The Experts below are selected from a list of 246 Experts worldwide ranked by ideXlab platform
Eva Ceulemans - One of the best experts on this subject based on the ideXlab platform.
-
PCovR2: A flexible principal covariates regression approach to parsimoniously handle Multiple Criterion variables
Behavior Research Methods, 2021Co-Authors: Sopiko Gvaladze, Marlies Vervloet, Katrijn Deun, Henk A. L. Kiers, Eva CeulemansAbstract:Principal covariates regression (PCovR) allows one to deal with the interpretational and technical problems associated with running ordinary regression using many predictor variables. In PCovR, the predictor variables are reduced to a limited number of components, and simultaneously, Criterion variables are regressed on these components. By means of a weighting parameter, users can flexibly choose how much they want to emphasize reconstruction and prediction. However, when datasets contain many Criterion variables, PCovR users face new interpretational problems, because many regression weights will be obtained and because some criteria might be unrelated to the predictors. We therefore propose PCovR2, which extends PCovR by also reducing the criteria to a few components. These Criterion components are predicted based on the predictor components. The PCovR2 weighting parameter can again be flexibly used to focus on the reconstruction of the predictors and criteria, or on filtering out relevant predictor components and predictable Criterion components. We compare PCovR2 to two other approaches, based on partial least squares (PLS) and principal components regression (PCR), that also reduce the criteria and are therefore called PLS2 and PCR2. By means of a simulated example, we show that PCovR2 outperforms PLS2 and PCR2 when one aims to recover all relevant predictor components and predictable Criterion components. Moreover, we conduct a simulation study to evaluate how well PCovR2, PLS2 and PCR2 succeed in finding (1) all underlying components and (2) the subset of relevant predictor and predictable Criterion components. Finally, we illustrate the use of PCovR2 by means of empirical data.
Guido M. Cortelazzo - One of the best experts on this subject based on the ideXlab platform.
-
A technique for Multiple Criterion approximation of FIR filters in magnitude and group delay
IEEE Transactions on Signal Processing, 1995Co-Authors: Giancarlo Calvagno, Guido M. Cortelazzo, Gian Antonio MianAbstract:In spite of the attention received by nonlinear phase (NLP) FIR filter design, the "best" way to solve this problem is still open to debate. The formulation of nonlinear phase FIR filter design in terms of simultaneous magnitude and group-delay approximation addresses the two parameters of ultimate interest for applications. The simultaneous minimization of these two functions (one of which, the group delay, rational) is approached on the basis of an original extension of the differential correction algorithm. The proposed design tool enjoys interesting theoretical properties and works very effectively. The filters obtained according to the Multiple Criterion optimization (MCO). Formulation are compared against filters that are optimal in the complex Chebychev norm. Then, the flexibility characteristic of MCO formulations of trading off between magnitude and group-delay performance is exemplified. >
-
ICASSP - A comparison between complex approximation and Multiple Criterion optimization in FIR filter design
[Proceedings] ICASSP 91: 1991 International Conference on Acoustics Speech and Signal Processing, 1991Co-Authors: Giancarlo Calvagno, Guido M. Cortelazzo, Gian Antonio MianAbstract:The authors introduce an algorithm for simultaneous magnitude and group-delay design of FIR (finite impulse response) filters, a Multiple Criterion optimization problem for which no characterization theory is presently available. The algorithm, derived from differential correction, has global convergence. An experimental comparison with a method for complex polynomial approximation, a problem whose mathematical characterization is known, yields very useful and consistent results. The authors compare the results of two filter design formulations which are conceptually similar but formally different, and they present data potentially useful for the mathematical characterization of simultaneous polynomial approximation in magnitude and group-delay. >
-
ICASSP - The use of Multiple Criterion optimization for the simultaneous phase and magnitude design of IIR digital filters
ICASSP '82. IEEE International Conference on Acoustics Speech and Signal Processing, 1Co-Authors: Guido M. Cortelazzo, M. LightnerAbstract:In this paper we investigate for the first time the applicability of the concepts and algorithms of Multiple Criterion Optimization to the problem of optimally trading-off magnitude and phase in IIR digital filters design. Particular attention is paid to the mathematical formulation of the simultaneous magnitude and phase design problem. Three different design criteria are introduced. The special modifications of a standard algorithm [9] necessary for filter design are discussed. Examples of what can be expected from magnitude-phase trade-offs are discussed. The results of this work is expected to be practical CAD tools for designing simultaneous magnitude and phase optimal filters and theoretical information about the optimal trade-offs between magnitude and phase.
