Artificial neural network and multiple linear regression modelling for prediction of moisture content of red beetroots during ultrasound assisted vacuum drying

Yıl 2025, Cilt: 40 Sayı: 2, 430 - 444, 30.12.2025

Nuray İnan Çınkır

Öz

The present work aimed to evaluate the possibility of artificial neural networks (ANN) and multiple linear regression (MLR) to characterize the drying kinetics of red beetroot slices during ultrasound assisted vacuum drying. The ANN model was chosen due to impact of the hidden layer's neuron number and size. The best ANN model was obtained by three layers (5 inputs, 15 neurons in one hidden layer and 1 output) with RMSE of 0.0117, MAPE of 2.293 and R2 of 0.9996 for all data. The results showed that the ANN is a more effective predictive tool since it can yield better outcomes than MLR.

Anahtar Kelimeler

drying , modelling , red beetroots; ultrasound , artificial neural networks , multi linear regression

Proje Numarası

OKÜBAP-2024-PT1-003

Ultrases destekli vakumlu kurutma sırasında kırmızı pancarların nem oranının tahmini için yapay sinir ağı ve çoklu doğrusal regresyon modellemesi

Öz

Bu çalışma, yapay sinir ağları (ANN) ve çoklu doğrusal regresyon (MLR) yöntemlerinin, ultrason destekli vakumlu kurutma sırasında kırmızı pancar dilimlerinin kuruma kinetiğini karakterize etme olasılığını değerlendirmeyi amaçlamaktadır. YSA modeli, gizli katmanın nöron sayısı ve boyutunun etkisi göz önünde bulundurularak seçilmiştir. En iyi YSA modeli, tüm veriler için RMSE değeri 0,0117, MAPE değeri 2,293 ve R2 değeri 0,9996 olan üç katmandan (5 giriş, bir gizli katmanda 15 nöron ve 1 çıkış) elde edilmiştir. Sonuçlar, YSA'nın MLR’ den daha iyi sonuçlar verebildiği için daha etkili bir tahminleme aracı olduğunu göstermiştir.

Anahtar Kelimeler

kurutma , modelleme , kırmızı pancar; ultrases , yapay sinir ağları , çoklu doğrusal regresyon

