A Dynamic Method for Discretization of Continuous Attributes

Authors:
Grace J. Hwang;Fumin Li
Affiliations:
-;-
Venue:
IDEAL '02 Proceedings of the Third International Conference on Intelligent Data Engineering and Automated Learning
Year:
2002

Citing 5
Cited 1

Applied multivariate statistical analysis

Applied multivariate statistical analysis
C4.5: programs for machine learning

C4.5: programs for machine learning
Feature Selection via Discretization

IEEE Transactions on Knowledge and Data Engineering
On Changing Continuous Attributes into Ordered Discrete Attributes

EWSL '91 Proceedings of the European Working Session on Machine Learning
Concurrent Discretization of Multiple Attributes

PRICAI '98 Proceedings of the 5th Pacific Rim International Conference on Artificial Intelligence: Topics in Artificial Intelligence

Integrating in-process software defect prediction with association mining to discover defect pattern

Information and Software Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

A discretization technique converts continuous attribute values into discrete ones. Discretization is needed when classification algorithms require only discrete attributes. It is also useful to increase the speed and the accuracy of classification algorithms. This paper presents a dynamic discretization method, whose main characteristic is to detect interdependencies between all continuous attributes. Empirical evaluation on 12 datasets from the UCI repository shows that the proposed algorithm is a relatively effective method for discretization.