Evolutionary feature construction using information gain and gini index

M. A. Muharram, G. D. Smith

Research output: Chapter in Book/Report/Conference proceedingChapter

25 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationGenetic Programming
EditorsMaarten Keijzer, Una-May O’Reilly, Simon Lucas, Ernesto Costa, Terence Soule
PublisherSpringer Berlin / Heidelberg
Pages379-388
Number of pages10
Volume3003
ISBN (Print)978-3-540-21346-8
DOIs
Publication statusPublished - 2004

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Berlin / Heidelberg

Cite this