Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming

The application of a versatile approach for modeling and prediction the moisture content of dried peels was evaluated using both empirical and semi-empirical equations (Lewis, Page, Henderson and Pabis, Modified Page, Logarithmic, and Modified Logistic) as well as machine learning models (K-nearest...

Full description

Saved in:
Bibliographic Details
Main Authors: Maressa O. Camilo, Romero F. Carvalho, Ariany B.S. Costa, Esly F.C. Junior, Andréa O.S. Costa, Robson C. Sousa
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:South African Journal of Chemical Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1026918524001203
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832595410747654144
author Maressa O. Camilo
Romero F. Carvalho
Ariany B.S. Costa
Esly F.C. Junior
Andréa O.S. Costa
Robson C. Sousa
author_facet Maressa O. Camilo
Romero F. Carvalho
Ariany B.S. Costa
Esly F.C. Junior
Andréa O.S. Costa
Robson C. Sousa
author_sort Maressa O. Camilo
collection DOAJ
description The application of a versatile approach for modeling and prediction the moisture content of dried peels was evaluated using both empirical and semi-empirical equations (Lewis, Page, Henderson and Pabis, Modified Page, Logarithmic, and Modified Logistic) as well as machine learning models (K-nearest neighbor | KNN, Decision Tree | DT, Artificial Neural Network | ANN and Support Vector Regression | SVR). Heuristic optimization methods, including genetic algorithms (GA) and nonlinear programming (NLP), were employed to identify the best empirical and semi-empirical models for estimating moisture content during the drying process of lemon peel layers. The parameters of the drying kinetics models were optimized using GA to achieve the best results. It was found that as the number of model parameters increases, particularly in models such as the logarithmic one, the optimization problem becomes more complex. Consequently, accurate initial guesses become increasingly important, emphasizing the need for heuristic methods like genetic algorithms. This optimization approach provided excellent performance metrics (R2 > 0.9715, SSR 〈 0.0625 and MSE < 0.0026 for endocarp and R2 〉 0.9678, SSR < 0.0755 and MSE < 0.0030 for epicarp). The models proposed in this study achieved the best results with the modified logistic equation (R2 > 0.9923, MSE 〈 0.0001 and SSR < 0.0013 for endocarp and R2 〉 0.9905, MSE < 0.0001 and SSR < 0.0013 for epicarp). In particular, the multilayer perceptron neural network of the machine learning proved to be the optimal choice as it best accounts for the complexity of the drying kinetics of lemons. This neural network model outperformed traditional empirical and semi-empirical models, demonstrating superior performance metrics (R2 > 0.9979, MSE 〈 0.0002 and SSR < 0.0012 for endocarp and R2 〉 0.9989, MSE < 0.0001 and SSR < 0.0008 for epicarp) when tested against validation data.
format Article
id doaj-art-9229a602c03d46f5b1f34a984ddb0b1c
institution Kabale University
issn 1026-9185
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series South African Journal of Chemical Engineering
spelling doaj-art-9229a602c03d46f5b1f34a984ddb0b1c2025-01-19T06:24:14ZengElsevierSouth African Journal of Chemical Engineering1026-91852025-01-0151136152Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programmingMaressa O. Camilo0Romero F. Carvalho1Ariany B.S. Costa2Esly F.C. Junior3Andréa O.S. Costa4Robson C. Sousa5Laboratory of Transport Phenomena and Unit Operations (LaFTOP), Center of Agricultural Sciences and Engineering, Federal University of Espírito Santo, Alto Universitário, 29500-000, Guararema, Alegre, ES, BrazilLaboratory of Transport Phenomena and Unit Operations (LaFTOP), Center of Agricultural Sciences and Engineering, Federal University of Espírito Santo, Alto Universitário, 29500-000, Guararema, Alegre, ES, BrazilLaboratory of Transport Phenomena and Unit Operations (LaFTOP), Center of Agricultural Sciences and Engineering, Federal University of Espírito Santo, Alto Universitário, 29500-000, Guararema, Alegre, ES, BrazilChemical Engineering Program, Federal University of Minas Gerais, Av. Presidente