Comparative Machine Learning Modeling of Infrared Drying Kinetics in Cactus Fruit (Opuntia ficus-indica) Slices

Öz

The objective of this study was to model the infrared drying kinetics of cactus fruit (Opuntia ficus-indica) slices using advanced machine learning (ML) approaches. Drying experiments were conducted at a constant temperature of 70 °C using slice thicknesses of 2, 5, and 8 mm. Approximately 200 experimental data points describing the temporal evolution of moisture ratio (MR) were obtained. In previous analyses, the Midilli–Küçük model was identified as the most suitable semi-empirical thin-layer model for this dataset. In the present study, the same experimental data were re-evaluated using nonlinear ML algorithms to further improve predictive accuracy. Support vector machines (SVM), artificial neural networks (ANN), random forest (RF), and linear regression (LR) were employed. Drying time and slice thickness were used as input variables, while moisture ratio was defined as the output variable. Model performance was evaluated using a rigorous 10-fold cross-validation procedure. The results indicated that the SVM model achieved the highest prediction accuracy, with a coefficient of determination of R² ≈ 0.9998 and a root mean square error of approximately 0.005, followed closely by the ANN model (R² ≈ 0.9990). In contrast, the linear regression model failed to adequately capture the nonlinear characteristics of the drying process. Overall, the findings demonstrate that SVM and ANN provide robust and accurate alternatives to conventional empirical thin-layer models for predicting infrared drying kinetics of cactus fruit.

Anahtar Kelimeler

• Artificial neural networks
• infrared drying
• machine learning
• moisture ratio
• Opuntia ficus-indica
• support vector machines

Destekleyen Kurum

TÜBİTAK (The Scientific and Technological Research Council of Türkiye) - Note: This support is specifically for training purposes under the 2237-A program, not direct research funding.

Proje Numarası

1129B372300736

Etik Beyan

This article does not contain any studies with human participants or animals performed by the author. Furthermore, the author declares that AI-assisted technologies (e.g., ChatGPT) were utilized exclusively for the purpose of English language editing, grammar correction, and improving the readability of the manuscript. The experimental design, data analysis, and scientific conclusions are entirely the original work of the author.

Teşekkür

The author would like to thank the coordinators of the project supported by the Scientific and Technological Research Council of Türkiye (TÜBİTAK 2237-A, "Process Analysis and Optimization"; Project Number: 1129B372300736), which facilitated the learning of the software programs used in this study.

Kaktüs Meyvesi (Opuntia ficus-indica) Dilimlerinin Kızılötesi Kurutma Kinetiğinin Karşılaştırmalı Makine Öğrenmesi ile Modellenmesi

Öz

Bu çalışmanın amacı, kaktüs meyvesi (Opuntia ficus-indica) dilimlerinin kızılötesi kurutma kinetiğini ileri makine öğrenmesi (ML) yaklaşımları kullanarak modellemektir. Kurutma deneyleri 70 °C sabit sıcaklıkta ve 2, 5 ve 8 mm dilim kalınlıkları kullanılarak gerçekleştirilmiştir. Nem oranının (MR) zamana bağlı değişimini tanımlayan yaklaşık 200 deneysel veri noktası elde edilmiştir. Önceki analizlerde, bu veri seti için en uygun yarı ampirik ince tabaka modelinin Midilli-Küçük modeli olduğu belirlenmiştir. Bu çalışmada, tahmin doğruluğunu daha da artırmak amacıyla aynı deneysel veriler doğrusal olmayan makine öğrenmesi algoritmaları kullanılarak yeniden değerlendirilmiştir. Analizlerde destek vektör makineleri (SVM), yapay sinir ağları (YSA), rastgele orman (RF) ve doğrusal regresyon (LR) algoritmaları kullanılmıştır. Kurutma süresi ve dilim kalınlığı girdi değişkenleri, nem oranı ise çıktı değişkeni olarak tanımlanmıştır. Model performansı, titiz bir 10-katlı çapraz doğrulama prosedürü ile test edilmiştir. Sonuçlar, SVM modelinin R² ≈ 0.9998 belirtme katsayısı ve yaklaşık 0.005 kök ortalama kare hatası ile en yüksek tahmin doğruluğuna ulaştığını, bunu YSA modelinin (R² ≈ 0.9990) yakından takip ettiğini göstermiştir. Buna karşılık, doğrusal regresyon modeli kurutma işleminin doğrusal olmayan özelliklerini yeterince yakalayamamıştır. Genel olarak bulgular, kaktüs meyvesinin kızılötesi kurutma kinetiğinin tahmin edilmesinde SVM ve YSA'nın geleneksel ampirik ince tabaka modellerine güçlü ve doğru alternatifler sunduğunu göstermektedir.

