Dealing with Missing Data using a Selection Algorithm on Rough Sets


Por: Prieto-Cubides, J, Argoty, C

Publicada: 1 ene 2018
Resumen:
This paper discusses the so-called missing data problem, i.e. the problem of imputing missing values in information systems. A new algorithm, called the ARSI algorithm, is proposed to address the imputation problem of missing values on categorical databases using the framework of rough set theory. This algorithm can be seen as a refinement of the ROUSTIDA algorithm and combines the approach of a generalized non-symmetric similarity relation with a generalized discernibility matrix to predict the missing values on incomplete information systems. Computational experiments show that the proposed algorithm is as efficient and competitive as other imputation algorithms.

Filiaciones:
Prieto-Cubides, J:
 Univ EAFIT, Medellin, Colombia

 Grp Invest Pensamiento, Bogota, Colombia

 Univ Sergio Arboleda, Bogota, Colombia

Argoty, C:
 Grp Invest Pensamiento, Bogota, Colombia

 Univ Mil Nueva Granada, Bogota, Colombia
ISSN: 18756891
Editorial
ATLANTIS PRESS, 29 AVENUE LAUMIERE, PARIS, 75019, FRANCE, Francia
Tipo de documento: Article
Volumen: 11 Número: 1
Páginas: 1307-1321
WOS Id: 000454694400031
imagen Gold

MÉTRICAS