Title :
Utility-based metaclassification
Author :
Pittarelli, Michael
Author_Institution :
Inst. of Technol., SUNY, Utica, NY, USA
Abstract :
A technique for accepting or rejecting the output of a Bayesian classifier is presented based on a metalevel Bayesian classifier using features of the probability distribution over the known classes calculated by the lower-level (object-level) classifier. The value of adding the metalevel classifier is determined by user utilities for the possible outcomes of the two-level process.
Keywords :
Bayes methods; pattern classification; statistical distributions; lower-level classifier; metalevel Bayesian classifier; object-level classifier; probability distribution; two-level process; utility-based metaclassification; Bayesian methods; Cybernetics; Glass; Probability distribution; Refractive index; Spatial databases; Testing; USA Councils; Vehicles; Windows; classifier; metaclassification; novelty detection;
Conference_Titel :
Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
978-1-4244-2793-2
Electronic_ISBN :
1062-922X
DOI :
10.1109/ICSMC.2009.5346303
