mirage

Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance

DSpace/Manakin Repository

 

Search DR-NTU


Advanced Search Subject Search

Browse

My Account

Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance

Show simple item record

dc.contributor.author Fu, Xiuju
dc.contributor.author Wang, Lipo
dc.date.accessioned 2012-06-12T06:41:58Z
dc.date.available 2012-06-12T06:41:58Z
dc.date.copyright 2003
dc.date.issued 2012-06-12
dc.identifier.citation Fu, X., & Wang, L. (2003). Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance. IEEE Transactions on Systems, Man, and Cybernetics – Part B: Cybernetics, 33(3), 399-409.
dc.identifier.uri http://hdl.handle.net/10220/8196
dc.description.abstract For high dimensional data, if no preprocessing is carried out before inputting patterns to classifiers, the computation required may be too heavy. For example, the number of hidden units of a radial basis function (RBF) neural network can be too large. This is not suitable for some practical applications due to speed and memory constraints. In many cases, some attributes are not relevant to concepts in the data at all. In this paper, we propose a novel separability-correlation measure (SCM) to rank the importance of attributes. According to the attribute ranking results, different attribute subsets are used as inputs to a classifier, such as an RBF neural network. Those attributes that increase the validation error are deemed irrelevant and are deleted. The complexity of the classifier can thus be reduced and its classification performance improved. Computer simulations show that our method for attribute importance ranking leads to smaller attribute subsets with higher accuracies compared with the existing SUD and Relief-F methods. We also propose a modified method for efficient construction of an RBF classifier. In this method we allow for large overlaps between clusters corresponding to the same class label. Our approach significantly reduces the structural complexity of the RBF network and improves the classification performance.
dc.format.extent 11 p.
dc.language.iso en
dc.relation.ispartofseries IEEE transactions on systems, man, and cybernetics – Part B: cybernetics
dc.rights © 2003 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TSMCB.2003.810911].
dc.subject DRNTU::Engineering::Electrical and electronic engineering
dc.title Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance
dc.type Journal Article
dc.contributor.school School of Electrical and Electronic Engineering
dc.identifier.doi http://dx.doi.org/10.1109/TSMCB.2003.810911
dc.description.version Accepted version

Files in this item

Files Size Format View
27. Data dimens ... RBF network structure.pdf 639.6Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Statistics

Total views

All Items Views
Data dimensionality reduction with application to simplifying RBF network structure and improving classification performance 231

Total downloads

All Bitstreams Views
27. Data dimensionality reduction with application to simplifying RBF network structure.pdf 147

Top country downloads

Country Code Views
United States of America 59
India 18
China 15
Singapore 14
Unknown Country 8

Top city downloads

city Views
Mountain View 40
Singapore 14
New Delhi 8
Taipei 6
Madras 4