scispace - formally typeset
Search or ask a question

Showing papers on "Adaptive algorithm published in 1988"


Journal ArticleDOI
TL;DR: In this article, an integrated approach to the design of practical adaptive control algorithms is presented, where many existing ideas are brought together, and the effect of various design parameters available to a user is explored.
Abstract: An integrated approach to the design of practical adaptive control algorithms is presented. Many existing ideas are brought together, and the effect of various design parameters available to a user is explored. The theory is extended by showing how the problem of stabilizability of the estimated model can be overcome by running parallel estimators. It is shown how asymptotic tracking of deterministic set points can be achieved in the presence of unmodeled dynamics. >

590 citations


Journal ArticleDOI
TL;DR: In this article, a two-dimensional least-mean-square (TDLMS) adaptive algorithm based on the method of steepest decent is proposed and applied to noise reduction in images.
Abstract: A two-dimensional least-mean-square (TDLMS) adaptive algorithm based on the method of steepest decent is proposed and applied to noise reduction in images. The adaptive property of the TDLMS algorithm enables the filter to have an improved tracking performance in nonstationary images. The results presented show that the TDLMS algorithm can be used successfully to reduce noise in images. The algorithm complexity is 2(N*N) multiplications and the same number of additions per image sample, where N is the parameter-matrix dimension. Analysis and convergence properties of the LMS algorithm in the one-dimensional case presented by other authors is shown to be applicable to this algorithm. The algorithm can be used in a number of two-dimensional applications such as image enhancement and image data processing. >

342 citations


Journal ArticleDOI
TL;DR: An effective h-version finite element adaptive strategy combined with mesh regeneration is presented and a nearly optimal mesh of predicted accuracy can be obtained in one or two adaptive process steps.
Abstract: An effective h-version finite element adaptive strategy combined with mesh regeneration is presented. This is based on the error estimator developed in Reference 1. The rate of convergence of the adaptive procedure has been tested for some examples and very strong convergence observed. Unlike some existing h-version adaptive procedures, a nearly optimal mesh of predicted accuracy can be obtained in one or two adaptive process steps.

188 citations


Journal ArticleDOI
Robert J. Wittrock1
TL;DR: An algorithm that schedules the loading of parts into a manufacturing line to minimize the makespan and secondarily to minimize queueing is presented.
Abstract: Consider a manufacturing line that produces parts of several types. Each part must be processed by at most one machine in each of several banks of machines. This paper presents an algorithm that schedules the loading of parts into such a line. The objective is primarily to minimize the makespan and secondarily to minimize queueing. The problem is decomposed into three subproblems and each of these is solved using a fast heuristic. The most challenging subproblem is that of finding a good loading sequence, and this is addressed using workload concepts and an approximation to dynamic programming. We make several extensions to the algorithm in order to handle limited storage capacity, expediting, and reactions to system dynamics. The algorithm was tested by computing schedules for a real production line, and the results are discussed.

180 citations


Journal ArticleDOI
TL;DR: In this article, a methode adaptative d'elements finis, basee sur une estimation d'erreur optimale de norme maxima for les problemes elliptiques lineaires, is proposed.
Abstract: On propose une methode adaptative d'elements finis, basee sur une estimation d'erreur optimale de norme maxima pour les problemes elliptiques lineaires

180 citations


Journal ArticleDOI
TL;DR: In this paper, an automatic gain control (AGC) scheme is introduced for adaptive algorithms that are used extensively in many applications, which is realized by using an estimate of the cross correlation between the adaptation error and the input signal to control the gain of the adaptive algorithm.
Abstract: An automatic gain control (AGC) scheme is introduced for adaptive algorithms that are used extensively in many applications. The scheme is realized by using an estimate of the cross correlation between the adaptation error and the input signal to control the gain of the adaptive algorithm. When the cross correlation is high, the gain is also high, and the adaptive algorithm is in an 'active' state. When the error and the input signals are uncorrelated, the gain is closed to zero, and the adaptive algorithm is put in an 'asleep' state. Thus, adaptive algorithms with such AGC are comparatively insensitive to disturbances appearing on the system output measurement, which can drive conventional adaptive algorithms away from the achieved adaptation. A fast, efficient algorithm for estimation of the cross-correlation coefficient of adaptive error and input is proposed. >

