DocumentCode :
2405646
Title :
Evidence aggregation for diagnosis: Bayesian and fuzzy strategies
Author :
Varga, Robert ; Matheson, Sarah ; Hamilton-Wright, Andrew
Author_Institution :
Comput. & Inf. Sci., Univ. of Guelph, Guelph, ON, Canada
fYear :
2009
fDate :
14-17 June 2009
Firstpage :
1
Lastpage :
5
Abstract :
This paper investigates the utility of using aggregate (average, max etc.) information in a multi-sample classification problem in terms of the accuracy of the overall classification, and the prediction of estimated error. Bayesian networks are presented here in order to allow comparison of these results with those of a previously presented fuzzy inference system. Different structures of Bayesian network are implemented, and also compared. Different methods of calculating aggregate information to append to the samples are also investigated. The authors find that appending the additional information does improve classification accuracy and lowers classification frequency. They also find that the addition of the average aggregator to the data is more effective than appending any other combination of aggregators. Lastly, they find that the naive Bayesian network structure performs better than tree-augmented Bayesian networks, as well as networks limited only in number of parents per node.
Keywords :
belief networks; fault diagnosis; fuzzy set theory; pattern clustering; average aggregator; classification accuracy; classification frequency; evidence aggregation; fault diagnosis; fuzzy inference system; fuzzy strategies; multisample classification problem; naive Bayesian network structure; overall classification; tree-augmented Bayesian network; Aggregates; Bayesian methods; Decision support systems; Diseases; Fuzzy systems; Information processing; Information science; Medical diagnostic imaging; Network topology; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Information Processing Society, 2009. NAFIPS 2009. Annual Meeting of the North American
Conference_Location :
Cincinnati, OH
Print_ISBN :
978-1-4244-4575-2
Electronic_ISBN :
978-1-4244-4577-6
Type :
conf
DOI :
10.1109/NAFIPS.2009.5156443
Filename :
5156443
Link To Document :
بازگشت