Share Email Print
cover

Proceedings Paper

Adaptive classification by maximizing class separability with respect to the unlabeled data
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, the Adaptive Mean-Field Bayesian Data Reduction Algorithm is discussed, which utilizes a method that maximizes the class separability of unlabeled training data. The algorithm is based on a Dirichlet distribution model for each class. In this new method, the Dirichlet model is extended such that dissimilar distributions are encouraged amongst the classes with respect to unlabeled data, and with respect to data containing missing values. It has previously been shown for two class cases that the theoretical probability of error is lower bounded by 0.25 under the original Dirichlet model. Thus, the new model has been developed with the idea of encouraging error probabilities below this lower bound given the data contains missing information, such as the class labels. Results are illustrated with simulated data as applied to sequential classification using Page's test. In general it is shown that the new method's performance is superior to that of the original Dirichlet model, where it is apparent that any previously acquired unlabeled data are being utilized in the training set to improve the correct classification of future test data samples.

Paper Details

Date Published: 8 August 2003
PDF: 11 pages
Proc. SPIE 5107, System Diagnosis and Prognosis: Security and Condition Monitoring Issues III, (8 August 2003); doi: 10.1117/12.487565
Show Author Affiliations
Robert S. Lynch, Naval Undersea Warfare Ctr. (United States)
Peter K. Willett, Univ. of Connecticut (United States)


Published in SPIE Proceedings Vol. 5107:
System Diagnosis and Prognosis: Security and Condition Monitoring Issues III
Peter K. Willett; Thiagalingam Kirubarajan, Editor(s)

© SPIE. Terms of Use
Back to Top