Title :
Error-Dependency Relationships for the Naïve Bayes Classifier with Binary Features
Author :
Kuncheva, Ludmila I. ; Hoare, ZoëS J.
Author_Institution :
Bangor Univ., Bangor
fDate :
4/1/2008 12:00:00 AM
Abstract :
We derive a tight dependency-related bound on the difference between the NB error and Bayes error for the case of two binary features and two classes. A measure of feature dependency is proposed for multiple features. Simulations and experiments with 23 real data sets were carried out.
Keywords :
belief networks; pattern classification; Naive Bayes classifier; binary features; error-dependency relationships; feature dependency; Classifier design and evaluation; Dependency; Feature evaluation and selection; Naive Bayes; Pattern Recognition; Algorithms; Artificial Intelligence; Bayes Theorem; Computer Simulation; Data Interpretation, Statistical; Logistic Models; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2007.70845