Proje Numarası

OKÜBAP-2024-PT1-003

Kaynakça

• Akyıldız, A., Şimşek Mertoğlu, T., İnan Çınkır, N., Ağçam, E. (2025). Modeling quality changes in heat-processed orange juice: a comparative study of artificial neural network and multiple linear regression approaches. Harran Tarım ve Gıda Bilimleri Derg, 29(2): 237–254.
• Batista, L. F., Marques, C. S., Pires, A. C. dos S., Minim, L. A., Soares, N. de F. F., Vidigal, M. C. T. R. (2021). Artificial neural networks modeling of non-fat yogurt texture properties: effect of process conditions and food composition. Food Bioprod. Process, 126: 164–174.
• Behroozi Khazaei, N., Tavakoli, T., Ghassemian, H., Khoshtaghaza, M. H., Banakar, A. (2013). Applied machine vision and artificial neural network for modeling and controlling of the grape drying process. Comput Electron Agric, 98: 205–213.
• Bromberger Soquetta, M., Schmaltz, S., Wesz Righes, F., Salvalaggio, R., de Marsillac Terra, L. (2018). Effects of pretreatment ultrasound bath and ultrasonic probe, in osmotic dehydration, in the kinetics of oven drying and the physicochemical properties of beet snacks. J Food Process Preserv, 42(1): 1–9.
• Çınkır, N. İ., Süfer, Ö. (2020). Microwave drying of TURKISH red meat (watermelon) radish (RAPHANUS SATIVUS L.): effect of osmotic dehydration, pre-treatment and slice thickness. Heat and Mass Transfer, 56(12): 3303–3313.
• 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. J Food Process Eng, 46(2): 1–13.
• Deng, F., Lu, H., Yuan, Y., Chen, H., Li, Q., Wang, L., Tao, Y., Zhou, W., Cheng, H., Chen, Y., Lei, X., Li, G., Li, M., Ren, W. (2023). Accurate prediction of the eating and cooking quality of rice using artificial neural networks and the texture properties of cooked rice. Food Chem, 407: 135176.
• Ding, B., Li, L., Yang, H. (2017). An artificial neural network approach to estimating the enzymatic hydrolysis of Chinese yam (Dioscorea opposita Thunb.) starch. J Food Process Preserv, e13176.
• Erzin, Y., Cetin, T. (2012). The use of neural networks for the prediction of the critical factor of safety of an artificial slope subjected to earthquake forces. Sci Iran, 19(2): 188–194.
• Ghani, I. M. M., Ahmad, S. (2010). Stepwise multiple regression method to forecast fish landing. Procedia Soc Behav Sci, 8(5): 549–554.
• Guin´e, R. P. F., Barroca, M. J., Gonçalves, F. J., Alves, M., Oliveira, S., Mendes, M. (2015). Artificial neural network modelling of the antioxidant activity and phenolic compounds of bananas submitted to different drying treatments. Food Chem, 168: 454–459.
• Fijalkowska, A., Nowacka, M., Wiktor, A., Sledz, M., Witrowa-Rajchert, D. (2016). Ultrasound as a pretreatment method to improve drying kinetics and sensory properties of dried apple. J Food Process Eng, 39(3): 256–265.
• İnan-Çınkır, N., Süfer, Ö., Pandiselvam, R. (2024). Kinetic and artificial neural network modeling of dried black beauty eggplant (Solanum melongena L.) slices during rehydration. J Food Process Eng, 47(3): 1–12.
• Jiang, C., Wan, F., Zang, Zhang, Q., Ma, G., Huang, X. (2022). Effect of an ultrasound pre-treatment on the characteristics and quality of far-infrared vacuum drying with Cistanche slices. Foods, 11(6).
• Kaveh, M., Chayjan, R. A. (2015). Mathematical and neural network modelling of terebinth fruit under fluidized bed drying. Res. Agric. Eng., 61(2): 55–65.
• Li, S., Hu, Y., Hong, Y., Xu, L., Zhou, M., Fu, C., Li, D. (2016). Analysis of the hydrolytic capacities of Aspergillus oryzae proteases on soybean protein using artificial neural networks. J Food Process Preserv, 40(5): 918–924.
• Li, M., Wang, B., Lv, W., Zhao, D. (2022). Effect of ultrasound pretreatment on the drying kinetics and characteristics of pregelatinized kidney beans based on microwave-assisted drying. Food Chem, 397: 133806.
• Liu, Y., Helikh, A. O., Filon, A. M., Tang, X. X., Duan, Z. H., Ren, A. Q. (2024). Beetroot (Beta vulgaris L. var. conditiva Alef.) pretreated by freeze-thaw: influence of drying methods on the quality characteristics. CYTA J Food, 22(1): 1–12.
• Malakar, S., Alam, M., Arora, V. K. (2022). Evacuated tube solar and sun drying of beetroot slices: comparative assessment of thermal performance, drying kinetics, and quality analysis. Sol Energy, 233: 246–258.
