A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed
This research aimed at modelling and predicting the antioxidant activities of Amaranthus viridis seed extract using four (4) data-driven models. Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbour (k-NN), and Decision Tree (DT) were used as modelling algorithms for the...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024005371 |
_version_ | 1797304532911259648 |
---|---|
author | Babatunde Olawoye Oladapo Fisoye Fagbohun Oyekemi Popoola-Akinola Jide Ebenezer Taiwo Akinsola Charles Taiwo Akanbi |
author_facet | Babatunde Olawoye Oladapo Fisoye Fagbohun Oyekemi Popoola-Akinola Jide Ebenezer Taiwo Akinsola Charles Taiwo Akanbi |
author_sort | Babatunde Olawoye |
collection | DOAJ |
description | This research aimed at modelling and predicting the antioxidant activities of Amaranthus viridis seed extract using four (4) data-driven models. Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbour (k-NN), and Decision Tree (DT) were used as modelling algorithms for the construction of a non-linear empirical model to predict the antioxidant properties of Amaranthus viridis seed extract. Datasets for the modelling operation were obtained from a Box Behnken design while the hyperparameters of the ANN, SVM, k-NN and DT were determined using a 10-fold cross-validation technique. Among the Machine Learning algorithms, DT was observed to exhibit excellent performance and outperformed other Machine Learning algorithms in predicting the antioxidant activities of the seed extract, with a sensitivity of 0.867, precision of 0.928, area under the curve of 0.979, root mean square error of 0.184 and correlation coefficient of 0.9878. It was closely followed by ANN which was used to analyze and explain in detail the effect of the independent variables on the antioxidant activities of the seed extracts. This result affirmed the suitability of DT in predicting the antioxidant activities of Amaranthus viridis. |
first_indexed | 2024-03-08T00:11:49Z |
format | Article |
id | doaj.art-1a6520f961034239a96ef88ea69233dd |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-03-08T00:11:49Z |
publishDate | 2024-02-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-1a6520f961034239a96ef88ea69233dd2024-02-17T06:38:12ZengElsevierHeliyon2405-84402024-02-01103e24506A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seedBabatunde Olawoye0Oladapo Fisoye Fagbohun1Oyekemi Popoola-Akinola2Jide Ebenezer Taiwo Akinsola3Charles Taiwo Akanbi4Department of Food Science and Technology, First Technical University, Ibadan, Oyo State, Nigeria; Corresponding author.Department of Biology, Wilmington College, Wilmington, OH, USADepartment of Food Science and Technology, First Technical University, Ibadan, Oyo State, NigeriaDepartment of Computer Science, First Technical University, Ibadan, Oyo State, NigeriaDepartment of Food Science and Technology, First Technical University, Ibadan, Oyo State, Nigeria; Department of Food Science and Technology, Obafemi Awolowo University Ile-Ife, NigeriaThis research aimed at modelling and predicting the antioxidant activities of Amaranthus viridis seed extract using four (4) data-driven models. Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbour (k-NN), and Decision Tree (DT) were used as modelling algorithms for the construction of a non-linear empirical model to predict the antioxidant properties of Amaranthus viridis seed extract. Datasets for the modelling operation were obtained from a Box Behnken design while the hyperparameters of the ANN, SVM, k-NN and DT were determined using a 10-fold cross-validation technique. Among the Machine Learning algorithms, DT was observed to exhibit excellent performance and outperformed other Machine Learning algorithms in predicting the antioxidant activities of the seed extract, with a sensitivity of 0.867, precision of 0.928, area under the curve of 0.979, root mean square error of 0.184 and correlation coefficient of 0.9878. It was closely followed by ANN which was used to analyze and explain in detail the effect of the independent variables on the antioxidant activities of the seed extracts. This result affirmed the suitability of DT in predicting the antioxidant activities of Amaranthus viridis.http://www.sciencedirect.com/science/article/pii/S2405844024005371Data-driven modelsSupport vector machineAntioxidantDecision treeAmaranthus viridis |
spellingShingle | Babatunde Olawoye Oladapo Fisoye Fagbohun Oyekemi Popoola-Akinola Jide Ebenezer Taiwo Akinsola Charles Taiwo Akanbi A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed Heliyon Data-driven models Support vector machine Antioxidant Decision tree Amaranthus viridis |
title | A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed |
title_full | A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed |
title_fullStr | A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed |
title_full_unstemmed | A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed |
title_short | A supervised machine learning approach for the prediction of antioxidant activities of Amaranthus viridis seed |
title_sort | supervised machine learning approach for the prediction of antioxidant activities of amaranthus viridis seed |
topic | Data-driven models Support vector machine Antioxidant Decision tree Amaranthus viridis |
url | http://www.sciencedirect.com/science/article/pii/S2405844024005371 |
work_keys_str_mv | AT babatundeolawoye asupervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT oladapofisoyefagbohun asupervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT oyekemipopoolaakinola asupervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT jideebenezertaiwoakinsola asupervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT charlestaiwoakanbi asupervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT babatundeolawoye supervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT oladapofisoyefagbohun supervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT oyekemipopoolaakinola supervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT jideebenezertaiwoakinsola supervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed AT charlestaiwoakanbi supervisedmachinelearningapproachforthepredictionofantioxidantactivitiesofamaranthusviridisseed |