Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes
Апстракт
This study aimed to investigate the drying kinetics of capers at different temperatures and to examine the morphological changes of capers during the drying and rehydration processes. Computer-aided image processing and Artificial Neural Network models (ANN) were used to analyze the shrinkage and moisture ratio of capers (drying) and the expansion of capers (rehydration). Lewis, Page, Fick's law, and logarithmic models were investigated to describe the conventional drying kinetics of capers at 50, 60, and 70 degrees C; the logarithmic model was shown to be the best describing model (r(2): 0.9996, 0.9996 and 0.9981, respectively). Effective diffusivities varied between 1.91 x 10(-10) and 2.62 x 10(-10) m(2)/s for the temperature range. The activation energy was 14.572 kJ/mol. Image processing revealed that diameter reduction rates were 1 x 10(-4) mm/s for 50 and 70 & DEG;C and 7 x 10(-5) mm/s for 60 degrees C. ANN was applied using multilayer perceptron models with three layers (input: ...ANN1, hidden: ANN2, and output: ANN3) which were sufficiently valid for predicting the experimental parameters (r(2): 0.9992, 0.9915, and 0.8484, respectively). All morphological properties were reduced with drying, and shrinkage of capers was increased proportionally with the moisture content. The Global Sensitivity Analysis recognized treatment time as the most influential parameter affecting the moisture ratio and the caper diameter changes. Practical applications One of the major problems for humans has been to improve food preservation techniques for long-term storage. The major scope of industry is the drying of fruits and/or vegetables to produce dried foods with high quality and a long shelf life. To the best of our knowledge, drying of capers regarding the drying kinetics, modeling and quality changes has not been published to date. In this study, goal was to better understand drying kinetics and geometric changes that occur to capers during the dehydration and rehydration processes at various drying temperatures. Quantitative information regarding geometrical changes to capers was supplied by the image processing of the acquired pictures, which enabled rapid monitoring of physical changes during dehydration and rehydration. The remarked kinetic model, ANN model, and Quantitative information regarding geometrical changes are valuable information for researchers studying on drying of food and large-scale dryer designers.
Кључне речи:
shrinkage rate / moisture ratio / image processing / drying of capers / artificial neural networkИзвор:
Journal of Food Process Engineering, 2023, 46, 2Финансирање / пројекти:
- OKUBAP (Scientific Research Projects Unit of Osmaniye Korkut Ata University) [OKUBAP-2021-PT3-016]
DOI: 10.1111/jfpe.14249
ISSN: 0145-8876
WoS: 000903357000001
Scopus: 2-s2.0-85145048588
Институција/група
Institut za opštu i fizičku hemijuTY - JOUR AU - Demir, Hasan AU - Demir, Hande AU - Lončar, Biljana AU - Nićetin, Milica AU - Pezo, Lato AU - Yilmaz, Fatma PY - 2023 UR - https://riofh.iofh.bg.ac.rs/handle/123456789/968 AB - This study aimed to investigate the drying kinetics of capers at different temperatures and to examine the morphological changes of capers during the drying and rehydration processes. Computer-aided image processing and Artificial Neural Network models (ANN) were used to analyze the shrinkage and moisture ratio of capers (drying) and the expansion of capers (rehydration). Lewis, Page, Fick's law, and logarithmic models were investigated to describe the conventional drying kinetics of capers at 50, 60, and 70 degrees C; the logarithmic model was shown to be the best describing model (r(2): 0.9996, 0.9996 and 0.9981, respectively). Effective diffusivities varied between 1.91 x 10(-10) and 2.62 x 10(-10) m(2)/s for the temperature range. The activation energy was 14.572 kJ/mol. Image processing revealed that diameter reduction rates were 1 x 10(-4) mm/s for 50 and 70 & DEG;C and 7 x 10(-5) mm/s for 60 degrees C. ANN was applied using multilayer perceptron models with three layers (input: ANN1, hidden: ANN2, and output: ANN3) which were sufficiently valid for predicting the experimental parameters (r(2): 0.9992, 0.9915, and 0.8484, respectively). All morphological properties were reduced with drying, and shrinkage of capers was increased proportionally with the moisture content. The Global Sensitivity Analysis recognized treatment time as the most influential parameter affecting the moisture ratio and the caper diameter changes. Practical applications One of the major problems