Feature selection based on sensitivity analysis

• Sánchez Maroño, Noelia ^[1] ; Alonso Betanzos, Amparo ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: XII Conferencia de la Asociación Española para la Inteligencia Artificial: (CAEPIA 2007). Actas / coord. por Daniel Borrajo Millán, Luis Castillo Vidal, Juan Manuel Corchado Rodríguez, Vol. 1, 2007, ISBN 978-84-611-8847-5, págs. 67-76
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • In this paper an incremental version of the ANOVA and Functional Networks Feature Selection (AFN-FS) method is presented. This new wrapper method (IAFN-FS) is based on an incremental functional decomposition, thus eliminating the main drawback of the basic method: the exponential complexity of the functional decomposition. This complexity limited its scope of applicability, being only applicable to datasets with a relatively small number of features. The performance of the incremental version of the method was tested against several real data sets. The results show that IAFN-FS outperforms the accuracy obtained by other standard and novel feature slection methods, using a small set of features.