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

Bibliographic Details
Main Authors: NAC, Andryani, VS, Asirvadam, NH, Hamid
Format: Conference or Workshop Item
Language:English
Published: 2009
Subjects:
Online Access:http://scholars.utp.edu.my/id/eprint/2333/
http://scholars.utp.edu.my/id/eprint/2333/1/SAMPLE_PAPER_PDF.pdf
_version_ 1848659231763333120
author NAC, Andryani
VS, Asirvadam
NH, Hamid
author_facet NAC, Andryani
VS, Asirvadam
NH, Hamid
author_sort NAC, Andryani
building UTP Institutional Repository
collection Online Access
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.
first_indexed 2025-11-13T07:27:09Z
format Conference or Workshop Item
id oai:scholars.utp.edu.my:2333
institution Universiti Teknologi Petronas
institution_category Local University
language English
last_indexed 2025-11-13T07:27:09Z
publishDate 2009
recordtype eprints
repository_type Digital Repository
spelling oai:scholars.utp.edu.my:23332017-01-19T08:25:52Z http://scholars.utp.edu.my/id/eprint/2333/ Finite Difference Approach on RBF Networks for On-line System Identification with Lost Packet NAC, Andryani VS, Asirvadam NH, Hamid TK Electrical engineering. Electronics Nuclear engineering 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 Conference or Workshop Item PeerReviewed application/pdf en http://scholars.utp.edu.my/id/eprint/2333/1/SAMPLE_PAPER_PDF.pdf NAC, Andryani and VS, Asirvadam and NH, Hamid (2009) Finite Difference Approach on RBF Networks for On-line System Identification with Lost Packet. In: International Conference on Electrical Engineering and Informatics, AUG 05-07, 2009, Bangi, MALAYSIA. http://apps.isiknowledge.com/full_record.do?product=WOS&search_mode=GeneralSearch&qid=31&SID=V2M3DaJN@i6obPF9OiE&page=1&doc=1
spellingShingle TK Electrical engineering. Electronics Nuclear engineering
NAC, Andryani
VS, Asirvadam
NH, Hamid
Finite Difference Approach on RBF Networks for On-line System Identification with Lost Packet
title 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_short 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
topic TK Electrical engineering. Electronics Nuclear engineering
url http://scholars.utp.edu.my/id/eprint/2333/
http://scholars.utp.edu.my/id/eprint/2333/
http://scholars.utp.edu.my/id/eprint/2333/1/SAMPLE_PAPER_PDF.pdf