2012
Leiva-Murillo, Jose M; Artés-Rodríguez, Antonio
Information-Theoretic Linear Feature Extraction Based on Kernel Density Estimators: A Review Artículo de revista
En: IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), vol. 42, no 6, pp. 1180–1189, 2012, ISSN: 1094-6977.
Resumen | Enlaces | BibTeX | Etiquetas: Bandwidth, Density, detection theory, Entropy, Estimation, Feature extraction, Feature extraction (FE), information theoretic linear feature extraction, information theory, information-theoretic learning (ITL), Kernel, Kernel density estimation, kernel density estimators, Machine learning
@article{Leiva-Murillo2012a,
title = {Information-Theoretic Linear Feature Extraction Based on Kernel Density Estimators: A Review},
author = {Jose M Leiva-Murillo and Antonio Art\'{e}s-Rodr\'{i}guez},
url = {http://www.tsc.uc3m.es/~antonio/papers/P44_2012_Information Theoretic Linear Feature Extraction Based on Kernel Density Estimators A Review.pdf http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6185689},
issn = {1094-6977},
year = {2012},
date = {2012-01-01},
journal = {IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)},
volume = {42},
number = {6},
pages = {1180--1189},
abstract = {In this paper, we provide a unified study of the application of kernel density estimators to supervised linear feature extraction by means of criteria inspired by information and detection theory. We enrich this study by the incorporation of two novel criteria to the study, i.e., the mutual information and the likelihood ratio test, and perform both a theoretical and an experimental comparison between the new methods and other ones previously described in the literature. The impact of the bandwidth selection of the density estimator in the classification performance is discussed. Some theoretical results that bound classification performance as a function or mutual information are also compiled. A set of experiments on different real-world datasets allows us to perform an empirical comparison of the methods, in terms of both accuracy and computational complexity. We show the suitability of these methods to determine the dimension of the subspace that contains the discriminative information.},
keywords = {Bandwidth, Density, detection theory, Entropy, Estimation, Feature extraction, Feature extraction (FE), information theoretic linear feature extraction, information theory, information-theoretic learning (ITL), Kernel, Kernel density estimation, kernel density estimators, Machine learning},
pubstate = {published},
tppubtype = {article}
}
2007
Leiva-Murillo, Jose M; Artés-Rodríguez, Antonio
Maximization of Mutual Information for Supervised Linear Feature Extraction Artículo de revista
En: IEEE Transactions on Neural Networks, vol. 18, no 5, pp. 1433–1441, 2007, ISSN: 1045-9227.
Resumen | Enlaces | BibTeX | Etiquetas: Algorithms, Artificial Intelligence, Automated, component-by-component gradient-ascent method, Computer Simulation, Data Mining, Entropy, Feature extraction, gradient methods, gradient-based entropy, Independent component analysis, Information Storage and Retrieval, information theory, Iron, learning (artificial intelligence), Linear discriminant analysis, Linear Models, Mutual information, Optimization methods, Pattern recognition, Reproducibility of Results, Sensitivity and Specificity, supervised linear feature extraction, Vectors
@article{Leiva-Murillo2007,
title = {Maximization of Mutual Information for Supervised Linear Feature Extraction},
author = {Jose M Leiva-Murillo and Antonio Art\'{e}s-Rodr\'{i}guez},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=4298118},
issn = {1045-9227},
year = {2007},
date = {2007-01-01},
journal = {IEEE Transactions on Neural Networks},
volume = {18},
number = {5},
pages = {1433--1441},
publisher = {IEEE},
abstract = {In this paper, we present a novel scheme for linear feature extraction in classification. The method is based on the maximization of the mutual information (MI) between the features extracted and the classes. The sum of the MI corresponding to each of the features is taken as an heuristic that approximates the MI of the whole output vector. Then, a component-by-component gradient-ascent method is proposed for the maximization of the MI, similar to the gradient-based entropy optimization used in independent component analysis (ICA). The simulation results show that not only is the method competitive when compared to existing supervised feature extraction methods in all cases studied, but it also remarkably outperform them when the data are characterized by strongly nonlinear boundaries between classes.},
keywords = {Algorithms, Artificial Intelligence, Automated, component-by-component gradient-ascent method, Computer Simulation, Data Mining, Entropy, Feature extraction, gradient methods, gradient-based entropy, Independent component analysis, Information Storage and Retrieval, information theory, Iron, learning (artificial intelligence), Linear discriminant analysis, Linear Models, Mutual information, Optimization methods, Pattern recognition, Reproducibility of Results, Sensitivity and Specificity, supervised linear feature extraction, Vectors},
pubstate = {published},
tppubtype = {article}
}