Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

Spray drying techniques are one of the methods to preserve and extend the shelf-life of coconut milk. The objective of this research was to create a particle swarm optimization–enhanced artificial neural network (PSO–ANN) that could predict the coconut milk spray drying process. The parameters for P...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jesse Lee Kar Ming, Mohd Shamsul Anuar, Muhammad Syahmeer How, Samsul Bahari Mohd Noor, Zalizawati Abdullah, Farah Saleena Taip
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	spray drying coconut milk artificial neural network particle swarm optimization processes Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/c9bc1236f93e45b2a9c8dc3cd6b93794
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c9bc1236f93e45b2a9c8dc3cd6b93794
record_format	dspace
spelling	oai:doaj.org-article:c9bc1236f93e45b2a9c8dc3cd6b937942021-11-25T17:34:24ZDevelopment of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk10.3390/foods101127082304-8158https://doaj.org/article/c9bc1236f93e45b2a9c8dc3cd6b937942021-11-01T00:00:00Zhttps://www.mdpi.com/2304-8158/10/11/2708https://doaj.org/toc/2304-8158Spray drying techniques are one of the methods to preserve and extend the shelf-life of coconut milk. The objective of this research was to create a particle swarm optimization–enhanced artificial neural network (PSO–ANN) that could predict the coconut milk spray drying process. The parameters for PSO tuning were selected as the number of particles and acceleration constant, respectively, for both global and personal best using a 2<sup>k</sup> factorial design. The optimal PSO settings were recorded as global best, C<sub>1</sub> = 4.0; personal best, C<sub>2</sub> = 0; and number of particles = 100. When comparing different types of spray drying models, PSO–ANN had an MSE value of 0.077, GA–ANN had an MSE of 0.033, while ANN had an MSE of 0.082. Sensitivity analysis was conducted on all three models to evaluate the significance level of each parameter on the model, and it was discovered that inlet temperature had the most significant influence on the model performance. In conclusion, the PSO–ANN was found to be more effective than ANN but less effective than GA–ANN in predicting the quality of coconut milk powder.Jesse Lee Kar MingMohd Shamsul AnuarMuhammad Syahmeer HowSamsul Bahari Mohd NoorZalizawati AbdullahFarah Saleena TaipMDPI AGarticlespray dryingcoconut milkartificial neural networkparticle swarm optimizationprocessesChemical technologyTP1-1185ENFoods, Vol 10, Iss 2708, p 2708 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	spray drying coconut milk artificial neural network particle swarm optimization processes Chemical technology TP1-1185
spellingShingle	spray drying coconut milk artificial neural network particle swarm optimization processes Chemical technology TP1-1185 Jesse Lee Kar Ming Mohd Shamsul Anuar Muhammad Syahmeer How Samsul Bahari Mohd Noor Zalizawati Abdullah Farah Saleena Taip Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
description	Spray drying techniques are one of the methods to preserve and extend the shelf-life of coconut milk. The objective of this research was to create a particle swarm optimization–enhanced artificial neural network (PSO–ANN) that could predict the coconut milk spray drying process. The parameters for PSO tuning were selected as the number of particles and acceleration constant, respectively, for both global and personal best using a 2<sup>k</sup> factorial design. The optimal PSO settings were recorded as global best, C<sub>1</sub> = 4.0; personal best, C<sub>2</sub> = 0; and number of particles = 100. When comparing different types of spray drying models, PSO–ANN had an MSE value of 0.077, GA–ANN had an MSE of 0.033, while ANN had an MSE of 0.082. Sensitivity analysis was conducted on all three models to evaluate the significance level of each parameter on the model, and it was discovered that inlet temperature had the most significant influence on the model performance. In conclusion, the PSO–ANN was found to be more effective than ANN but less effective than GA–ANN in predicting the quality of coconut milk powder.
format	article
author	Jesse Lee Kar Ming Mohd Shamsul Anuar Muhammad Syahmeer How Samsul Bahari Mohd Noor Zalizawati Abdullah Farah Saleena Taip
author_facet	Jesse Lee Kar Ming Mohd Shamsul Anuar Muhammad Syahmeer How Samsul Bahari Mohd Noor Zalizawati Abdullah Farah Saleena Taip
author_sort	Jesse Lee Kar Ming
title	Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
title_short	Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
title_full	Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
title_fullStr	Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
title_full_unstemmed	Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk
title_sort	development of an artificial neural network utilizing particle swarm optimization for modeling the spray drying of coconut milk
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c9bc1236f93e45b2a9c8dc3cd6b93794
work_keys_str_mv	AT jesseleekarming developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk AT mohdshamsulanuar developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk AT muhammadsyahmeerhow developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk AT samsulbaharimohdnoor developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk AT zalizawatiabdullah developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk AT farahsaleenataip developmentofanartificialneuralnetworkutilizingparticleswarmoptimizationformodelingthespraydryingofcoconutmilk
_version_	1718412253755080704

Development of an Artificial Neural Network Utilizing Particle Swarm Optimization for Modeling the Spray Drying of Coconut Milk

Ejemplares similares