PREDICTION OF VACUUM DRYING KINETICS OF FINGERROOT USING ARTIFICIAL NEURAL NETWORK MODELS
Keywords:
Fingerroot, Vacuum Drying, Artificial Neural Network, Drying RateAbstract
Drying is a crucial post-harvest process that significantly affects the quality, safety, and shelf-life of herbal materials. This study aimed to develop an Artificial Neural Network (ANN) model to predict the drying behavior of fingerroot (Boesenbergia rotunda) under vacuum conditions. Drying experiments were conducted at three absolute pressures (5, 10, and 15 kPa) and three sample thicknesses (3, 5, and 7 mm), with key response variables including moisture content (MC), moisture ratio (MR), and drying rate (DR). The results indicated that drying at a low pressure of 5 kPa enhanced moisture removal efficiency, resulting in the shortest drying time, whereas higher pressures slowed down the drying process. The developed ANN model consisted of two hidden layers and incorporated early stopping and learning rate reduction mechanisms to optimize training performance. Model evaluation showed excellent agreement with experimental data, with R2 values exceeding 0.98, RMSE below 0.03, and MAPE ranging from 3.8% to 10.9%, demonstrating the reliability and predictive capability of the developed ANN model for vacuum drying behavior prediction. This study highlights the potential of ANN for improving efficiency and controlling vacuum drying processes of herbal materials, contributing to industrial-scale dryer design, energy savings, and preservation of bioactive compounds in medicinal herbs.
References
Chen, Z., & Lamb, F. M. (2007). Analysis of the vacuum drying rate for red oak in a hot water vacuum drying system. Drying Technology, 25(3), 497–500. https://doi.org/10.1080/07373930601184064
Ilman Fahrudin, F., Sulaiman, R., Rukayadi, Y., & Sukaryadi, Y. (2020). Effect of Drying Methods on Physicochemical Characteristics of Boesenbergia Rotunda (L.) Mansf. Powder Article in. International Journal of Advanced Science and Technology, 29(6), 3952–3962. Retrieved from https://www.researchgate.net/publication/370927914
Kaveh, M., Çetin, N., Khalife, E., Abbaspour-Gilandeh, Y., Sabouri, M., & Sharifian, F. (2023). Machine learning approaches for estimating apricot drying characteristics in various advanced and conventional dryers. Journal of Food Process Engineering, 46(12). https://doi.org/10.1111/jfpe.14475
Khan, M. I. H., Sablani, S. S., Joardder, M. U. H., & Karim, M. A. (2022). Application of machine learning-based approach in food drying: opportunities and challenges. Drying Technology, 40(6), 1051–1067. https://doi.org/10.1080/07373937.2020.1853152
Li, Y., Wang, X., Wu, Z., Wan, N., & Yang, M. (2020). Dehydration of hawthorn fruit juices using ultrasound-assisted vacuum drying. Ultrasonics Sonochemistry, 68. https://doi.org/10.1016/j.ultsonch.2020.105219
Martynenko, A., & Misra, N. N. (2020). Machine learning in drying. Drying Technology, 38(5–6), 596–609. https://doi.org/10.1080/07373937.2019.1690502
Menlik, T., Özdemir, M. B., & Kirmaci, V. (2010). Determination of freeze-drying behaviors of apples by artificial neural network. Expert Systems with Applications, 37(12), 7669–7677. https://doi.org/ 10.1016/ j.eswa. 2010.04.075
Phahom, T., & Mano, J. (2023). Integration of multiple linear regression, principal component analysis, and hierarchical cluster analysis for optimizing dried fingerroot (Boesenbergia rotunda) extraction process. Journal of Applied Research on Medicinal and Aromatic Plants, 36. https://doi.org/10.1016/j.jarmap.2023.100511
Seremet, L., Botez, E., Nistor, O. V., Andronoiu, D. G., & Mocanu, G. D. (2016). Effect of different drying methods on moisture ratio and rehydration of pumpkin slices. Food Chemistry, 195, 104–109. https://doi.org/10.1016/j.foodchem.2015.03.125
Shindo, K., Kato, M., Kinoshita, A., Kobayashi, A., & Koike, Y. (2006). Analysis of antioxidant activities contained in the Boesenbergia pandurata Schult. rhizome. Bioscience, Biotechnology and Biochemistry, 70(9), 2281–2284. https://doi.org/10.1271/bbb.60086
Taghinezhad, E., Szumny, A., Kaveh, M., Sharabiani, V. R., Kumar, A., & Shimizu, N. (2020). Parboiled paddy drying with different dryers: Thermodynamic and quality properties, mathematical modeling using ANNs assessment. Foods, 9(1). https://doi.org/10.3390/foods9010086
Techapichetvanich, P., Tangpanithandee, S., Supannapan, K., Wongwiwatthananukit, S., Chang, L. C., & Khemawoot, P. (2024). Oral sub-chronic toxicity of fingerroot (Boesenbergia rotunda) rhizome extract formulation in Wistar rats. Toxicology Reports, 12, 224–233. https://doi.org/10.1016/j.toxrep.2024.01.013
Therdthai, N., & Northongkom, H. (2011). Characterization of hot air drying and microwave vacuum drying of fingerroot (Boesenbergia pandurata). International Journal of Food Science and Technology, 46(3), 601–607. https://doi.org/10.1111/j.1365-2621.2010.02525.x
Topal, M. E., Şahin, B., & Vela, S. (2024). Artificial Neural Network Modeling Techniques for Drying Kinetics of Citrus medica Fruit during the Freeze-Drying Process. Processes, 12(7). https://doi.org/10.3390/pr12071362
Trakoontivakorn, G., Nakahara, K., Shinmoto, H., Takenaka, M., Onishi-Kameyama, M., Ono, H., Tsushida, T. (2001). Structural analysis of a novel antimutagenic compound, 4-hydroxypanduratin A, and the antimutagenic activity of flavonoids in a Thai spice, fingerroot (Boesenbergia pandurata Schult.) against mutagenic heterocyclic amines. Journal of Agricultural and Food Chemistry, 49(6), 3046–3050. https://doi.org/10.1021/jf010016o
Zielinska, M., Ropelewska, E., Xiao, H. W., Mujumdar, A. S., & Law, C. L. (2020). Review of recent applications and research progress in hybrid and combined microwave-assisted drying of food products: Quality properties. Critical Reviews in Food Science and Nutrition, 60, 2212–2264. Taylor and Francis Inc. https://doi.org/10.1080/10408398.2019.1632788
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 ภาณุศักดิ์ มูลศรี, สัญชัย รำเพยพัด, อภิเดช บุญเจือ, อำพล พิชัยเชิด, วิชชุพงษ์ วิบูลเจริญ, ศรันย์ คัมภีร์ภัทร, ไมตรี ธรรมมา, วริศราภรณ์ จรโคกกรวด
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
