Paper Info
Title
A Novel Hybrid Model for Information Processing Basing on Rough Sets and Fuzzy SVM
Abstract
Rough set theory (RST) is a new effective tool in dealing with vagueness and uncertainty information from a large number of data. Fuzzy support vector machine (FSVM) has become the focus of research in machine learning. And it greatly improves the capabilities of fault-tolerance and generalization of standard support vector machine. The hybrid model of RS-FSVM inherits the merits of RS and FSVM, and is applied into fused image quality evaluation in this paper. RST is used as preprocessing step to improve the performances of FSVM. A large number of experimental results show that when the number training samples are enough RS-SVM can achieve higher precision of classification than methods of FSVM and SVM.
Year
DOI
Venue
2008
10.1109/MUE.2008.68
MUE
Keywords
DocType
ISBN
rough set theory,fuzzy set theory,higher precision,image fusion,rough set,fuzzy support vector machine,fuzzy svm,learning (artificial intelligence),number training sample,fused image quality evaluation,large number,fault tolerance,standard support vector machine,image classification,rough sets,information processing,hybrid model,machine learning,enough rs-svm,fault-tolerance,information processing basing,novel hybrid model,support vector machines,fuzzy sets,learning artificial intelligence,set theory,support vector machine,uncertainty,image quality,fault tolerant
Conference
978-0-7695-3134-2
Citations 
PageRank 
References 
1
0.35
3
Authors
2
Name
Order
Citations
PageRank
Guang-ming Xian1514.58
Bi-qing Zeng2184.83