You are not logged in.

Robust single-hidden layer feedforward network-based pattern classifier

Man, Zhihong, Lee, Kevin, Wang, Dianhui, Cao, Zhenwei and Khoo, Suiyang 2012, Robust single-hidden layer feedforward network-based pattern classifier, IEEE transactions on neural networks and learning systems, vol. 23, no. 12, pp. 1974-1986, doi: 10.1109/TNNLS.2012.2218616.

Attached Files
Name Description MIMEType Size Downloads

Title Robust single-hidden layer feedforward network-based pattern classifier
Author(s) Man, Zhihong
Lee, Kevin
Wang, Dianhui
Cao, Zhenwei
Khoo, Suiyang
Journal name IEEE transactions on neural networks and learning systems
Volume number 23
Issue number 12
Start page 1974
End page 1986
Total pages 13
Publisher IEEE
Place of publication Piscataway, N. J.
Publication date 2012-12
ISSN 2162-237X
2162-2388
Keyword(s) Discrete Fourier transform
regularization theory
pattern classification
feedforward networks
Summary In this paper, a new robust single-hidden layer feedforward network (SLFN)-based pattern classifier is developed. It is shown that the frequency spectrums of the desired feature vectors can be specified in terms of the discrete Fourier transform (DFT) technique. The input weights of the SLFN are then optimized with the regularization theory such that the error between the frequency components of the desired feature vectors and the ones of the feature vectors extracted from the outputs of the hidden layer is minimized. For the linearly separable input patterns, the hidden layer of the SLFN plays the role of removing the effects of the disturbance from the noisy input data and providing the linearly separable feature vectors for the accurate classification. However, for the nonlinearly separable input patterns, the hidden layer is capable of assigning the DFTs of all feature vectors to the desired positions in the frequencydomain such that the separability of all nonlinearly separable patterns are maximized. In addition, the output weights of the SLFN are also optimally designed so that both the empirical and the structural risks are well balanced and minimized in a noisy environment. Two simulation examples are presented to show the excellent performance and effectiveness of the proposed classification scheme.
Language eng
DOI 10.1109/TNNLS.2012.2218616
Field of Research 080108 Neural, Evolutionary and Fuzzy Computation
090602 Control Systems, Robotics and Automation
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category C1 Refereed article in a scholarly journal
Persistent URL http://hdl.handle.net/10536/DRO/DU:30049525

Document type: Journal Article
Collection: School of Engineering
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 17 times in TR Web of Science
Scopus Citation Count Cited 23 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 251 Abstract Views, 3 File Downloads  -  Detailed Statistics
Created: Wed, 28 Nov 2012, 19:19:53 EST by Sui Yang Khoo

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.