DocumentCode :
642857
Title :
Adaption of NNS classification to domain of category values
Author :
Kovacs, Levente ; Kusper, G.
Author_Institution :
Dept. of Inf. Technol., Univ. of Miskolc, Miskolc, Hungary
fYear :
2013
fDate :
26-28 Sept. 2013
Firstpage :
299
Lastpage :
303
Abstract :
The paper discusses the classical Shepard and Kriging interpolation methods and provides an extension for the category-valued functions. A special weighted combination operator is proposed which can be used in the adapted Shepard interpolation for objects in general metric spaces. This method provides better approximation for the cases where the set of neighboring concepts is heterogeneous and dense enough.
Keywords :
approximation theory; interpolation; Kriging interpolation methods; NNS classification; Shepard interpolation methods; approximation; category-valued functions; special weighted combination operator; Function approximation; Informatics; Intelligent systems; Interpolation; Measurement; Standards; Shepard interpolation; concept interpolation; concept similarity;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Systems and Informatics (SISY), 2013 IEEE 11th International Symposium on
Conference_Location :
Subotica
Print_ISBN :
978-1-4799-0303-0
Type :
conf
DOI :
10.1109/SISY.2013.6662590
Filename :
6662590
Link To Document :
بازگشت