102 citations


Journal ArticleDOI
TL;DR: An adaptive method that utilizes the ordering property of the LSP parameters is introduced and a combination of this adaptive algorithm with nonuniform-step-size quantization is shown to be very effective for encoding the L SP parameters.
Abstract: The performance of several algorithms for the quantization of the LSP (line spectrum polar) parameters is studied. An adaptive method that utilizes the ordering property of the LSP parameters is introduced. A combination of this adaptive algorithm with nonuniform-step-size quantization is shown to be very effective for encoding the LSP parameters. The performance of the different quantization schemes is studied on several sequences of speech samples. For the spectra distortion measure, appropriate performance comparisons between the different quantization schemes are rendered. >

87 citations


Journal ArticleDOI
TL;DR: A global convergence theory is presented using recent methods for analyzing robustness properties of adaptive control algorithms and it is argued that within this framework, the analysis of the properties of the corresponding adaptive control algorithm essentially reduces to the issue of robustness to unmodelled dynamics.

81 citations


Journal ArticleDOI
TL;DR: Optimum combining for diversity antennas at the mobile is discussed in this article, where the aim is to add the wanted signal vectors in a maximum ratio sense, while interferers are weighted so that their resultant is in a permanent deep fade.
Abstract: Optimum combining for diversity antennas at the mobile is discussed. Effectively, the aim is to add the wanted signal vectors in a maximum ratio sense, while interferers are weighted so that their resultant is in a permanent deep fade. Even if there are not enough degrees of freedom available to accomplish this fully, an optimum solution can still be found. Many interpretations from conventional array technology do not apply to the mobile communications case and the mechanism of optimum combining for array branch signals rather than discrete spatial signals is reviewed. Physical interpretation of the formulation is emphasized throughout. Problems with the adaptive algorithm and its implementation are also identified. Sample matrix inversion is shown to be a likely algorithm to apply in vehicular mobile communications receivers. A worst case example gives an idea of the required computation rates. >

75 citations


Journal ArticleDOI
TL;DR: A simple algorithm, based on Newton's method, is constructed, which permits asymptotic minimization of L1 distance for nonparametric density estimators and is applicable to multivariate kernel estimator, multivariate histogram estimators, and smoothed histograms estimators such as frequency polygons.

68 citations


Journal ArticleDOI
TL;DR: It is shown that postfilters based on higher order LPC (linear predictive coding) models can provide very low distortion in terms of special tilt and can provide better speech enhancement than circuits based on the backward-adaptive pole-zero predictor in ADPCM (adaptive digital pulse code modulation).
Abstract: It is shown that postfiltering circuits based on higher order LPC (linear predictive coding) models can provide very low distortion in terms of special tilt. Thus, they can provide better speech enhancement than circuits based on the backward-adaptive pole-zero predictor in ADPCM (adaptive digital pulse code modulation). Quantitative criteria for designing postfiltering circuits based on higher-order LPC models are discussed. These postfilters are particularly attractive for systems where high-order LPC analysis is an integral part of the coding algorithm. In a subjective test that used a computer-simulated version of these circuits, enhanced ADPCM obtained a mean opinion score of 3.6 at 16 kb/s. >

Proceedings ArticleDOI
11 Apr 1988
TL;DR: It is shown that the computationally most efficient 7N form of fast recursive least-squares transversal filter (FTF) is exponentially unstable, and by introducing redundancy in this algorithm, feedback of numerical errors becomes possible.
Abstract: The problem of numerical stability of fast recursive least-squares transversal filter (FTF) algorithms is addressed. The prewindowing case with exponential weighting is considered. A framework for the analysis of the error propagation in these algorithms is developed. Within this framework, it is shown that the computationally most efficient 7N form (dealt with by G. Carayanmis et al. (1983) and by J.M. Cioffi (1984)) is exponentially unstable. By introducing redundancy in this algorithm, feedback of numerical errors becomes possible. This leads to a numerically stable FTF algorithm with complexity 9N. The results are presented for the complex multichannel joint-process filtering problem. >

