Bio-signal identification using simple growing RBF-network (OLACA)
An enhanced online adaptive centre allocation algorithms (or resource allocation network (RAN)) using simple/stochastic back-propagation method with minimal weight update variant are developed for direct-link radial basis function (DRBF) networks. These algorithms are developed primarily for applica...
Saved in:
Main Authors: | , , |
---|---|
Format: | Conference or Workshop Item |
Published: |
2007
|
Subjects: | |
Online Access: | http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4658387 http://eprints.utp.edu.my/4037/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.utp.eprints.4037 |
---|---|
record_format |
eprints |
spelling |
my.utp.eprints.40372011-01-17T01:33:45Z Bio-signal identification using simple growing RBF-network (OLACA) Asirvadam , Vijanth Sagayan McLoone, Sean Palaniappan, R TK Electrical engineering. Electronics Nuclear engineering QA75 Electronic computers. Computer science An enhanced online adaptive centre allocation algorithms (or resource allocation network (RAN)) using simple/stochastic back-propagation method with minimal weight update variant are developed for direct-link radial basis function (DRBF) networks. These algorithms are developed primarily for applications with fast sampling rate which demands significant reduction in computation load per iteration. The new algorithms are evaluated on a chaotic nonlinear biological based time series signals such as electroencephalographic (EEG) and electrocardiography (ECG). The EEG and ECG signals not only shows non-stationary behaviour but also large oscillation or changes. When the sample time is in milliseconds, both neural network adaptation and weight update must take place within the short time frame thus any learning rule must be computationally simple. The second order techniques, such as extended Kalman filter (EKF), need large amount of memory O(N2) and computationally intensive. The main goal of this paper is to develop a simple back-propagation based (SBP) resource allocation network (RAN), or also known as sequential learning technique using Radial Basis Function by incorporating Gaussian kernel, in order to identify (model) EEG and ECG signals. Simulation results show the modeled data show good representation of the original signals with less prediction error. 2007-11 Conference or Workshop Item PeerReviewed http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4658387 Asirvadam , Vijanth Sagayan and McLoone, Sean and Palaniappan, R (2007) Bio-signal identification using simple growing RBF-network (OLACA). In: International Conference on Intelligent and Advanced Systems, 2007. ICIAS 2007. , 25-28 Nov 2007, Kuala Lumpur. http://eprints.utp.edu.my/4037/ |
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 Asirvadam , Vijanth Sagayan McLoone, Sean Palaniappan, R Bio-signal identification using simple growing RBF-network (OLACA) |
description |
An enhanced online adaptive centre allocation algorithms (or resource allocation network (RAN)) using simple/stochastic back-propagation method with minimal weight update variant are developed for direct-link radial basis function (DRBF) networks. These algorithms are developed primarily for applications with fast sampling rate which demands significant reduction in computation load per iteration. The new algorithms are evaluated on a chaotic nonlinear biological based time series signals such as electroencephalographic (EEG) and electrocardiography (ECG). The EEG and ECG signals not only shows non-stationary behaviour but also large oscillation or changes. When the sample time is in milliseconds, both neural network adaptation and weight update must take place within the short time frame thus any learning rule must be computationally simple. The second order techniques, such as extended Kalman filter (EKF), need large amount of memory O(N2) and computationally intensive. The main goal of this paper is to develop a simple back-propagation based (SBP) resource allocation network (RAN), or also known as sequential learning technique using Radial Basis Function by incorporating Gaussian kernel, in order to identify (model) EEG and ECG signals. Simulation results show the modeled data show good representation of the original signals with less prediction error. |
format |
Conference or Workshop Item |
author |
Asirvadam , Vijanth Sagayan McLoone, Sean Palaniappan, R |
author_facet |
Asirvadam , Vijanth Sagayan McLoone, Sean Palaniappan, R |
author_sort |
Asirvadam , Vijanth Sagayan |
title |
Bio-signal identification using simple growing RBF-network (OLACA) |
title_short |
Bio-signal identification using simple growing RBF-network (OLACA) |
title_full |
Bio-signal identification using simple growing RBF-network (OLACA) |
title_fullStr |
Bio-signal identification using simple growing RBF-network (OLACA) |
title_full_unstemmed |
Bio-signal identification using simple growing RBF-network (OLACA) |
title_sort |
bio-signal identification using simple growing rbf-network (olaca) |
publishDate |
2007 |
url |
http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4658387 http://eprints.utp.edu.my/4037/ |
_version_ |
1738655315732201472 |
score |
13.209306 |