• Matworks, 2025. Improve Shallow Neural Network Generalization and Avoid Overfitting. Retrieved on December 21, 2025 from: https://www.mathworks.com/help/deeplearning/ug/improve-neural-network-generalization-and-avoid-overfitting.html
• Meerasri, J., Sothornvit, R. (2022). Artificial neural networks (ANNs) and multiple linear regression (MLR) for prediction of moisture content for coated pineapple cubes. Case Stud Therm Eng, 33: 101942.
• Mihaly Cozmuta, L. (2025). The application of multiple linear regression methods to FTIR spectra of fingernails for predicting gender and age of human subjects. Heliyon, 11(4): e42815.
• Mothibe, K. J., Zhang, M., Nsoratindana, J., Wang, Y. (2011). Use of ultrasound pretreatment in drying of fruits: drying rates, quality attributes, and shelf life extension. Dry Technol, 29(14): 1611–1621.
• Nejatdarabi, S., Mohebbi, M. (2023). Predicting the rehydration process of mushroom powder by multiple linear regression (MLR) and artificial neural network (ANN) in different rehydration medium. J Food Meas Charact, 17(2): 1962–1973.
• Özkan-Karabacak, A., Acoğlu, B., Yolci Ömeroğlu, P., Çopur, Ö. U. (2020). Microwave pre-treatment for vacuum drying of orange slices: drying characteristics, rehydration capacity and quality properties. J Food Process Eng, 43(11): 1–15.
• Preethi, R., Deotale, S. M., Moses, J. A., Anandharamakrishnan, C. (2020). Conductive hydro drying of beetroot (Beta vulgaris L.) pulp: insights for natural food colorant applications. J Food Process Eng, 43(12).
• Sampaio, P. S., Almeida, A. S., Brites, C. M. (2021). Use of artificial neural network model for rice quality prediction based on grain physical parameters. Foods, 10(12).
• Selvi, K. Ç., Alkhaled, A. Y., Yıldız, T. (2022). Application of artificial neural network for predicting the drying kinetics and chemical attributes of linden (Tilia platyphyllos Scop.) during the infrared drying process. Processes, 10(10).
• Sun, M., Xu, Y., Ding, Y., Gu, Y., Zhuang, Y., Fan, X. (2023). Effect of ultrasound pretreatment on the moisture migration and quality of Cantharellus cibarius following hot air drying. Foods, 12(14).
• Tekin Cakmak, Z. H., Kayacan Cakmakoglu, S., Avcı, E., Sagdic, O., Karasu, S. (2021). Ultrasound-assisted vacuum drying as alternative drying method to increase drying rate and bioactive compounds retention of raspberry. J Food Process Preserv, 45(12): 1–11.
• Torkashvand, A. M., Ahmadi, A., Nikravesh, N. L. (2017). Prediction of kiwifruit firmness using fruit mineral nutrient concentration by artificial neural network (ANN) and multiple linear regressions (MLR). J Integr Agric, 16(7): 1634–1644.
• Wang, H., Che, G., Wan, L., Wang, X., Tang, H. (2022). Combination of LF-NMR and BP-ANN to monitor the moisture content of rice during hot-air drying. J Food Process Eng, 45(9): 1–12.
• Xing, S., Lin, Z., Gao, X., Wang, D., Liu, G., Cao, Y., Liu, Y. (2024). Research on outgoing moisture content prediction models of corn drying process based on sensitive variables. Appl Sci (Basel), 14(13).
• Yadav, A. K., Chandel, S. S. (2017). Identification of relevant input variables for prediction of 1-minute time-step photovoltaic module power using artificial neural network and multiple linear regression models. Renew Sust Energ, 77: 955–969.
• Yamchi, A. A., Hosainpour, A., Hassanpour, A., Fanaei, A. R. (2024). Drying kinetics and thermodynamic properties of ultrasound pretreatment bitter melon dried by infrared. J Food Process Preserv, 2024: Article ID 1987547.
• Yang, T., Zheng, X., Vidyarthi, S. K., Xiao, H., Yao, X., Li, Zang, Y., Zhang, J. (2023). Artificial neural network modeling and genetic algorithm multiobjective optimization of process of drying-assisted walnut breaking. Foods, 12(9): 1–21.
• Yu, P., Low, M. Y., Zhou, W. (2018). Design of experiments and regression modelling in food flavour and sensory analysis: a review. Trends Food Sci Technol, 71: 202–215.
• Zhang, L., Liao, L., Qiao, Y., Wang, C., Shi, D., An, K., Hu, J. (2020). Effects of ultrahigh pressure and ultrasound pretreatments on properties of strawberry chips prepared by vacuum-freeze drying. Food Chem, 303: 125386.