@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}

}

@article{Koch2010a,

title = {Gaussian Fading Is the Worst Fading},

author = {Tobias Koch and Amos Lapidoth},

url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5429105},

issn = {0018-9448},

year  = {2010},

date = {2010-01-01},

journal = {IEEE Transactions on Information Theory},

volume = {56},

number = {3},

pages = {1158--1165},

abstract = {The capacity of peak-power limited, single-antenna, noncoherent, flat-fading channels with memory is considered. The emphasis is on the capacity pre-log, i.e., on the limiting ratio of channel capacity to the logarithm of the signal-to-noise ratio (SNR), as the SNR tends to infinity. It is shown that, among all stationary and ergodic fading processes of a given spectral distribution function and whose law has no mass point at zero, the Gaussian process gives rise to the smallest pre-log. The assumption that the law of the fading process has no mass point at zero is essential in the sense that there exist stationary and ergodic fading processes whose law has a mass point at zero and that give rise to a smaller pre-log than the Gaussian process of equal spectral distribution function. An extension of these results to multiple-input single-output (MISO) fading channels with memory is also presented.},

keywords = {Additive noise, channel capacity, channels with memory, Distribution functions, ergodic fading processes, Fading, fading channels, flat fading, flat-fading channel capacity, Gaussian channels, Gaussian fading, Gaussian processes, H infinity control, high signal-to-noise ratio (SNR), Information technology, information theory, multiple-input single-output fading channels, multiplexing gain, noncoherent, noncoherent channel capacity, peak-power limited channel capacity, Signal to noise ratio, signal-to-noise ratio, single-antenna channel capacity, spectral distribution function, time-selective, Transmitters},

pubstate = {published},

tppubtype = {article}

}

@article{Leiva-Murillo2008c,

title = {A Simulated Annealing Approach to Speaker Segmentation in Audio Databases},

author = {Jose M Leiva-Murillo and Sancho Salcedo-Sanz and Ascensi\'{o}n Gallardo-Antol\'{i}n and Antonio Art\'{e}s-Rodr\'{i}guez},

url = {http://www.sciencedirect.com/science/article/pii/S0952197607000954},

year  = {2008},

date = {2008-01-01},

journal = {Engineering Applications of Artificial Intelligence},

volume = {21},

number = {4},

pages = {499--508},

abstract = {In this paper we present a novel approach to the problem of speaker segmentation, which is an unavoidable previous step to audio indexing. Mutual information is used for evaluating the accuracy of the segmentation, as a function to be maximized by a simulated annealing (SA) algorithm. We introduce a novel mutation operator for the SA, the Consecutive Bits Mutation operator, which improves the performance of the SA in this problem. We also use the so-called Compaction Factor, which allows the SA to operate in a reduced search space. Our algorithm has been tested in the segmentation of real audio databases, and it has been compared to several existing algorithms for speaker segmentation, obtaining very good results in the test problems considered.},

keywords = {Audio indexing, information theory, Simulated annealing, Speaker segmentation},

pubstate = {published},

tppubtype = {article}

}

@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}

}