Share Email Print

Proceedings Paper

An ensemble learning algorithm based on generalized attribute value partitioning
Author(s): Weidong Tian; Fang Wu; Jipeng Qiang; Hongjuan Zhou
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The method of disturbing training data randomly to train individual classifiers has been widely applied in some ensemble learning methods such as Bagging and Boosting to achieve strong generalization ability, however, it seems something blind. In this paper, a new ensemble learning algorithm named GAVPEL is proposed. By using the hierarchy nature of the data set, GAVPEL leverages the generalized attribute value partitioning method to form an ensemble tree, called a generalized classifier hierarchy tree. While classifying, GAVPEL selects part of the individual classifiers based on attribute value and ensembles them with majority voting. Experiment results show that GAVPEL can efficiently improve generalization performance when compared with some popular ensemble learning algorithms.

Paper Details

Date Published: 2 December 2011
PDF: 7 pages
Proc. SPIE 8004, MIPPR 2011: Pattern Recognition and Computer Vision, 80041F (2 December 2011); doi: 10.1117/12.902971
Show Author Affiliations
Weidong Tian, Hefei Univ. of Technology (China)
Institute of Intelligent Machines (China)
Fang Wu, Hefei Univ. of Technology (China)
Jipeng Qiang, Hefei Univ. of Technology (China)
Hongjuan Zhou, Hefei Univ. of Technology (China)

Published in SPIE Proceedings Vol. 8004:
MIPPR 2011: Pattern Recognition and Computer Vision
Jonathan Roberts; Jie Ma, Editor(s)

© SPIE. Terms of Use
Back to Top