Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression
The need to maintain the highest possible levels of bioactive components contained in raw materials requires the elaboration of tools supporting their processing operations, starting from the first stages of the food production chain. In this study, artificial neural networks (ANNs) and response sur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/27/8/2445 |
| _version_ | 1797409904268410880 |
|---|---|
| author | Jolanta Wawrzyniak Magdalena Rudzińska Marzena Gawrysiak-Witulska Krzysztof Przybył |
| author_facet | Jolanta Wawrzyniak Magdalena Rudzińska Marzena Gawrysiak-Witulska Krzysztof Przybył |
| author_sort | Jolanta Wawrzyniak |
| collection | DOAJ |
| description | The need to maintain the highest possible levels of bioactive components contained in raw materials requires the elaboration of tools supporting their processing operations, starting from the first stages of the food production chain. In this study, artificial neural networks (ANNs) and response surface regression (RSR) were used to develop models of phytosterol degradation in bulks of rapeseed stored under various temperatures and water activity conditions (<i>T</i> = 12–30 °C and <i>a<sub>w</sub></i> = 0.75–0.90). Among ANNs, networks based on a multilayer perceptron (MLP) and a radial basis function (RBF) were tested. The model input constituted <i>a<sub>w</sub></i>, temperature and storage time, whilst the model output was the phytosterol level in seeds. The ANN-based modeling turned out to be more effective in estimating phytosterol levels than the RSR, while MLP-ANNs proved to be more satisfactory than RBF-ANNs. The approximation quality of the ANNs models depended on the number of neurons and the type of activation functions in the hidden layer. The best model was provided by the MLP-ANN containing nine neurons in the hidden layer equipped with the logistic activation function. The model performance evaluation showed its high prediction accuracy and generalization capability (<i>R</i><sup>2</sup> = 0.978; <i>RMSE</i> = 0.140). Its accuracy was also confirmed by the elliptical joint confidence region (EJCR) test. The results show the high usefulness of ANNs in predictive modeling of phytosterol degradation in rapeseeds. The elaborated MLP-ANN model may be used as a support tool in modern postharvest management systems. |
| first_indexed | 2024-03-09T04:22:18Z |
| format | Article |
| id | doaj.art-bf5f0660840d4596b831ad069401a81b |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-03-09T04:22:18Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-bf5f0660840d4596b831ad069401a81b2023-12-03T13:46:13ZengMDPI AGMolecules1420-30492022-04-01278244510.3390/molecules27082445Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface RegressionJolanta Wawrzyniak0Magdalena Rudzińska1Marzena Gawrysiak-Witulska2Krzysztof Przybył3Faculty of Food Science and Nutrition, Poznań University of Life Sciences, 60-624 Poznań, PolandFaculty of Food Science and Nutrition, Poznań University of Life Sciences, 60-624 Poznań, PolandFaculty of Food Science and Nutrition, Poznań University of Life Sciences, 60-624 Poznań, PolandFaculty of Food Science and Nutrition, Poznań University of Life Sciences, 60-624 Poznań, PolandThe need to maintain the highest possible levels of bioactive components contained in raw materials requires the elaboration of tools supporting their processing operations, starting from the first stages of the food production chain. In this study, artificial neural networks (ANNs) and response surface regression (RSR) were used to develop models of phytosterol degradation in bulks of rapeseed stored under various temperatures and water activity conditions (<i>T</i> = 12–30 °C and <i>a<sub>w</sub></i> = 0.75–0.90). Among ANNs, networks based on a multilayer perceptron (MLP) and a radial basis function (RBF) were tested. The model input constituted <i>a<sub>w</sub></i>, temperature and storage time, whilst the model output was the phytosterol level in seeds. The ANN-based modeling turned out to be more effective in estimating phytosterol levels than the RSR, while MLP-ANNs proved to be more satisfactory than RBF-ANNs. The approximation quality of the ANNs models depended on the number of neurons and the type of activation functions in the hidden layer. The best model was provided by the MLP-ANN containing nine neurons in the hidden layer equipped with the logistic activation function. The model performance evaluation showed its high prediction accuracy and generalization capability (<i>R</i><sup>2</sup> = 0.978; <i>RMSE</i> = 0.140). Its accuracy was also confirmed by the elliptical joint confidence region (EJCR) test. The results show the high usefulness of ANNs in predictive modeling of phytosterol degradation in rapeseeds. The elaborated MLP-ANN model may be used as a support tool in modern postharvest management systems.https://www.mdpi.com/1420-3049/27/8/2445phytosterol degradationrapeseed storageartificial neural networksresponse surface regressionpredictive modelingpostharvest preservation systems |
| spellingShingle | Jolanta Wawrzyniak Magdalena Rudzińska Marzena Gawrysiak-Witulska Krzysztof Przybył Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression Molecules phytosterol degradation rapeseed storage artificial neural networks response surface regression predictive modeling postharvest preservation systems |
| title | Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression |
| title_full | Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression |
| title_fullStr | Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression |
| title_full_unstemmed | Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression |
| title_short | Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression |
| title_sort | predictive models of phytosterol degradation in rapeseeds stored in bulk based on artificial neural networks and response surface regression |
| topic | phytosterol degradation rapeseed storage artificial neural networks response surface regression predictive modeling postharvest preservation systems |
| url | https://www.mdpi.com/1420-3049/27/8/2445 |
| work_keys_str_mv | AT jolantawawrzyniak predictivemodelsofphytosteroldegradationinrapeseedsstoredinbulkbasedonartificialneuralnetworksandresponsesurfaceregression AT magdalenarudzinska predictivemodelsofphytosteroldegradationinrapeseedsstoredinbulkbasedonartificialneuralnetworksandresponsesurfaceregression AT marzenagawrysiakwitulska predictivemodelsofphytosteroldegradationinrapeseedsstoredinbulkbasedonartificialneuralnetworksandresponsesurfaceregression AT krzysztofprzybył predictivemodelsofphytosteroldegradationinrapeseedsstoredinbulkbasedonartificialneuralnetworksandresponsesurfaceregression |