Discretization of Ordinal Attributes and Feature Selection
| dc.contributor.author | Huan Liu | en_US |
| dc.contributor.author | Rudy Setiono | en_US |
| dc.date.accessioned | 2004-10-21T14:28:52Z | en_US |
| dc.date.accessioned | 2017-01-23T07:00:39Z | |
| dc.date.available | 2004-10-21T14:28:52Z | en_US |
| dc.date.available | 2017-01-23T07:00:39Z | |
| dc.date.issued | 1995-04-01T00:00:00Z | en_US |
| dc.description.abstract | The performance of classification algorithms may deteriorate due to irrelevant attributes. Numeric attributes make the situation worse, since many classification algorithms require that the training data contain only discrete attributes. Discretization can turn numeric attributes into discrete ones. Feature selection can eliminate some irrelevant attributes. This paper describes Chi2, a simple and general algorithm that uses the $\chi^2$ statistic to discretize numeric attributes repeatedly until some inconsistencies are found in the data, and achieves feature selection via discretization. In addition, it can handle mixed attributes and multi-class data naturally. %data, and achieves feature selection and discretization in one go. Experiments are conducted on the real and synthetic data sets. The empirical results demonstrate that Chi2 is effective in feature selection and discretization of numeric and ordinal attributes. | en_US |
| dc.format.extent | 186160 bytes | en_US |
| dc.format.extent | 211663 bytes | en_US |
| dc.format.mimetype | application/pdf | en_US |
| dc.format.mimetype | application/postscript | en_US |
| dc.identifier.uri | https://dl.comp.nus.edu.sg/xmlui/handle/1900.100/1386 | en_US |
| dc.language.iso | en | en_US |
| dc.relation.ispartofseries | TRB4/95 | en_US |
| dc.title | Discretization of Ordinal Attributes and Feature Selection | en_US |
| dc.type | Technical Report | en_US |
Files
License bundle
1 - 1 of 1