Optimization of computational intelligence approach for the prediction of glutinous rice dehydration

BACKGROUND: Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution of moisture during the dehydration process of glutinous...

Full description

Bibliographic Details
Main Authors: Jimoh, Kabiru Ayobami, Hashim, Norhashila, Shamsudin, Rosnah, Che Man, Hasfalina, Jahari, Mahirah
Format: Article
Published: John Wiley and Sons Ltd 2024
Online Access:http://psasir.upm.edu.my/id/eprint/112883/
_version_ 1848866065734434816
author Jimoh, Kabiru Ayobami
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Jahari, Mahirah
author_facet Jimoh, Kabiru Ayobami
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Jahari, Mahirah
author_sort Jimoh, Kabiru Ayobami
building UPM Institutional Repository
collection Online Access
description BACKGROUND: Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution of moisture during the dehydration process of glutinous rice. The hyperparameters of the models were optimized with three strategies: Bayesian optimization, grid search and random search. To understand the parameters that facilitate intelligence model adaptation to the dehydration process, global sensitivity analysis (GSA) was used to compute the impact of the input variables on the model output. RESULT: The result shows that the optimum computational intelligence techniques include the 3-9-1 topology trained with Bayesian regulation function for ANN, Gaussian kernel function for SVM, Matérn covariance function combined with zero mean function for GPR, boosting method for EoT and 4 minimum leaf size for DT. GPR has the highest performance with R2 of 100% and 99.71% during calibration and testing of the model, respectively. GSA reveals that all the models significantly rely on the variation in time as the main factor that affects the model outputs. CONCLUSION: Therefore, the computational intelligence models, especially GPR, can be applied for an effective description of moisture evolution during small-scale and industrial dehydration of glutinous rice. © 2024 Society of Chemical Industry. © 2024 Society of Chemical Industry.
first_indexed 2025-11-15T14:14:41Z
format Article
id upm-112883
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T14:14:41Z
publishDate 2024
publisher John Wiley and Sons Ltd
recordtype eprints
repository_type Digital Repository
spelling upm-1128832024-11-06T01:56:05Z http://psasir.upm.edu.my/id/eprint/112883/ Optimization of computational intelligence approach for the prediction of glutinous rice dehydration Jimoh, Kabiru Ayobami Hashim, Norhashila Shamsudin, Rosnah Che Man, Hasfalina Jahari, Mahirah BACKGROUND: Five computational intelligence approaches, namely Gaussian process regression (GPR), artificial neural network (ANN), decision tree (DT), ensemble of trees (EoT) and support vector machine (SVM), were used to describe the evolution of moisture during the dehydration process of glutinous rice. The hyperparameters of the models were optimized with three strategies: Bayesian optimization, grid search and random search. To understand the parameters that facilitate intelligence model adaptation to the dehydration process, global sensitivity analysis (GSA) was used to compute the impact of the input variables on the model output. RESULT: The result shows that the optimum computational intelligence techniques include the 3-9-1 topology trained with Bayesian regulation function for ANN, Gaussian kernel function for SVM, Matérn covariance function combined with zero mean function for GPR, boosting method for EoT and 4 minimum leaf size for DT. GPR has the highest performance with R2 of 100% and 99.71% during calibration and testing of the model, respectively. GSA reveals that all the models significantly rely on the variation in time as the main factor that affects the model outputs. CONCLUSION: Therefore, the computational intelligence models, especially GPR, can be applied for an effective description of moisture evolution during small-scale and industrial dehydration of glutinous rice. © 2024 Society of Chemical Industry. © 2024 Society of Chemical Industry. John Wiley and Sons Ltd 2024 Article PeerReviewed Jimoh, Kabiru Ayobami and Hashim, Norhashila and Shamsudin, Rosnah and Che Man, Hasfalina and Jahari, Mahirah (2024) Optimization of computational intelligence approach for the prediction of glutinous rice dehydration. Journal of the Science of Food and Agriculture, 104 (10). pp. 6208-6220. ISSN 0022-5142; eISSN: 1097-0010 https://scijournals.onlinelibrary.wiley.com/doi/10.1002/jsfa.13445 10.1002/jsfa.13445
spellingShingle Jimoh, Kabiru Ayobami
Hashim, Norhashila
Shamsudin, Rosnah
Che Man, Hasfalina
Jahari, Mahirah
Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title_full Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title_fullStr Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title_full_unstemmed Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title_short Optimization of computational intelligence approach for the prediction of glutinous rice dehydration
title_sort optimization of computational intelligence approach for the prediction of glutinous rice dehydration
url http://psasir.upm.edu.my/id/eprint/112883/
http://psasir.upm.edu.my/id/eprint/112883/
http://psasir.upm.edu.my/id/eprint/112883/