the rate of change of the input signal to the filter. When the input signal has a large step input or it changes rapidly, the time constant is shortened; however when the input signal has a small step input or it changes more slowly, the time constant of the filter is increased.

Constrained adaptive filtering algorithms: asymptotic convergence properties for dependent data

Abstract: The convergence properties of constrained adaptive filtering algorithms are established. The constraint is in the form of a bounded set in which the filter's coefficients must lie. A recursive procedure that converges to the deterministic solution of the constrained linear mean-square estimation problem is obtained, using an appropriate contraction mapping. The recursion is used to derive the adaptive algorithm for the filter coefficients. Bounds on the mean-square error of the coefficients. Bounds on the mean-square error of the estimates of the filter coefficients and on the excess error of the input signal estimate are derived for processes that are either strong mixing or asymptotically uncorrelated. The algorithms use a moving window of size n on the data from one adaptation step to the next. However, tighter bounds can be obtained when a skipped sampling mechanism is used. >

Design of an on-line multiply-add module for recursive digital filters

Abstract: An online multiply-add module that allows high filter sampling rates when used to implement the direct form II second-order filter structure is described Important characteristics of online arithmetic are that it produces most significant digit first and that its digit cycle time is independent of the data wordlength These features not only permit high-speed filtering, but also allow the elimination of all nonlinear oscillation in the filter without affecting the sampling rate, and effectively eliminate scaling of the filter's input data The derivation of the online multiply-add algorithm and its hardware design using a 15- mu m CMOS standard cell library are presented A method for eliminating nonlinear oscillations by increasing the filter's working precision is described >

A generalization of morphological filters using multiple structuring elements

Abstract: A new class of morphological filters is proposed for smoothing an image contaminated with noise. A multiple model that includes the combination of linear and nonlinear operations is used in the design of the new filter. The performance of the averaging version of this new filter is similar to that of the alpha-trimmed mean filter. The structure-preserving properties of this new filter depend on the values assigned to the coefficients in the filter. The idempotent property is obtained when a closing-min and opening-max version of the filter is used. The root structure of the output signal is also investigated. >

QRD-Based Lattice Filter Algorithms.

Abstract: A new lattice filter algorithm for adaptive filtering is presented. In common with other lattice algorithms for adaptive filtering, this algorithm only requires 0(p) operations for the solution of a p-th order problem. The algorithm is derived from the QR-decomposition (QRD) based recursive least squares minimisation algorithm and hence is expected to have superior numerical properties compared with other fast algorithms. This algorithm contains within it a new algo-rithm for solving the least squares linear prediction problem. The algorithms are presented in two forms: one that in-volves taking square-roots and one that does not. Some preliminary computer simulation results are presented that in-dicate that the output residuals produced by the new, fast adaptive filtering algorithm are in good agreement with those from the more established, 0(p 2 ) QRD recursive least squares minimisation algorithm.

Adaptive nonlinear control an estimation-based algorithm

Abstract: This has been succesfully performed in the case of a robot arm with as many motors as axis. Two rather different methcxls have been used. For example: [Mi-Go] proposes an adaptive controller where the estimation of p ' is performed without taking into account the control law to be used, the certainty equivalence law is feedback tinearisation, and some additive terms are added to compensate for the effect of updating t~. This is an estimation-based approach. LSI-Li] proposes to update : to make a global positive function decrease. The certainty equivalence control law is not

Nonlinear IIR adaptive filtering using a bilinear structure

Abstract: A nonlinear IIR (infinite-impulse-response) adaptive filter that is based on a Volterra polynomial realized by a set of bilinear systems is presented. Each bilinear system corresponds to a cascade connection of linear systems and multipliers. This allows the extension of some linear adaptive concepts. Nonlinear IIR adaptive filters have an advantage over FIR (finite-impulse-response) Volterra filters in that in some applications they may result in less computation. The results of a simulation example show the applicability and practical convergence rate of the nonlinear IIR adaptive filter presented. >

Asymptotic properties of an adaptive beam former algorithm

Abstract: The asymptotic properties of a recursive adaptive beam former algorithm are studied. Both decreasing-gain and constant-gain cases are treated. For the case of decreasing gain the mean square convergence result is obtained, whereas for constant gain a sharp bound is derived, and asymptotic analysis for the normalized error is carried out. The analysis provides a clear picture of the local behaviour of the iterates near the optimal value. A sequence of scale deviations or normalized errors is shown to converge to a Gauss-Markov diffusion process which satisfies a stochastic differential equation. >