Minimising the delta test for variable selection in regression problems
Authors: Guillen, Alberto1; Sovilj, Dusan2; Lendasse, Amaury2; Mateo, Fernando3; Rojas, Ignacio4
Source: International Journal of High Performance Systems Architecture, Volume 1, Number 4, 29 March 2009 , pp. 269-281(13)
Publisher: Inderscience Publishers
Abstract:
The problem of selecting an adequate set of variables from a given data set of a sampled function becomes crucial by the time of designing the model that will approximate it. Several approaches have been presented in the literature although recent studies showed how the delta test is a powerful tool to determine if a subset of variables is correct. This paper presents new methodologies based on the delta test such as tabu search, genetic algorithms and the hybridisation of them, to determine a subset of variables which is representative of a function. The paper considers as well the scaling problem where a relevance value is assigned to each variable. The new algorithms were adapted to be run in parallel architectures so better performances could be obtained in a small amount of time, presenting great robustness and scalability.Keywords: COMPUTING AND MATHEMATICS JOURNALS; Computing Science, Applications and Software
Document Type: Research article
DOI: http://dx.doi.org/10.1504/IJHPSA.2008.024211
Affiliations: 1: Department of Informatics, University of Jaen, Campus Las Lagunillas, Edif A3, 23071 Jaen, Spain. 2: Department of Information and Computer Science, Helsinki University of Technology, P.O. Box 5400, FI-02015 HUT, Finland. 3: Institute of Applications of Information Technology and Advanced Communications, Polytechnic University of Valencia, Camino de Vera s/n, 46022 Valencia, Spain. 4: Department of Computer Architecture and Technology, University of Granada, C/ Periodista Daniel Saucedo s/n, 18071 Granada, Spain.
Publication date: 2009-03-29
- The International Journal of High Performance Systems Architecture provides a lively forum for the communications of original research. It acts as a scientific and professional journal to timely disseminate original research work on advanced systems architecture, which is at the heart of high-performance and cost-effective systems.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Terms & Conditions
- Newsletter
- Blog
- ingentaconnect is not responsible for the content or availability of external websites
- In this: publication
- By this: publisher
- In this Subject: Computer Science
- By this author: Guillen, Alberto ; Sovilj, Dusan ; Lendasse, Amaury ; Mateo, Fernando ; Rojas, Ignacio

Shopping cart
Receive new issue alert
Get Permissions