Recognition of multidimensional affine patterns using a constrained GA

Author

Calafiore, Giuseppe ; Bona, Basilio

Author_Institution

Dipartimento di Autom. e Inf., Politecnico di Torino, Italy

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

1235

Abstract

The problem of determining an affine relation among multidimensional data points is addressed in this paper. In the first step of the illustrated procedure, the parameters for the linear manifold that fits the data are determined in closed form using a (weighted) total least squares formulation of the problem. The solution obtained, however, is highly sensitive to data points with exceptionally high noise (outliers). The problem of outliers suppression is then formulated as a constrained binary optimization problem and a genetic algorithm with nonstationary penalty function is used to solve it efficiently

Keywords

genetic algorithms; least squares approximations; pattern recognition; closed form; constrained GA; constrained binary optimization problem; genetic algorithm; linear manifold parameters; multidimensional affine pattern recognition; multidimensional data points; noise; nonstationary penalty function; outliers suppression; weighted total least-squares formulation; Data processing; Fitting; Gaussian noise; Genetic algorithms; Least squares methods; Maximum likelihood detection; Maximum likelihood estimation; Multidimensional systems; Noise robustness; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.616210

Filename

616210