Studies comparing the effectiveness of models for drying bitter gourd slices

Drying is an essential food preservation method, improving product shelf life and quality while reducing transportation and storage costs. This study evaluated the drying kinetics of bitter gourd slices under halogen drying conditions using both traditional empirical models (Page, Midilli, Logarithm...

Full description

Saved in:
Bibliographic Details
Main Authors: Dinh Anh Tuan Tran, Tuan Nguyen Van, Thi Khanh Phuong Ho
Format: Article
Language:English
Published: Czech Academy of Agricultural Sciences 2025-06-01
Series:Czech Journal of Food Sciences
Subjects:
Online Access:https://cjfs.agriculturejournals.cz/artkey/cjf-202503-0004_studies-comparing-the-effectiveness-of-models-for-drying-bitter-gourd-slices.php
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418179984490496
author Dinh Anh Tuan Tran
Tuan Nguyen Van
Thi Khanh Phuong Ho
author_facet Dinh Anh Tuan Tran
Tuan Nguyen Van
Thi Khanh Phuong Ho
author_sort Dinh Anh Tuan Tran
collection DOAJ
description Drying is an essential food preservation method, improving product shelf life and quality while reducing transportation and storage costs. This study evaluated the drying kinetics of bitter gourd slices under halogen drying conditions using both traditional empirical models (Page, Midilli, Logarithmic, Peleg, and Two-Term) and the machine learning-based random forest (RF) model. Experiments were conducted at 60 °C, 65 °C, and 70 °C with slice thicknesses of 3, 5, and 7 mm. Model performance was assessed using the coefficient of determination (R<sup>2</sup>), root mean square error (RMSE) and mean absolute percentage error (MAPE). The results show that the RF model demonstrated the highest accuracy, with an average R2 of 0.9826, the lowest RMSE (0.0655), and MAPE (1.40 %). Its ability to capture non-linear drying behaviour made it the most reliable model. The Midilli model was the best-performing traditional model, with an average R2 of 0.9851, but its accuracy declined for thicker slices and higher temperatures. Logarithmic and Peleg models exhibited significant errors, particularly during the mid-to-late drying phases. The results highlight RF's robustness and adaptability, outperforming traditional models in handling complex drying dynamics.
format Article
id doaj-art-2c25d7252058464aba1efafedc6d59ff
institution Kabale University
issn 1212-1800
1805-9317
language English
publishDate 2025-06-01
publisher Czech Academy of Agricultural Sciences
record_format Article
series Czech Journal of Food Sciences
spelling doaj-art-2c25d7252058464aba1efafedc6d59ff2025-08-20T03:32:31ZengCzech Academy of Agricultural SciencesCzech Journal of Food Sciences1212-18001805-93172025-06-0143320521510.17221/255/2024-CJFScjf-202503-0004Studies comparing the effectiveness of models for drying bitter gourd slicesDinh Anh Tuan Tran0https://orcid.org/0000-0002-7860-845XTuan Nguyen Van1Thi Khanh Phuong Ho2Faculty of Heat and Refrigeration engineering, Industrial University of Ho Chi Minh City, Ho Chi Minh City, VietnamFaculty of Heat and Refrigeration engineering, Industrial University of Ho Chi Minh City, Ho Chi Minh City, VietnamFaculty of Heat and Refrigeration engineering, Industrial University of Ho Chi Minh City, Ho Chi Minh City, VietnamDrying is an essential food preservation method, improving product shelf life and quality while reducing transportation and storage costs. This study evaluated the drying kinetics of bitter gourd slices under halogen drying conditions using both traditional empirical models (Page, Midilli, Logarithmic, Peleg, and Two-Term) and the machine learning-based random forest (RF) model. Experiments were conducted at 60 °C, 65 °C, and 70 °C with slice thicknesses of 3, 5, and 7 mm. Model performance was assessed using the coefficient of determination (R<sup>2</sup>), root mean square error (RMSE) and mean absolute percentage error (MAPE). The results show that the RF model demonstrated the highest accuracy, with an average R2 of 0.9826, the lowest RMSE (0.0655), and MAPE (1.40 %). Its ability to capture non-linear drying behaviour made it the most reliable model. The Midilli model was the best-performing traditional model, with an average R2 of 0.9851, but its accuracy declined for thicker slices and higher temperatures. Logarithmic and Peleg models exhibited significant errors, particularly during the mid-to-late drying phases. The results highlight RF's robustness and adaptability, outperforming traditional models in handling complex drying dynamics.https://cjfs.agriculturejournals.cz/artkey/cjf-202503-0004_studies-comparing-the-effectiveness-of-models-for-drying-bitter-gourd-slices.phprandom forest modelmomordica charantialtraditional drying modelhalogen dryermoisture content
spellingShingle Dinh Anh Tuan Tran
Tuan Nguyen Van
Thi Khanh Phuong Ho
Studies comparing the effectiveness of models for drying bitter gourd slices
Czech Journal of Food Sciences
random forest model
momordica charantial
traditional drying model
halogen dryer
moisture content
title Studies comparing the effectiveness of models for drying bitter gourd slices
title_full Studies comparing the effectiveness of models for drying bitter gourd slices
title_fullStr Studies comparing the effectiveness of models for drying bitter gourd slices
title_full_unstemmed Studies comparing the effectiveness of models for drying bitter gourd slices
title_short Studies comparing the effectiveness of models for drying bitter gourd slices
title_sort studies comparing the effectiveness of models for drying bitter gourd slices
topic random forest model
momordica charantial
traditional drying model
halogen dryer
moisture content
url https://cjfs.agriculturejournals.cz/artkey/cjf-202503-0004_studies-comparing-the-effectiveness-of-models-for-drying-bitter-gourd-slices.php
work_keys_str_mv AT dinhanhtuantran studiescomparingtheeffectivenessofmodelsfordryingbittergourdslices
AT tuannguyenvan studiescomparingtheeffectivenessofmodelsfordryingbittergourdslices
AT thikhanhphuongho studiescomparingtheeffectivenessofmodelsfordryingbittergourdslices