Consistency-Based Feature Selection

Authors:
Kilho Shin;Xian Ming Xu
Affiliations:
Carnegie Mellon CyLab, Japan;Carnegie Mellon CyLab, Japan
Venue:
KES '09 Proceedings of the 13th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems: Part I
Year:
2009

Citing 5
Cited 3

Learning Boolean concepts in the presence of many irrelevant features

Artificial Intelligence
Consistency-based search in feature selection

Artificial Intelligence
Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)

Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems)
Searching for interacting features

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence

A Consistency-Constrained Feature Selection Algorithm with the Steepest Descent Method

MDAI '09 Proceedings of the 6th International Conference on Modeling Decisions for Artificial Intelligence
Consistency measures for feature selection: a formal definition, relative sensitivity comparison and a fast algorithm

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
DE+RBFNs based classification: A special attention to removal of inconsistency and irrelevant features

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Feature selection, the job to select features relevant to classification, is a central problem of machine learning. Inconsistency rate is known as an effective measure to evaluate consistency (relevance) of feature subsets, and INTERACT, a state-of-the-art feature selection algorithm, takes advantage of it. In this paper, we shows that inconsistency rate is not the unique measure of consistency by introducing two new consistency measures, and also, show that INTERACT has the important deficiency that it fails for particular types of probability distributions. To fix the deficiency, we propose two new algorithms, which have flexibility of taking advantage of any of the new measures as well as inconsistency rate. Furthermore, through experiments, we compare the three consistency measures, and prove effectiveness of the new algorithms.