2021
Sevilla-Salcedo, Carlos; Gómez-Verdejo, Vanessa; Olmos, Pablo M
Sparse semi-supervised heterogeneous interbattery bayesian analysis Artículo de revista
En: Pattern Recognition, vol. 120, pp. 108141, 2021, ISSN: 0031-3203.
Resumen | Enlaces | BibTeX | Etiquetas: Bayesian model, Canonical correlation analysis, Factor analysis, Feature selection, Multi-task, Principal component analysis, Semi-supervised
@article{SEVILLASALCEDO2021108141,
title = {Sparse semi-supervised heterogeneous interbattery bayesian analysis},
author = {Carlos Sevilla-Salcedo and Vanessa G\'{o}mez-Verdejo and Pablo M Olmos},
url = {https://www.sciencedirect.com/science/article/pii/S0031320321003289},
doi = {https://doi.org/10.1016/j.patcog.2021.108141},
issn = {0031-3203},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {Pattern Recognition},
volume = {120},
pages = {108141},
abstract = {The Bayesian approach to feature extraction, known as factor analysis (FA), has been widely studied in machine learning to obtain a latent representation of the data. An adequate selection of the probabilities and priors of these bayesian models allows the model to better adapt to the data nature (i.e. heterogeneity, sparsity), obtaining a more representative latent space. The objective of this article is to propose a general FA framework capable of modelling any problem. To do so, we start from the Bayesian Inter-Battery Factor Analysis (BIBFA) model, enhancing it with new functionalities to be able to work with heterogeneous data, to include feature selection, and to handle missing values as well as semi-supervised problems. The performance of the proposed model, Sparse Semi-supervised Heterogeneous Interbattery Bayesian Analysis (SSHIBA), has been tested on different scenarios to evaluate each one of its novelties, showing not only a great versatility and an interpretability gain, but also outperforming most of the state-of-the-art algorithms.},
keywords = {Bayesian model, Canonical correlation analysis, Factor analysis, Feature selection, Multi-task, Principal component analysis, Semi-supervised},
pubstate = {published},
tppubtype = {article}
}
2016
Song, Yang; Schreier, Peter J; Ramírez, David; Hasija, Tanuj
Canonical Correlation Analysis of High-Dimensional Data With Very Small Sample Support Artículo de revista
En: Signal Processing, vol. 128, pp. 449–458, 2016, ISSN: 01651684.
Resumen | Enlaces | BibTeX | Etiquetas: Bartlett-Lawley statistic, Canonical correlation analysis, Journal, Model-order selection, Principal component analysis, Small sample support
@article{Song2016,
title = {Canonical Correlation Analysis of High-Dimensional Data With Very Small Sample Support},
author = {Yang Song and Peter J Schreier and David Ram\'{i}rez and Tanuj Hasija},
url = {http://www.sciencedirect.com/science/article/pii/S0165168416300834},
doi = {10.1016/j.sigpro.2016.05.020},
issn = {01651684},
year = {2016},
date = {2016-11-01},
journal = {Signal Processing},
volume = {128},
pages = {449--458},
abstract = {This paper is concerned with the analysis of correlation between two high-dimensional data sets when there are only few correlated signal components but the number of samples is very small, possibly much smaller than the dimensions of the data. In such a scenario, a principal component analysis (PCA) rank-reduction preprocessing step is commonly performed before applying canonical correlation analysis (CCA). We present simple, yet very effective, approaches to the joint model-order selection of the number of dimensions that should be retained through the PCA step and the number of correlated signals. These approaches are based on reduced-rank versions of the Bartlett\textendashLawley hypothesis test and the minimum description length information-theoretic criterion. Simulation results show that the techniques perform well for very small sample sizes even in colored noise.},
keywords = {Bartlett-Lawley statistic, Canonical correlation analysis, Journal, Model-order selection, Principal component analysis, Small sample support},
pubstate = {published},
tppubtype = {article}
}