Journal ArticleDOI
TL;DR: A medium-band speech coder that uses a weighted vector quantization scheme in the transformed domain and adaptively weighted matching is used instead of conventional adaptive bit allocation, which means the residual signal can be reconstructed by the decoder, even if the spectral envelope parameters are destroyed due to transmission errors.
Abstract: A medium-band speech coder is proposed that uses a weighted vector quantization scheme in the transformed domain. The linear prediction residue is transformed and vector-quantized. In order to control the quantization errors in the transformed domain, adaptively weighted matching is used instead of conventional adaptive bit allocation. Therefore, the residual signal can be reconstructed by the decoder, even if the spectral envelope parameters are destroyed due to transmission errors. This coder is also capable of maintaining higher SNR (signal-to-noise ratio) performance than time-domain vector quantization coders for a wide range of computation complexities and bit rates. Coded speech is natural and unaffected by background noise. The mean opinion score for this coder at 7.2 kb/s is comparable to that of 5.5-bit log PCM coded speech sampled at 6.4 kHz. >

Journal ArticleDOI
TL;DR: In this paper, an adaptive finite element procedure is developed for the transient analysis of nonlinear shells, which employs fission and fusion of elements to adaptively refine and coarsen the mesh.

Journal ArticleDOI
TL;DR: The time (shift) delay parameter between two signals is modeled as a finite-impulse response filter whose coefficients are samples of a sinc function, which involves less computation and the elimination of interpolation needed in previous approaches to obtain nonintegral time-delay estimates.
Abstract: The time (shift) delay parameter between two signals is modeled as a finite-impulse response filter whose coefficients are samples of a sinc function. The time-domain LMS (least-mean-squares) adaptive algorithm is used, but only the weight with the largest magnitude is updated, which involves less computation. The result is a faster adaptation and the elimination of interpolation needed in previous approaches to obtain nonintegral (multiples of sampling period) time-delay estimates. >

Journal Article
TL;DR: In this article, the authors proposed a neuromimetic solution based on a recursive and fully-interconnected network of operators, where the weights of the connections are varying according to an adaptation rule, which executes an independence test of the network's output.
Abstract: The problem of sources discrimination, very classical in Signal Processing field, is also an actual problem in biological systems . Biological sensors are sensitive to many sources, so the Central Nervous System processes typically multidimensional signais, each component of which is an unknown mixture of unknown sources, assumed independent . The neuromimetic solution, proposed in this paper, is based on a recursive and fully-interconnected network of operators. The weight of the connections are varying according to an adaptation rule, which executes an independence test of the network outputs . With regard to adaptation rudes used in adaptive filtering, here the adaptive increment is achieved necessarily by the product of two non-linear functions . Some experimental results, in Signal Processing and Image Processing fields, show the efficiency of this adaptive algorithm . We proue also the possible generalization of this algorithm in the case of more complex (non-linear, degenerated, etc .) mixtures . This algorithm points out a new concept of Independent Components Analysis, more powerful than this one of Principal Components Analysis, and applicable in the general frame of data analysis.

Journal ArticleDOI
TL;DR: In this paper, improved versions of an anticipative adaptive array are examined that provide efficient compensation by adapting the complex weights at each antenna element to the appropriate values for a carrier frequency before that frequency is received.
Abstract: To fully utilize the theoretical processing gain achievable when an adaptive array and frequency hopping are combined, frequency compensation is required. Improved versions of an anticipative adaptive array are examined that provide efficient compensation by adapting the complex weights at each antenna element to the appropriate values for a carrier frequency before that frequency is received. The underlying adaptive algorithm used is the maximum algorithm. Computer simulation results are used to compare the different versions of anticipative processing. These results show that an appropriate version ensures the rapid convergence of weights to values that provide wideband nulling of the interference and noise. >

Journal ArticleDOI
TL;DR: The simulations suggest that sort smoothing times are sufficient for rapid weight convergence without large fluctuations in the power estimates significantly affecting transient weight behavior.
Abstract: A general filtering scheme is presented for obtaining an input power estimate for setting the convergence parameter mu separately in each frequency bin of a frequency-domain LMS adaptive filter (FDAF) algorithm. A linear filtering operation is performed on the magnitude square of the input data and incorporated directly into the algorithm as a data-dependent time-varying stochastic mu (n). The mean performance of the weighted normalized frequency domain LMS algorithm (WNFDAF) is analyzed using independent and identically distributed Gaussian data, and the results are validated by the Monte Carlo simulations of the algorithm. The simulations are also used to study the weight transient behavior. The simulations suggest that sort smoothing times are sufficient for rapid weight convergence without large fluctuations in the power estimates significantly affecting transient weight behavior. >