for humans has been to improve food preservation techniques for long-term storage. The major scope of industry is the drying of fruits and/or vegetables to produce dried foods with high quality and a long shelf life. To the best of our knowledge, drying of capers regarding the drying kinetics, modeling and quality changes has not been published to date. In this study, goal was to better understand drying kinetics and geometric changes that occur to capers during the dehydration and rehydration processes at various drying temperatures. Quantitative information regarding geometrical changes to capers was supplied by the image processing of the acquired pictures, which enabled rapid monitoring of physical changes during dehydration and rehydration. The remarked kinetic model, ANN model, and Quantitative information regarding geometrical changes are valuable information for researchers studying on drying of food and large-scale dryer designers. T2 - Journal of Food Process Engineering T1 - Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes IS - 2 VL - 46 DO - 10.1111/jfpe.14249 UR - conv_1068 ER -
@article{ author = "Demir, Hasan and Demir, Hande and Lončar, Biljana and Nićetin, Milica and Pezo, Lato and Yilmaz, Fatma", year = "2023", abstract = "This study aimed to investigate the drying kinetics of capers at different temperatures and to examine the morphological changes of capers during the drying and rehydration processes. Computer-aided image processing and Artificial Neural Network models (ANN) were used to analyze the shrinkage and moisture ratio of capers (drying) and the expansion of capers (rehydration). Lewis, Page, Fick's law, and logarithmic models were investigated to describe the conventional drying kinetics of capers at 50, 60, and 70 degrees C; the logarithmic model was shown to be the best describing model (r(2): 0.9996, 0.9996 and 0.9981, respectively). Effective diffusivities varied between 1.91 x 10(-10) and 2.62 x 10(-10) m(2)/s for the temperature range. The activation energy was 14.572 kJ/mol. Image processing revealed that diameter reduction rates were 1 x 10(-4) mm/s for 50 and 70 & DEG;C and 7 x 10(-5) mm/s for 60 degrees C. ANN was applied using multilayer perceptron models with three layers (input: ANN1, hidden: ANN2, and output: ANN3) which were sufficiently valid for predicting the experimental parameters (r(2): 0.9992, 0.9915, and 0.8484, respectively). All morphological properties were reduced with drying, and shrinkage of capers was increased proportionally with the moisture content. The Global Sensitivity Analysis recognized treatment time as the most influential parameter affecting the moisture ratio and the caper diameter changes. Practical applications One of the major problems for humans has been to improve food preservation techniques for long-term storage. The major scope of industry is the drying of fruits and/or vegetables to produce dried foods with high quality and a long shelf life. To the best of our knowledge, drying of capers regarding the drying kinetics, modeling and quality changes has not been published to date. In this study, goal was to better understand drying kinetics and geometric changes that occur to capers during the dehydration and rehydration processes at various drying temperatures. Quantitative information regarding geometrical changes to capers was supplied by the image processing of the acquired pictures, which enabled rapid monitoring of physical changes during dehydration and rehydration. The remarked kinetic model, ANN model, and Quantitative information regarding geometrical changes are valuable information for researchers studying on drying of food and large-scale dryer designers.", journal = "Journal of Food Process Engineering", title = "Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes", number = "2", volume = "46", doi = "10.1111/jfpe.14249", url = "conv_1068" }
Demir, H., Demir, H., Lončar, B., Nićetin, M., Pezo, L.,& Yilmaz, F.. (2023). Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes. in Journal of Food Process Engineering, 46(2). https://doi.org/10.1111/jfpe.14249 conv_1068
Demir H, Demir H, Lončar B, Nićetin M, Pezo L, Yilmaz F. Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes. in Journal of Food Process Engineering. 2023;46(2). doi:10.1111/jfpe.14249 conv_1068 .
Demir, Hasan, Demir, Hande, Lončar, Biljana, Nićetin, Milica, Pezo, Lato, Yilmaz, Fatma, "Artificial neural network and kinetic modeling of capers during dehydration and rehydration processes" in Journal of Food Process Engineering, 46, no. 2 (2023), https://doi.org/10.1111/jfpe.14249 ., conv_1068 .