Sopiko Gvaladze - One of the best experts on this subject based on the ideXlab platform.
-
PCovR2: A flexible principal covariates regression approach to parsimoniously handle Multiple Criterion variables
Behavior Research Methods, 2021Co-Authors: Sopiko Gvaladze, Marlies Vervloet, Katrijn Deun, Henk A. L. Kiers, Eva CeulemansAbstract:Principal covariates regression (PCovR) allows one to deal with the interpretational and technical problems associated with running ordinary regression using many predictor variables. In PCovR, the predictor variables are reduced to a limited number of components, and simultaneously, Criterion variables are regressed on these components. By means of a weighting parameter, users can flexibly choose how much they want to emphasize reconstruction and prediction. However, when datasets contain many Criterion variables, PCovR users face new interpretational problems, because many regression weights will be obtained and because some criteria might be unrelated to the predictors. We therefore propose PCovR2, which extends PCovR by also reducing the criteria to a few components. These Criterion components are predicted based on the predictor components. The PCovR2 weighting parameter can again be flexibly used to focus on the reconstruction of the predictors and criteria, or on filtering out relevant predictor components and predictable Criterion components. We compare PCovR2 to two other approaches, based on partial least squares (PLS) and principal components regression (PCR), that also reduce the criteria and are therefore called PLS2 and PCR2. By means of a simulated example, we show that PCovR2 outperforms PLS2 and PCR2 when one aims to recover all relevant predictor components and predictable Criterion components. Moreover, we conduct a simulation study to evaluate how well PCovR2, PLS2 and PCR2 succeed in finding (1) all underlying components and (2) the subset of relevant predictor and predictable Criterion components. Finally, we illustrate the use of PCovR2 by means of empirical data.
M. Lightner - One of the best experts on this subject based on the ideXlab platform.
-
ICASSP - The use of Multiple Criterion optimization for the simultaneous phase and magnitude design of IIR digital filters
ICASSP '82. IEEE International Conference on Acoustics Speech and Signal Processing, 1Co-Authors: Guido M. Cortelazzo, M. LightnerAbstract:In this paper we investigate for the first time the applicability of the concepts and algorithms of Multiple Criterion Optimization to the problem of optimally trading-off magnitude and phase in IIR digital filters design. Particular attention is paid to the mathematical formulation of the simultaneous magnitude and phase design problem. Three different design criteria are introduced. The special modifications of a standard algorithm [9] necessary for filter design are discussed. Examples of what can be expected from magnitude-phase trade-offs are discussed. The results of this work is expected to be practical CAD tools for designing simultaneous magnitude and phase optimal filters and theoretical information about the optimal trade-offs between magnitude and phase.
Marlies Vervloet - One of the best experts on this subject based on the ideXlab platform.
-
PCovR2: A flexible principal covariates regression approach to parsimoniously handle Multiple Criterion variables
Behavior Research Methods, 2021Co-Authors: Sopiko Gvaladze, Marlies Vervloet, Katrijn Deun, Henk A. L. Kiers, Eva CeulemansAbstract:Principal covariates regression (PCovR) allows one to deal with the interpretational and technical problems associated with running ordinary regression using many predictor variables. In PCovR, the predictor variables are reduced to a limited number of components, and simultaneously, Criterion variables are regressed on these components. By means of a weighting parameter, users can flexibly choose how much they want to emphasize reconstruction and prediction. However, when datasets contain many Criterion variables, PCovR users face new interpretational problems, because many regression weights will be obtained and because some criteria might be unrelated to the predictors. We therefore propose PCovR2, which extends PCovR by also reducing the criteria to a few components. These Criterion components are predicted based on the predictor components. The PCovR2 weighting parameter can again be flexibly used to focus on the reconstruction of the predictors and criteria, or on filtering out relevant predictor components and predictable Criterion components. We compare PCovR2 to two other approaches, based on partial least squares (PLS) and principal components regression (PCR), that also reduce the criteria and are therefore called PLS2 and PCR2. By means of a simulated example, we show that PCovR2 outperforms PLS2 and PCR2 when one aims to recover all relevant predictor components and predictable Criterion components. Moreover, we conduct a simulation study to evaluate how well PCovR2, PLS2 and PCR2 succeed in finding (1) all underlying components and (2) the subset of relevant predictor and predictable Criterion components. Finally, we illustrate the use of PCovR2 by means of empirical data.