封面圖片

Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate

In this study, an artificial neural network (ANN) trained by backpropagation algorithm, Levenberg–Marquadart, was applied to predict the yield of enzymatic synthesis of dioctyl adipate. Immobilized Candida antarctica lipase B was used as a biocatalyst for the reaction. Temperature, time, amount of e...

全面介紹

Saved in:
書目詳細資料
Main Authors: Abdul Rahman, Mohd Basyaruddin, Chaibakhsh, Naz, Basri, Mahiran, Salleh, Abu Bakar, Raja Abdul Rahman, Raja Noor Zaliha
格式: Article
語言:English
出版: Humana Press 2009
在線閱讀:http://psasir.upm.edu.my/id/eprint/13222/1/Application%20of%20artificial%20neural%20network%20for%20yield%20prediction%20of%20lipase.pdf
http://psasir.upm.edu.my/id/eprint/13222/
http://link.springer.com/article/10.1007/s12010-008-8465-z?view=classic
標簽: 添加標簽
沒有標簽, 成為第一個標記此記錄!
id my.upm.eprints.13222
record_format eprints
spelling my.upm.eprints.132222016-09-27T04:14:19Z http://psasir.upm.edu.my/id/eprint/13222/ Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate Abdul Rahman, Mohd Basyaruddin Chaibakhsh, Naz Basri, Mahiran Salleh, Abu Bakar Raja Abdul Rahman, Raja Noor Zaliha In this study, an artificial neural network (ANN) trained by backpropagation algorithm, Levenberg–Marquadart, was applied to predict the yield of enzymatic synthesis of dioctyl adipate. Immobilized Candida antarctica lipase B was used as a biocatalyst for the reaction. Temperature, time, amount of enzyme, and substrate molar ratio were the four input variables. After evaluating various ANN configurations, the best network was composed of seven hidden nodes using a hyperbolic tangent sigmoid transfer function. The correlation coefficient (R 2) and mean absolute error (MAE) values between the actual and predicted responses were determined as 0.9998 and 0.0966 for training set and 0.9241 and 1.9439 for validating dataset. A simulation test with a testing dataset showed that the MAE was low and R 2 was close to 1. These results imply the good generalization of the developed model and its capability to predict the reaction yield. Comparison of the performance of radial basis network with the developed models showed that radial basis function was more accurate but its performance was poor when tested with unseen data. In further part of the study, the feed forward back propagation model was used for prediction of the ester yield within the given range of the main parameters. Humana Press 2009-09-01 Article PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/13222/1/Application%20of%20artificial%20neural%20network%20for%20yield%20prediction%20of%20lipase.pdf Abdul Rahman, Mohd Basyaruddin and Chaibakhsh, Naz and Basri, Mahiran and Salleh, Abu Bakar and Raja Abdul Rahman, Raja Noor Zaliha (2009) Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate. Applied Biochemistry and Biotechnology, 158 (3). pp. 722-735. ISSN 0273-2289; ESSN: 1559-0291 http://link.springer.com/article/10.1007/s12010-008-8465-z?view=classic 10.1007/s12010-008-8465-z
institution Universiti Putra Malaysia
building UPM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Putra Malaysia
content_source UPM Institutional Repository
url_provider http://psasir.upm.edu.my/
language English
description In this study, an artificial neural network (ANN) trained by backpropagation algorithm, Levenberg–Marquadart, was applied to predict the yield of enzymatic synthesis of dioctyl adipate. Immobilized Candida antarctica lipase B was used as a biocatalyst for the reaction. Temperature, time, amount of enzyme, and substrate molar ratio were the four input variables. After evaluating various ANN configurations, the best network was composed of seven hidden nodes using a hyperbolic tangent sigmoid transfer function. The correlation coefficient (R 2) and mean absolute error (MAE) values between the actual and predicted responses were determined as 0.9998 and 0.0966 for training set and 0.9241 and 1.9439 for validating dataset. A simulation test with a testing dataset showed that the MAE was low and R 2 was close to 1. These results imply the good generalization of the developed model and its capability to predict the reaction yield. Comparison of the performance of radial basis network with the developed models showed that radial basis function was more accurate but its performance was poor when tested with unseen data. In further part of the study, the feed forward back propagation model was used for prediction of the ester yield within the given range of the main parameters.
format Article
author Abdul Rahman, Mohd Basyaruddin
Chaibakhsh, Naz
Basri, Mahiran
Salleh, Abu Bakar
Raja Abdul Rahman, Raja Noor Zaliha
spellingShingle Abdul Rahman, Mohd Basyaruddin
Chaibakhsh, Naz
Basri, Mahiran
Salleh, Abu Bakar
Raja Abdul Rahman, Raja Noor Zaliha
Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
author_facet Abdul Rahman, Mohd Basyaruddin
Chaibakhsh, Naz
Basri, Mahiran
Salleh, Abu Bakar
Raja Abdul Rahman, Raja Noor Zaliha
author_sort Abdul Rahman, Mohd Basyaruddin
title Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
title_short Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
title_full Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
title_fullStr Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
title_full_unstemmed Application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
title_sort application of artificial neural network for yield prediction of lipase-catalyzed synthesis of dioctyl adipate
publisher Humana Press
publishDate 2009
url http://psasir.upm.edu.my/id/eprint/13222/1/Application%20of%20artificial%20neural%20network%20for%20yield%20prediction%20of%20lipase.pdf
http://psasir.upm.edu.my/id/eprint/13222/
http://link.springer.com/article/10.1007/s12010-008-8465-z?view=classic
_version_ 1643825265886887936
score 13.251813

相似書籍