Abstract
In this paper, we introduce an adaptation of a multivariate feature selection method to deal with functional features. In our case, observations are described by a set of functions defined over a common domain (e.g. a time interval). The feature selection method consists on combining variable weighting with a feature extraction projection. Although the employed method was primarily intended for observations described by vectors in ℝn, we propose a simple extension that allows us to select a set of functional features, which is well suited for classification. This study is complemented by the incorporation of Functional Principal Component Analysis (FPCA) that project functions into a finite dimensional space were we can perform classification easily. Another remarkable property of FPCA is that it can provide insight about the nature of the functional features. The proposed algorithms are tested on a pathological voice detection task. Two databases are considered: Massachusetts Eye and Ear Infirmary Voice Laboratory voice disorders database and Universidad Politécnica de Madrid voice database. As a result, we obtain a canonical function whose time average is enough to reach similar performances to the ones reported in the literature.
This is part of the project 20201004208, funded by Universidad Nacional de Colombia.
Chapter PDF
Similar content being viewed by others
Keywords
- Feature Selection
- Gaussian Mixture Model
- Feature Selection Method
- Canonical Function
- Functional Data Analysis
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
John, G.H., Kohavi, R., Pfleger, K.: Irrelevant features and the subset selection problem. In: ICML (1994)
Blum, A.L., Langley, P.: Selection of relevant features and examples in machine learning. In: AI, vol. 97(1-2) (1997)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. In: JMLR (2003)
Yu, L., Liu, H.: Efficient feature selection via analysis of relevance and redundancy. In: JMLR (2004)
Wolf, L., Shashua, A.: Feature selection for unsupervised and supervised inference: the emergence of sparsity in a weighted-based approach. In: JMLR (2005)
Ramsay, J., Silverman, B.: Functional Data Analysis, 2nd edn. Springer, Heidelberg (2005)
Jolliffe, I.T.: Principal Component Analysis, 2nd edn. Springer, Heidelberg (2002)
Ferraty, F., Vieu, P.: Nonparametric Functional Data Analysis. Springer, Heidelberg (2006)
Sánchez, L., Martínez, F., Castellanos, G., Salazar, A.: Feature extraction of weighted data for implicit variable selection. In: CAIP. Springer, Heidelberg (2007)
Bradley, P.S., Mangasarian, O.L., Street, W.N.: Feature selection via mathematical programming. INFORMS Journal on Computing 10 (1998)
Friedman, J.H.: Regularized discriminant analysis. Journal of the American Statistical Association (1989)
Webb, A.R.: Statistical Pattern Recognition, 2nd edn. John Wiley & Sons, Chichester (2002)
Daza, G., Arias, J., Godino, J., Sáenz, N., Osma, V., Castellanos, G.: Dynamic feature extraction: An application to voice pathology detection. Intelligent Automation and Soft Computing 15(4) (2009)
Godino-Llorente, J.I., Gómez-Vilda, P., Blanco-Velasco, M.: Dimensionality reduction of pathological voice quality assesment system based on gaussian mixtures models and short-term cepstarl parameters. IEEE Transactions on Biomedical Engineering 53(10), 1943–1953 (2006)
Schölkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, December 2002. MIT Press, Cambridge (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sánchez Giraldo, L., Martínez Tabares, F., Castellanos Domínguez, G. (2009). Functional Feature Selection by Weighted Projections in Pathological Voice Detection. In: Bayro-Corrochano, E., Eklundh, JO. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2009. Lecture Notes in Computer Science, vol 5856. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10268-4_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-10268-4_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-10267-7
Online ISBN: 978-3-642-10268-4
eBook Packages: Computer ScienceComputer Science (R0)