An Adaptive Fuzzy Classification System

TFIR > Department of Electrical Engineering > conference > Item 987654321/1004

Please use this identifier to cite or link to this item: http://163.15.40.127/ir/handle/987654321/1004

Title:	An Adaptive Fuzzy Classification System
Authors:	Guo, Nai Ren Kuo, Chao-Lin 蔡宗吉 Tsai, Tzong-Jiy Chen, Shi-Jaw (東方技術學院電機工程系) 郭乃仁
Contributors:	東方技術學院電機工程系
Keywords:	Fuzzy system adaptive algorithm classification problem pattern recognition
Date:	2008-06-27
Issue Date:	2010-12-24 16:19:09 (UTC+8)
Abstract:	The problem of the data analysis and the pattern recognition, searching the relationship between the feature variables of a database and inferred results are special important. In this paper, a fuzzy classification model is established to solve the classification problem. And the objective is to propose an adaptive classification system that can be generating the fuzzy IF-THEN rules automatically and revising the confidence value dynamically. The dynamic adaptive modification algorithm is employed to modify the confidence value while that rule becomes an essential factor for classification problem. Finally, the well-known Iris and Wine databases are exploited to test the performances. Simulations demonstrate that the proposed method can provide sufficiently high classification rate even with higher feature dimension.
Relation:	SMCia 2008 IEEEConference on soft Computing in Industrial Applications
Appears in Collections:	[Department of Electrical Engineering] conference

Files in This Item:

There are no files associated with this item.