Proceedings ArticleDOI
27 Mar 1988
TL;DR: The results indicate that, under heavy loads, the usual policy of placing jobs where they will incur the shortest expected delay leads to inefficient system performance, and a novel adaptive algorithm is introduced having a performance much closer to optimal.
Abstract: The authors consider the problem of job placement in load-sharing algorithms for large heterogeneous distributed computing environments. They present simulation results using a simple model; the results indicate that, under heavy loads, the usual policy of placing jobs where they will incur the shortest expected delay leads to inefficient system performance. Thus, purely greedy policies are not sufficient; the authors identify a simple threshold algorithm that does significantly better. The authors introduce a novel adaptive algorithm having a performance much closer to optimal. >

Proceedings ArticleDOI
12 Jun 1988
TL;DR: A technique is presented for identifying the impulse response of a nonminimum phase channel based solely on observations of the channel output using a two-step estimation procedure whereby the channel input is first estimated and then used in conjunction with the observed channel output to determine a least-squares model of the actual channel.
Abstract: A technique is presented for identifying the impulse response of a nonminimum phase channel based solely on observations of the channel output. The technique uses a two-step estimation procedure whereby the channel input is first estimated and then used in conjunction with the observed channel output to determine a least-squares model of the actual channel. Estimation of the channel input is accomplished through equalisation, demodulation, and remodulation of the channel output. The constant-modulus adaptive algorithm (CMA) is used in the equalization process. The technique is applicable to channels carrying quadrature amplitude modulation (QAM), frequency modulation (FM), and frequency-shift keyed (FSK) modulation. In addition to identifying the channel response, the technique also generates an estimate of the additive cochannel interference. >

Proceedings ArticleDOI
11 Apr 1988
TL;DR: Simulation results are presented which demonstrate that the proposed adaptive filtering algorithm's performance is comparable to RLS, and that it is quite robust with respect to finite-wordlength implementation.
Abstract: An adaptive filtering algorithm is introduced which is largely immune to the deleterious effects of colored inputs, yet requires only O(N) computation. Simulation results are presented which demonstrate that the proposed algorithm's performance is comparable to RLS (recursive least squares), and that it is quite robust with respect to finite-wordlength implementation. >

Proceedings ArticleDOI
01 Jan 1988
TL;DR: An adaptive technique and its analog and digital realizations to perform synchronous amplitude demodulation to take advantage of the tracking capability of gradient techniques and is similar to the LMS adaptive algorithm.
Abstract: This paper introduces an adaptive technique and its analog and digital realizations to perform synchronous amplitude demodulation. The algorithm takes advantage of the tracking capability of gradient techniques. The realizations for this algorithm require minimal hardware compared to other implementations for synchronous amplitude demodulation. Either the digital or the analog realization requires at most two (2) multipliers, an adder and a subtractor. Low pass filtering will only be required for high accuracy applications. The technique and realizations introduced in this paper rely on the availability of both the modulated carrier signal and the reference carrier. The algorithm presented is similar to the LMS adaptive algorithm. The coefficients of the adaptive structure track the message signal to be detected. Simu- lation results are presented to demonstrate the effect of the sampling frequency f/sub s/, the carrier frequency f. and the message frequency f/sub m on the performance of algorithm. The algorithm was implemented in VLSI hardware. Experimental results of this implementation are also presented.

Journal ArticleDOI
TL;DR: In this paper, a least-mean-square (LMS) adaptive algorithm for calculating the discrete Hartley transform (DHT) is presented, where the transform kernel of the DHT serves as the input vector and the input signal to be analysed is regarded as the "desired response" for the adaptive process.
Abstract: A least-mean-square (LMS) adaptive algorithm for calculating the discrete Hartley transform (DHT) is presented. The transform kernel of the DHT serves as the input vector and the input signal to be analysed is regarded as the ‘desired response’ for the adaptive process. For a proper choice of convergent factor, i.e. u = 1/2, the ‘LMS DHT analyser’ will provide an exact N-sample DHT. All the operations involved are real. Incorporation of one new sample requires only one adaptation.

