Evolutionary feature construction using information gain and gini index

Muharram, M. A. and Smith, G. D. (2004) Evolutionary feature construction using information gain and gini index. In: Genetic Programming. Lecture Notes in Computer Science, 3003 . Springer Berlin / Heidelberg, pp. 379-388. ISBN 978-3-540-21346-8

Full text not available from this repository. (Request a copy)

Abstract

Feature construction using genetic programming is carried out to study the effect on the performance of a range of classification algorithms with the inclusion of the evolved attributes. Two different fitness functions are used in the genetic program, one based on information gain and the other based on the gini index. The classification algorithms used are three classification tree algorithms, namely C5, CART, CHAID and an MLP neural network. The intention of the research is to ascertain if the decision tree classification algorithms benefit more using features constructed using a genetic programme whose fitness function incorporates the same fundamental learning mechanism as the splitting criteria of the associated decision tree.

Item Type: Book Section
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Vishal Gautam
Date Deposited: 21 Jul 2011 13:25
Last Modified: 25 Jul 2019 03:22
URI: https://ueaeprints.uea.ac.uk/id/eprint/23785
DOI: 10.1007/978-3-540-24650-3_36

Actions (login required)

View Item View Item