DocumentCode :
2303550
Title :
A new fuzzy classifier based on simulated annealing and subtractive clustering
Author :
Torun, Yunus ; Tohumoglu, Gulay
Author_Institution :
Biyomedikal Cihaz Teknolojileri Programi, G.M.Y.O. Gaziantep Univ., Gaziantep, Turkey
fYear :
2009
fDate :
9-11 April 2009
Firstpage :
460
Lastpage :
463
Abstract :
In this study, subtractive clustering method is used in order to obtain membership functions and rule base of fuzzy classifier system. Neighborhood radii of subtractive clustering method which directly effects the system dynamic and number of rules in the fuzzy classifier, is obtained by new simulated annealing optimization algorithm. The proposed classifier is firstly applied on pap-smear test which is used in diagnosis of cervical cancer. The classifier is also tested with some well known biomedical and other classification problems in the literature. The results obtained by the offered hybrid classifier have better performance than the other methods.
Keywords :
cancer; fuzzy set theory; medical diagnostic computing; pattern classification; pattern clustering; simulated annealing; tumours; biomedical classification problem; cervical cancer diagnosis; fuzzy classifier system; pap-smear test; simulated annealing optimization algorithm; subtractive clustering method; Decision support systems; Simulated annealing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing and Communications Applications Conference, 2009. SIU 2009. IEEE 17th
Conference_Location :
Antalya
Print_ISBN :
978-1-4244-4435-9
Electronic_ISBN :
978-1-4244-4436-6
Type :
conf
DOI :
10.1109/SIU.2009.5136432
Filename :
5136432
Link To Document :
بازگشت