Ponencia
Best Agglomerative Ranked Subset for Feature Selection
Autor/es | Ruiz Sánchez, Roberto
Aguilar Ruiz, Jesús Salvador Riquelme Santos, José Cristóbal |
Departamento | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Fecha de publicación | 2008-09 |
Fecha de depósito | 2023-05-03 |
Publicado en |
|
Resumen | The enormous increase of the size in databases makes finding an optimal subset of features extremely difficult. In this paper, a new feature selection method is proposed that will allow any subset evaluator -including the ... The enormous increase of the size in databases makes finding an optimal subset of features extremely difficult. In this paper, a new feature selection method is proposed that will allow any subset evaluator -including the wrapper evaluation method- to be used to find a group of features that will allow a distinction to be made between the different possible classes. The method, BARS (Best Agglomerative Ranked Subset), is based on the idea of relevance and redundancy, in the sense that a ranked feature (or set) is more relevant if it adds information when it is included in the final subset of selected features. This heuristic method reduces dimensionality drastically and leads to improvements in the accuracy, in comparison to a complete set and as opposed to other feature selection algorithms. |
Agencias financiadoras | Comisión Interministerial de Ciencia y Tecnología (CICYT). España |
Identificador del proyecto | TIN2007- 68084-C02 |
Cita | Ruiz Sánchez, R., Aguilar Ruiz, J. y Riquelme Santos, J.C. (2008). Best Agglomerative Ranked Subset for Feature Selection. En Proceedings of the 2008 International Conference on New Challenges for Feature Selection in Data Mining and Knowledge Discovery (FSDM'08), Antwerp, Bélgica. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Best agglomerative ranked subset ... | 202.1Kb | [PDF] | Ver/ | |