DocumentCode :
638442
Title :
Ant colony based semi-greedy algorithm for regression tree induction
Author :
Melnikov, G.A. ; Gubarev, V.V.
Author_Institution :
Dept. of Comput. Sci., Novosibirsk State Tech. Univ., Novosibirsk, Russia
Volume :
2
fYear :
2013
fDate :
June 28 2013-July 1 2013
Firstpage :
238
Lastpage :
240
Abstract :
Regression trees belong to a very important class of regression models which allows to split feature space into segments with building specialized local model for each of them and to achieve visualizable, easy interpretable and accurate piece-wise models. In this paper we propose a novel ant colony based semi-greedy algorithm for regression tree induction, combining techniques from both traditional regression tree induction algorithms and Ant Colony Optimization. The results of experiments on publicly available data sets show that the proposed algorithm outperforms conventional algorithms for regression tree induction in accuracy and results in less complex solutions.
Keywords :
greedy algorithms; optimisation; regression analysis; tree data structures; ant colony based semigreedy algorithm; ant colony optimization; feature space split; piecewise models; regression models; regression tree induction algorithms; Computational modeling; ant colony optimization; data mining; machine learning; model trees; regression; regression trees;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Strategic Technology (IFOST), 2013 8th International Forum on
Conference_Location :
Ulaanbaatar
Print_ISBN :
978-1-4799-0931-5
Type :
conf
DOI :
10.1109/IFOST.2013.6616894
Filename :
6616894
Link To Document :
بازگشت