Empirical and feed forward neural networks models of tapioca starch hydrolysis

The aim of dynamic modeling of the tapioca starch hydrolysis process is to generate models for forecasting the future product concentration (glucose) from the initial conditions of available process measurements. This paper compares two methods of modeling the tapioca starch hydrolysis process: (1)...

Full description

Bibliographic Details
Main Authors: Rashid, Roslina, Jamaluddin, Hishamuddin, Saidina Amin, Nor Aishah
Format: Article
Published: Taylor & Francis 2006
Subjects:
Online Access:http://eprints.utm.my/7132/
_version_ 1848891408868442112
author Rashid, Roslina
Jamaluddin, Hishamuddin
Saidina Amin, Nor Aishah
author_facet Rashid, Roslina
Jamaluddin, Hishamuddin
Saidina Amin, Nor Aishah
author_sort Rashid, Roslina
building UTeM Institutional Repository
collection Online Access
description The aim of dynamic modeling of the tapioca starch hydrolysis process is to generate models for forecasting the future product concentration (glucose) from the initial conditions of available process measurements. This paper compares two methods of modeling the tapioca starch hydrolysis process: (1) The empirical approach and (2) the feed forward neural network (FFNN) approach. Experiments were conducted to obtain a set of data for the modeling purpose. The Gauss-Newton method was used for parameter estimation in the empirical analysis and a multilayer neural network with one hidden layer was utilized in the neural networks approach. This study indicates that the FFNN model of tapioca starch hydrolysis produces better predictive accuracy, that is simpler to develop and has a generalization capability compared with the empirical model.
first_indexed 2025-11-15T20:57:30Z
format Article
id utm-7132
institution Universiti Teknologi Malaysia
institution_category Local University
last_indexed 2025-11-15T20:57:30Z
publishDate 2006
publisher Taylor & Francis
recordtype eprints
repository_type Digital Repository
spelling utm-71322009-07-02T06:47:59Z http://eprints.utm.my/7132/ Empirical and feed forward neural networks models of tapioca starch hydrolysis Rashid, Roslina Jamaluddin, Hishamuddin Saidina Amin, Nor Aishah TJ Mechanical engineering and machinery The aim of dynamic modeling of the tapioca starch hydrolysis process is to generate models for forecasting the future product concentration (glucose) from the initial conditions of available process measurements. This paper compares two methods of modeling the tapioca starch hydrolysis process: (1) The empirical approach and (2) the feed forward neural network (FFNN) approach. Experiments were conducted to obtain a set of data for the modeling purpose. The Gauss-Newton method was used for parameter estimation in the empirical analysis and a multilayer neural network with one hidden layer was utilized in the neural networks approach. This study indicates that the FFNN model of tapioca starch hydrolysis produces better predictive accuracy, that is simpler to develop and has a generalization capability compared with the empirical model. Taylor & Francis 2006-06 Article PeerReviewed Rashid, Roslina and Jamaluddin, Hishamuddin and Saidina Amin, Nor Aishah (2006) Empirical and feed forward neural networks models of tapioca starch hydrolysis. Applied Artificial Intelligence, 20 (1). pp. 79-97. ISSN 0883-9514 http://dx.doi.org/10.1080/08839510500191422 10.1080/08839510500191422
spellingShingle TJ Mechanical engineering and machinery
Rashid, Roslina
Jamaluddin, Hishamuddin
Saidina Amin, Nor Aishah
Empirical and feed forward neural networks models of tapioca starch hydrolysis
title Empirical and feed forward neural networks models of tapioca starch hydrolysis
title_full Empirical and feed forward neural networks models of tapioca starch hydrolysis
title_fullStr Empirical and feed forward neural networks models of tapioca starch hydrolysis
title_full_unstemmed Empirical and feed forward neural networks models of tapioca starch hydrolysis
title_short Empirical and feed forward neural networks models of tapioca starch hydrolysis
title_sort empirical and feed forward neural networks models of tapioca starch hydrolysis
topic TJ Mechanical engineering and machinery
url http://eprints.utm.my/7132/
http://eprints.utm.my/7132/
http://eprints.utm.my/7132/