Anahtar Kelimeler

• Yapay sinir ağları
• kızılötesi kurutma
• makine öğrenmesi
• nem oranı
• Opuntia ficus-indica
• destek vektör makineleri

Destekleyen Kurum

TÜBİTAK (Türkiye Bilimsel ve Teknolojik Araştırma Kurumu - 2237-A Programı)

Proje Numarası

1129B372300736

Etik Beyan

Bu makale, insan katılımcılar veya hayvanlar üzerinde gerçekleştirilen herhangi bir çalışma içermemektedir ve etik kurul izni gerektirmemektedir. Ayrıca yazar, yapay zeka destekli araçların (örn. ChatGPT) yalnızca makalenin İngilizce dil redaksiyonu, gramer düzeltmesi ve okunabilirliğini artırmak amacıyla kullanıldığını beyan eder. Çalışmanın deneysel kurgusu, veri analizi ve bilimsel çıkarımları tamamen yazarın kendi özgün çalışmasıdır.

Teşekkür

Bu çalışmada kullandığım programları öğrenmeme yardımcı olan Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (“TÜBİTAK 2237-A, Proses Analizi ve Optimizasyonu”; Proje Numarası: 1129B372300736) tarafından desteklenen projenin koordinatörlerine teşekkür ederim.

Kaynakça

1. Anumudu, C. K., Onyeaka, H., Ekwueme, C. T., Hart, A., Isaac-Bamgboye, F., & Miri, T. (2024). Advances in the Application of Infrared in Food Processing for Improved Food Quality and Microbial Inactivation. Foods, 13(24). https://doi.org/10.3390/foods13244001
2. Buzrul, S. (2022). Reassessment of Thin-Layer Drying Models for Foods: A Critical Short Communication. Processes, 10(1). https://doi.org/10.3390/pr10010118
3. Çetin, N. (2022). Prediction of moisture ratio and drying rate of orange slices using machine learning approaches. Journal of Food Processing and Preservation, 46(11), e17011. https://doi.org/10.1111/jfpp.17011
4. Ciriminna, R., Morreale, V., Pecoraino, M., & Pagliaro, M. (2019). Solar air drying for innovative Opuntia ficus-indica cladode dehydration. 4open, 2, 1. https://doi.org/10.1051/fopen/2019001
5. Cruz-Rubio, J. M., Mueller, M., Loeppert, R., Viernstein, H., & Praznik, W. (2020). The Effect of Cladode Drying Techniques on the Prebiotic Potential and Molecular Characteristics of the Mucilage Extracted from Opuntia ficus-indica and Opuntia joconostle. Scientia Pharmaceutica, 88(4), 43. https://doi.org/10.3390/scipharm88040043
6. Doymaz, İ. (2014). Thin-Layer Drying of Bay Laurel Leaves (Laurus nobilis L.). Journal of Food Processing and Preservation, 38(1), 449–456. https://doi.org/10.1111/j.1745-4549.2012.00793.x
7. El-Mesery, H. S., Ashiagbor, K., Hu, Z., & Rostom, M. (2024). Mathematical modeling of thin-layer drying kinetics and moisture diffusivity study of apple slices using infrared conveyor-belt dryer. Journal of Food Science, 89(3), 1658–1671. https://doi.org/10.1111/1750-3841.16967
8. El-Mesery, H. S., ElMesiry, A. H., Quaye, E. K., Hu, Z., & Salem, A. (2025). Machine learning algorithm for estimating and optimizing the phytochemical content and physicochemical properties of okra slices in an infrared heating system. Food Chemistry: X, 25, 102248. https://doi.org/10.1016/j.fochx.2025.102248

