Implementation of a scalable decision forest model based on information theory

Authors:
Li-Min Wang;Xue-Bai Zang
Affiliations:
College of Computer Science and Technology, Jilin University, PR China and State Key Laboratory for Novel Software Technology, Nanjing University, PR China;College of Computer Science and Technology, Jilin University, PR China
Venue:
Expert Systems with Applications: An International Journal
Year:
2011

Citing 7
Cited 0

A Comparative Analysis of Methods for Pruning Decision Trees

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Random Subspace Method for Constructing Decision Forests

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Experimental Comparison of Three Methods for Constructing Ensembles of Decision Trees: Bagging, Boosting, and Randomization

Machine Learning
Information Theory, Inference & Learning Algorithms

Information Theory, Inference & Learning Algorithms
A classifier learning system using a coevolution method for deflection yoke misconvergence pattern classification problem

Information Sciences: an International Journal
Induction of multiple fuzzy decision trees based on rough set technique

Information Sciences: an International Journal
Decision forests with oblique decision trees

MICAI'06 Proceedings of the 5th Mexican international conference on Artificial Intelligence

Quantified Score

Hi-index	12.05

Visualization

Abstract

One of the most challenging problems in data mining is to develop scalable algorithms capable of mining massive data sets. A novel decision forest learning algorithm named FDF is proposed in this paper to represent multi-level semantic knowledge of the relationship between the data and information implicated. FDF provides their users with just a single set of rules by redefining information gain of information theory, then each tree in the decision forest is constructed in the down-top learning framework, and the number of trees and stopping criteria can be set automatically. When no existing tree match test samples, FDF will build new logical rules for this and thus realize scalable construction process. Empirical studies on a set of natural domains show that decision forest has clear advantages with respect to probabilistic performance.