Journal ArticleDOI
01 Jan 1988
TL;DR: The FOBA is the frequency-domain implementation of the recently proposed optimum block algorithm (OBA) and results in computational savings in comparison to the OBA and in performance enhancement relative to thefrequency-domain LMS algorithm.
Abstract: A time-varying convergence factor mu is proposed for the frequency-domain LMS (least-mean-square) adaptive algorithm, which results in the frequency-domain optimal block algorithm (FOBA). The FOBA is the frequency-domain implementation of the recently proposed optimum block algorithm (OBA). The FOBA results in computational savings in comparison to the OBA and in performance enhancement relative to the frequency-domain LMS algorithm. >

Journal ArticleDOI
TL;DR: A method is presented to measure the echo path response using pseudonoise sequences and the autocorrelation properties of these sequences are shown to reduce the error in measurement.
Abstract: A method is presented to measure the echo path response using pseudonoise sequences. The autocorrelation properties of these sequences are shown to reduce the error in measurement. The optimal choice of taps to achieve echo cancellation is evaluated. This scheme is compared to the LMS adaptive algorithm. The LMS algorithm can achieve the same level of cancellation with proper choice of mu . However, the number of iterations required has not been considered. The optimum choice of taps is evaluated. >

Journal ArticleDOI
TL;DR: An adaptive optimization algorithm using a dynamic identification scheme with a bilevel forgetting factor (BFF) has been developed and the simulation results show superiority of this method to other methods when applied to maximize the cellular productivity of a continuous culture of baker's yeast.
Abstract: An adaptive optimization algorithm using a dynamic identification scheme with a bilevel forgetting factor (BFF) has been developed. The simulation results show superiority of this method to other methods when applied to maximize the cellular productivity of a continuous culture of baker's yeast, Saccharomyces cerievisiae. Within the limited ranges of tuning parameters tested the BFF algorithm is found to be superior in terms of initial optimization speed and accuracy and reoptimization speed and accuracy when there is an external change and long term stability (removal of “blowing up” phenomena). Algorithms tested include those based on a constant forgetting factor, an adaptive variable forgetting factor (VFF) and moving window (MW) identification.

Journal ArticleDOI
TL;DR: In this article, it is shown that the parameters appearing in these nonminimal models can be uniquely estimated if and only if a certain design identity has a unique solution, and the result is used to develop persistency of excitation results for these models.
Abstract: It is frequently convenient to use specially structured nonminimal models for parameter estimation such as in the case of direct adaptive control where the model is parameterized in terms of the desired control law parameters. This is done, for example, in direct model reference adaptive control and in direct pole assignment adaptive control algorithms. It is shown that the parameters appearing in these nonminimal models can be uniquely estimated if and only if a certain design identity has a unique solution. The result is used to develop persistency of excitation results for these models. >

Journal ArticleDOI
TL;DR: It is shown that an adaptive algorithm using Runge-Kutta methods gives modest to significant computational savings over the use of a single implicit Runge, Kutta solution method.

Proceedings ArticleDOI
15 Jun 1988
TL;DR: The problem is solved using a self-tuner based in indirect adaptive pole placement using a standard algorithm that has no difficulties in coping with the problem and the specified parameter variations.
Abstract: In this paper the problem is solved using a self-tuner based in indirect adaptive pole placement. This design approach fits nicely to the specifications given. The design method for the case of known parameters is first presented. The adaptive algorithm is then given. The standard algorithm has no difficulties in coping with the problem and the specified parameter variations. Some special features of the given problem are then discussed and several variations are then given.

Journal ArticleDOI
M. Dahleh1
TL;DR: In this article, a sufficient condition for the adaptive stabilization of a large class of delay systems modeled by functional differential equations is given, where knowledge of the order of a finite dimensional controller, such that for every system in the class there exists a stabilizing controller of that order, is shown to constitute sufficient a priori information.