9. Eroğlu, S. (2024). Çekirdekli ve Çekirdeksiz Nar Tanelerinin Ultrason Ön İşlemli Kurutma Kinetiğinin En Çok İki Parametre İçeren İnce Tabaka Modelleri Kullanılarak İncelenmesi. Turkish Journal of Agriculture - Food Science and Technology, 12(7), 1129–1136. https://doi.org/10.24925/turjaf.v12i7.1129-1136.6805
10. Eroğlu, S., & Çevik, Ş. (2025). Drying Kinetics and Effective Moisture Diffusivity of Cactus Pear Slices at Different Thicknesses Using a Laboratory Scale Infrared Dryer. Proceedings of the 9th International Conference on Natural Science and Technology (ICONST 2025). 9th International Conference on Natural Science and Technology (ICONST 2025), Kotor, Montenegro.
11. Gouws, C. A., D’Cunha, N. M., Georgousopoulou, E. N., Mellor, D. D., & Naumovski, N. (2019). The effect of different drying techniques on phytochemical content and in vitro antioxidant properties of Australian‐grown prickly pears ( Opuntia ficus indica ). Journal of Food Processing and Preservation, 43(3), e13900. https://doi.org/10.1111/jfpp.13900
12. Hadjout-Krimat, L., Belbahi, A., Dahmoune, F., Hentabli, M., Boudria, A., Achat, S., Remini, H., Oukhmanou-Bensidhoum, S., Spigno, G., & Madani, K. (2023). Study of microwave and convective drying kinetics of pea pods (Pisum sativum L.): A new modeling approach using support vector regression methods optimized by dragonfly algorithm techniques. Journal of Food Process Engineering, 46(2), e14232. https://doi.org/10.1111/jfpe.14232
13. Hazervazifeh, A., Moghaddam, P. A., Pashmforoush, F., & Maleki, H. H. (2026). Machine learning-guided infrared drying of spearmint: Energy-efficient fixed vs. two-step temperature methods for phytochemical retention and market-compliant quality. Journal of Stored Products Research, 116, 102953. https://doi.org/10.1016/j.jspr.2026.102953
14. Jiang, N., Ma, J., Ma, R., Zhang, Y., Chen, P., Ren, M., & Wang, C. (2023). Effect of slice thickness and hot-air temperature on the kinetics of hot-air drying of Crabapple slices. Food Science and Technology, 43, e100422. https://doi.org/10.1590/fst.100422
15. Jibril, A. N., Zhang, X., Wang, S., Bello, Z. A., Henry, I. I., & Chen, K. (2024). Far-infrared drying influence on machine learning algorithms in improving corn drying process with graphene irradiation heating plates. Journal of Food Process Engineering, 47(4), e14603. https://doi.org/10.1111/jfpe.14603
16. Khaledifard, G., Taki, M., Dastjerdi, R. M., & Behbahani, B. A. (2025). Integrating drying kinetics, quality attributes and machine learning for red pepper drying in a greenhouse solar dryer. Scientific Reports, 16(1), 1899. https://doi.org/10.1038/s41598-025-31576-z
17. Khan, Md. I. H., Sablani, S. S., Nayak, R., & Gu, Y. (2022). Machine learning-based modeling in food processing applications: State of the art. Comprehensive Reviews in Food Science and Food Safety, 21(2), 1409–1438. https://doi.org/10.1111/1541-4337.12912
18. Kidane, H., Farkas, I., & Buzás, J. (2025). Characterizing agricultural product drying in solar systems using thin-layer drying models: Comprehensive review. Discover Food, 5(1), 84. https://doi.org/10.1007/s44187-025-00362-1
