Finite Difference approach on RBF networks for on-line system identification with lost packet

Radial Basis Function networks (RBF) is one form of feed forward neural network architecture which is popular besides multi layer preceptor (MLP). It is widely used especially in identifying a black box system. In many cases, identifying of the system process normally has lack of data or may lose so...

Full description

Saved in:
Bibliographic Details
Main Authors: Andryani, N.A.C., Asirvadam, V.S., Hamid, N.H.
Format: Conference or Workshop Item
Published: 2009
Subjects:
Online Access:http://eprints.utp.edu.my/4643/1/ieee2009Afny.pdf
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5254687
http://eprints.utp.edu.my/4643/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utp.eprints.4643
record_format eprints
spelling my.utp.eprints.46432017-01-19T08:25:16Z Finite Difference approach on RBF networks for on-line system identification with lost packet Andryani, N.A.C. Asirvadam, V.S. Hamid, N.H. TK Electrical engineering. Electronics Nuclear engineering QA75 Electronic computers. Computer science Radial Basis Function networks (RBF) is one form of feed forward neural network architecture which is popular besides multi layer preceptor (MLP). It is widely used especially in identifying a black box system. In many cases, identifying of the system process normally has lack of data or may lose some packets data needed in the identifying process. Finite Difference approach with its enhancement, Richardson Extrapolation, is used to improve the learning performance especially in the non linear learning parameter update for identifying system with lost packet data case in online manner. Since initializing of non linear learning's parameters is crucial in RBF networks' learning, random initialization is placed with some clustering method. Some unsupervised learning methods such as, K means clustering and Fuzzy K means clustering are used to replace it. All the possible combination methods in the initialization and update process try to improve the whole performance of the learning process regarding to the system identification with lost packet data case. It can be showed that Finite difference approach with dynamic step size on recursive prediction error for the non linear parameter update with appropriate initialization method succeed to perform better performance compared to extreme learning machine (ELM) as the previous learning method. 2009-08 Conference or Workshop Item NonPeerReviewed application/pdf http://eprints.utp.edu.my/4643/1/ieee2009Afny.pdf http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5254687 Andryani, N.A.C. and Asirvadam, V.S. and Hamid, N.H. (2009) Finite Difference approach on RBF networks for on-line system identification with lost packet. In: Electrical Engineering and Informatics, 2009. ICEEI '09. International Conference on, 5-7 Aug 2009, Bangi, Selangor, Malaysia. http://eprints.utp.edu.my/4643/
institution Universiti Teknologi Petronas
building UTP Resource Centre
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Petronas
content_source UTP Institutional Repository
url_provider http://eprints.utp.edu.my/
topic TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
QA75 Electronic computers. Computer science
Andryani, N.A.C.
Asirvadam, V.S.
Hamid, N.H.
Finite Difference approach on RBF networks for on-line system identification with lost packet
description Radial Basis Function networks (RBF) is one form of feed forward neural network architecture which is popular besides multi layer preceptor (MLP). It is widely used especially in identifying a black box system. In many cases, identifying of the system process normally has lack of data or may lose some packets data needed in the identifying process. Finite Difference approach with its enhancement, Richardson Extrapolation, is used to improve the learning performance especially in the non linear learning parameter update for identifying system with lost packet data case in online manner. Since initializing of non linear learning's parameters is crucial in RBF networks' learning, random initialization is placed with some clustering method. Some unsupervised learning methods such as, K means clustering and Fuzzy K means clustering are used to replace it. All the possible combination methods in the initialization and update process try to improve the whole performance of the learning process regarding to the system identification with lost packet data case. It can be showed that Finite difference approach with dynamic step size on recursive prediction error for the non linear parameter update with appropriate initialization method succeed to perform better performance compared to extreme learning machine (ELM) as the previous learning method.
format Conference or Workshop Item
author Andryani, N.A.C.
Asirvadam, V.S.
Hamid, N.H.
author_facet Andryani, N.A.C.
Asirvadam, V.S.
Hamid, N.H.
author_sort Andryani, N.A.C.
title Finite Difference approach on RBF networks for on-line system identification with lost packet
title_short Finite Difference approach on RBF networks for on-line system identification with lost packet
title_full Finite Difference approach on RBF networks for on-line system identification with lost packet
title_fullStr Finite Difference approach on RBF networks for on-line system identification with lost packet
title_full_unstemmed Finite Difference approach on RBF networks for on-line system identification with lost packet
title_sort finite difference approach on rbf networks for on-line system identification with lost packet
publishDate 2009
url http://eprints.utp.edu.my/4643/1/ieee2009Afny.pdf
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5254687
http://eprints.utp.edu.my/4643/
_version_ 1738655358962892800
score 13.211869