Constructing X-of-N attributes with a genetic algorithm

DMCA

Constructing X-of-N attributes with a genetic algorithm (2002)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Otavio Larsen , Alex A. Freitas , Julio C. Nievola

Venue:	In Proc. of the Genetic and Evolutionary Computation Conference
Citations:	3 - 0 self

BibTeX

@INPROCEEDINGS{Larsen02constructingx-of-n,
    author = {Otavio Larsen and Alex A. Freitas and Julio C. Nievola},
    title = {Constructing X-of-N attributes with a genetic algorithm},
    booktitle = {In Proc. of the Genetic and Evolutionary Computation Conference},
    year = {2002},
    pages = {1268},
    publisher = {Morgan Kaufmann}
}

OpenURL

Abstract

The predictive accuracy obtained by a classification algorithm is strongly dependent on the quality of the attributes of the data being mined. When the attributes are little relevant for predicting the class of a record, the predictive accuracy will tend to be low. To combat this problem, a natural approach consists of constructing new attributes out of the original attributes. Many attribute construction algorithms work by simply constructing conjunctions and/or disjunctions of attribute-value pairs. This kind of representation has a limited expressiveness power to represent attribute interactions. A more expressive representation is X-of-N [Zheng 1995]. An Xof-N condition consists of a set of N attribute-value pairs. The value of an X-of-N condition for a given example

Keyphrases

genetic algorithm x-of-n attribute predictive accuracy attribute-value pair expressive representation limited expressiveness power x-of-n condition attribute interaction new attribute original attribute natural approach xof-n condition many attribute construction algorithm work x-of-n zheng classification algorithm

DMCA