Antônio Carlos, 6627, 31270-901, Belo Horizonte, Minas Gerais, MG, BrazilChemical Engineering Program, Federal University of Minas Gerais, Av. Presidente Antônio Carlos, 6627, 31270-901, Belo Horizonte, Minas Gerais, MG, BrazilLaboratory of Transport Phenomena and Unit Operations (LaFTOP), Center of Agricultural Sciences and Engineering, Federal University of Espírito Santo, Alto Universitário, 29500-000, Guararema, Alegre, ES, Brazil; Corresponding author..The application of a versatile approach for modeling and prediction the moisture content of dried peels was evaluated using both empirical and semi-empirical equations (Lewis, Page, Henderson and Pabis, Modified Page, Logarithmic, and Modified Logistic) as well as machine learning models (K-nearest neighbor | KNN, Decision Tree | DT, Artificial Neural Network | ANN and Support Vector Regression | SVR). Heuristic optimization methods, including genetic algorithms (GA) and nonlinear programming (NLP), were employed to identify the best empirical and semi-empirical models for estimating moisture content during the drying process of lemon peel layers. The parameters of the drying kinetics models were optimized using GA to achieve the best results. It was found that as the number of model parameters increases, particularly in models such as the logarithmic one, the optimization problem becomes more complex. Consequently, accurate initial guesses become increasingly important, emphasizing the need for heuristic methods like genetic algorithms. This optimization approach provided excellent performance metrics (R2 > 0.9715, SSR 〈 0.0625 and MSE < 0.0026 for endocarp and R2 〉 0.9678, SSR < 0.0755 and MSE < 0.0030 for epicarp). The models proposed in this study achieved the best results with the modified logistic equation (R2 > 0.9923, MSE 〈 0.0001 and SSR < 0.0013 for endocarp and R2 〉 0.9905, MSE < 0.0001 and SSR < 0.0013 for epicarp). In particular, the multilayer perceptron neural network of the machine learning proved to be the optimal choice as it best accounts for the complexity of the drying kinetics of lemons. This neural network model outperformed traditional empirical and semi-empirical models, demonstrating superior performance metrics (R2 > 0.9979, MSE 〈 0.0002 and SSR < 0.0012 for endocarp and R2 〉 0.9989, MSE < 0.0001 and SSR < 0.0008 for epicarp) when tested against validation data.http://www.sciencedirect.com/science/article/pii/S1026918524001203DryingTahiti lemonEmpirical and semi-empirical modelsMachine learningGenetic algorithms
spellingShingle Maressa O. Camilo
Romero F. Carvalho
Ariany B.S. Costa
Esly F.C. Junior
Andréa O.S. Costa
Robson C. Sousa
Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
South African Journal of Chemical Engineering
Drying
Tahiti lemon
Empirical and semi-empirical models
Machine learning
Genetic algorithms
title Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
title_full Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
title_fullStr Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
title_full_unstemmed Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
title_short Drying kinetic for moisture content prediction of peels Tahiti lemon (Citrus latifolia): Approach by machine learning and optimization - genetic algorithms and nonlinear programming
title_sort drying kinetic for moisture content prediction of peels tahiti lemon citrus latifolia approach by machine learning and optimization genetic algorithms and nonlinear programming
topic Drying
Tahiti lemon
Empirical and semi-empirical models
Machine learning
Genetic algorithms
url http://www.sciencedirect.com/science/article/pii/S1026918524001203
work_keys_str_mv AT maressaocamilo dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming
AT romerofcarvalho dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming
AT arianybscosta dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming
AT eslyfcjunior dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming
AT andreaoscosta dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming
AT robsoncsousa dryingkineticformoisturecontentpredictionofpeelstahitilemoncitruslatifoliaapproachbymachinelearningandoptimizationgeneticalgorithmsandnonlinearprogramming