Nonlinear identification for dengue fever / Herlina Abdul Rahim.

This thesis presents the development of a non-invasive system identification for the monitoring of the progression of dengue infection based on hemoglobin concentration. Prior to the system development, a simple statistical approach were applied to process the dengue infection data. From this, five...

Full description

Saved in:

Bibliographic Details
Main Author:	Abdul Rahim, Herlina
Format:	Thesis
Language:	English
Published:	2009
Subjects:	Diseases due to physical agents Infectious and parasitic diseases
Online Access:	https://ir.uitm.edu.my/id/eprint/43387/1/43387.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-uitm-ir.43387
record_format	uketd_dc
spelling	my-uitm-ir.433872021-08-31T16:02:49Z Nonlinear identification for dengue fever / Herlina Abdul Rahim. 2009 Abdul Rahim, Herlina Diseases due to physical agents Infectious and parasitic diseases This thesis presents the development of a non-invasive system identification for the monitoring of the progression of dengue infection based on hemoglobin concentration. Prior to the system development, a simple statistical approach were applied to process the dengue infection data. From this, five significant variables, i.e. gender, weight, vomiting, reactance and day of fever were chosen to be the input variables. All of these are non-invasive parameters. The developed system uses the nonlinear system identification based on Artificial Neural Network (ANN), which involved Nonlinear Autoregressive (NAR), Nonlinear Autoregressive with exogenous Input (NARX) and Nonlinear Autoregressive Moving Average with exogenous Input (NARMAX). Each of the models is divided into two approaches, which are unregularized approach and regularized approach. The type of order selection criteria involves, The Final Prediction Error (FPE), Akaike's Information Criteria (AIC), and Lipschitz number. For comparison purposes, linear models which are Autoregressive (AR), Autoregressive with exogenous Input (ARX) and Autoregressive Moving Average with exogenous Input (ARMAX) were used. The findings indicate that NARMAX model with regularized approach yields better accuracy by 88.40%; this model is 100% better than the one recently published, i.e. using linear regression model with an accuracy of only 42%. The best parameters' settings for the NARMAX model can be found using the Lipschitz number criterion for the model order selection with artificial neural network structure of 5-2-1 trained using the Levenberg Marquardt algorithm. 2009 Thesis https://ir.uitm.edu.my/id/eprint/43387/ https://ir.uitm.edu.my/id/eprint/43387/1/43387.pdf text en public phd doctoral Universiti Teknologi MARA Faculty of Electrical Engineering Taib, Mohd. Nasir (Prof. Dr.)
institution	Universiti Teknologi MARA
collection	UiTM Institutional Repository
language	English
advisor	Taib, Mohd. Nasir (Prof. Dr.)
topic	Diseases due to physical agents Infectious and parasitic diseases
spellingShingle	Diseases due to physical agents Infectious and parasitic diseases Abdul Rahim, Herlina Nonlinear identification for dengue fever / Herlina Abdul Rahim.
description	This thesis presents the development of a non-invasive system identification for the monitoring of the progression of dengue infection based on hemoglobin concentration. Prior to the system development, a simple statistical approach were applied to process the dengue infection data. From this, five significant variables, i.e. gender, weight, vomiting, reactance and day of fever were chosen to be the input variables. All of these are non-invasive parameters. The developed system uses the nonlinear system identification based on Artificial Neural Network (ANN), which involved Nonlinear Autoregressive (NAR), Nonlinear Autoregressive with exogenous Input (NARX) and Nonlinear Autoregressive Moving Average with exogenous Input (NARMAX). Each of the models is divided into two approaches, which are unregularized approach and regularized approach. The type of order selection criteria involves, The Final Prediction Error (FPE), Akaike's Information Criteria (AIC), and Lipschitz number. For comparison purposes, linear models which are Autoregressive (AR), Autoregressive with exogenous Input (ARX) and Autoregressive Moving Average with exogenous Input (ARMAX) were used. The findings indicate that NARMAX model with regularized approach yields better accuracy by 88.40%; this model is 100% better than the one recently published, i.e. using linear regression model with an accuracy of only 42%. The best parameters' settings for the NARMAX model can be found using the Lipschitz number criterion for the model order selection with artificial neural network structure of 5-2-1 trained using the Levenberg Marquardt algorithm.
format	Thesis
qualification_name	Doctor of Philosophy (PhD.)
qualification_level	Doctorate
author	Abdul Rahim, Herlina
author_facet	Abdul Rahim, Herlina
author_sort	Abdul Rahim, Herlina
title	Nonlinear identification for dengue fever / Herlina Abdul Rahim.
title_short	Nonlinear identification for dengue fever / Herlina Abdul Rahim.
title_full	Nonlinear identification for dengue fever / Herlina Abdul Rahim.
title_fullStr	Nonlinear identification for dengue fever / Herlina Abdul Rahim.
title_full_unstemmed	Nonlinear identification for dengue fever / Herlina Abdul Rahim.
title_sort	nonlinear identification for dengue fever / herlina abdul rahim.
granting_institution	Universiti Teknologi MARA
granting_department	Faculty of Electrical Engineering
publishDate	2009
url	https://ir.uitm.edu.my/id/eprint/43387/1/43387.pdf
_version_	1783734689194835968

Nonlinear identification for dengue fever / Herlina Abdul Rahim.

Similar Items