A new minimax probability based classifier using fuzzy hyper-ellipsoid

Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/11054

Title:	A new minimax probability based classifier using fuzzy hyper-ellipsoid
Authors:	Deng, Z Chung, FL Wang, S
Issue Date:	2007
Source:	International Joint Conference on Neural Networks, 2007 : IJCNN 2007, 12-17 August 2007, Orlando, FL, p. 2385-2390
Abstract:	In this paper, a new classifier called minimax-probability based fuzzy hyper-ellipsoid machine (MP-FHM) is proposed. It offers an alternative implementation of the minimax probability based classification with hyper plane and can be taken as an extended version of the ball-model based classifier. By the theorem proposed by Marshall and Qlkin, the training procedure of MP-FHM can be transformed into solving the corresponding unconstrained optimization problems, and thereby various optimization techniques can easily be adopted to solve them. In addition, the MP-FHM can be kernelized, and therefore it has strong nonlinear classification capabilities like other kernel-based classifiers. Various experiments were conducted and the results demonstrate that the proposed classifier is competitive with the state-of-the-art classifiers and is a very promising classification method.
Keywords:	Computational geometry Fuzzy set theory Learning (artificial intelligence) Minimax techniques Pattern classification
Publisher:	IEEE
ISBN:	978-1-4244-1379-9 978-1-4244-1380-5 (E-ISBN)
ISSN:	1098-7576
DOI:	10.1109/IJCNN.2007.4371331
Appears in Collections:	Conference Paper

View full-text via PolyU eLinks

7

Last Week
0

Last month

Citations as of Aug 15, 2020

105

Last Week
2

Last month

Citations as of Sep 14, 2020

Check