19. Kilic, A. (2025). Comprehensive Evaluation of Mathematical Models Used in the Thin‐Layer Cold Dried Foods. Food Science & Nutrition, 13(7), e70558. https://doi.org/10.1002/fsn3.70558
20. Kucuk, H., Midilli, A., Kilic, A., & Dincer, I. (2014). A Review on Thin-Layer Drying-Curve Equations. Drying Technology, 32(7), 757–773. https://doi.org/10.1080/07373937.2013.873047
21. Kumar, N., Sarkar, B. C., & Sharma, H. K. (2012). Mathematical modelling of thin layer hot air drying of carrot pomace. Journal of Food Science and Technology, 49(1), 33–41. https://doi.org/10.1007/s13197-011-0266-7
22. Li, Y., Che, G., Wan, L., Zhang, Q., Qu, T., & Zhao, F. (2023). Characteristics and mathematical models of the thin-layer drying of paddy rice with low-pressure superheated steam. International Journal of Agricultural and Biological Engineering, 16(1), 273–282. https://doi.org/10.25165/j.ijabe.20231601.7810
23. Martins, T. S., Sousa, T. S. e, Sales, V. H. G., Bandeira, M. da G. A., Higuita, D. M. C., & Vélez, H. A. V. (2021). Comparison between Thin-Layer Models and Non-Traditional Methods in the Modelling of Drying Kinetics of Crustacean Wastes. Brazilian Archives of Biology and Technology, 64, e21210130. https://doi.org/10.1590/1678-4324-2021210130
24. Moreno-Castillo, E. J., González-García, R., Grajales-Lagunes, A., Ruiz-Cabrera, M. A., & Abud-Archila, M. (2005). Water Diffusivity and Color of Cactus Pear Fruits (Opuntia Ficus Indica) Subjected to Osmotic Dehydration. International Journal of Food Properties, 8(2), 323–336. https://doi.org/10.1081/JFP-200060269
25. Ovando-Medina, V. M. (2023). Infrared drying kinetics of Capsicum annuum L. var. Glabriusculum (Piquin pepper) and mathematical modeling. Journal of Food Process Engineering, 46(7), e14333. https://doi.org/10.1111/jfpe.14333
26. Qadri, O. S., Osama, K., & Srivastava, A. K. (2020). Foam mat drying of papaya using microwaves: Machine learning modeling. Journal of Food Process Engineering, 43(6), e13394. https://doi.org/10.1111/jfpe.13394
27. Rashvand, M., Nadimi, M., Paliwal, J., Zhang, H., & Feyissa, A. H. (2024). Effect of Pulsed Electric Field on the Drying Kinetics of Apple Slices during Vacuum-Assisted Microwave Drying: Experimental, Mathematical and Computational Intelligence Approaches. Applied Sciences, 14(17), 7861. https://doi.org/10.3390/app14177861
28. Rodriguez, A., Sancho, A. M., Barrio, Y., Rosito, P., & Gozzi, M. S. (2019). Combined drying of Nopal pads ( Opuntia ficus‐indica ): Optimization of osmotic dehydration as a pretreatment before hot air drying. Journal of Food Processing and Preservation, 43(11). https://doi.org/10.1111/jfpp.14183
29. Sabbaghi, H., Nguyen, P. N., Sabbaghi, H., & Nguyen, P. N. (2025). Infrared Drying in Food Technology: Principles and Practical Insights. IntechOpen. https://doi.org/10.5772/intechopen.1009292
30. Sağlam, C., & Çetin, N. (2022). Machine learning algorithms to estimate drying characteristics of apples slices dried with different methods. Journal of Food Processing and Preservation, 46(10), e16496. https://doi.org/10.1111/jfpp.16496
31. Srivastava, P. K., & Sit, N. (2024). Mathematical and ANN Modelling for Convective Drying of Spanish Cherry Seeds: Bioactive Degradation, Energy Efficiency, and Mass Transfer Evaluation. Food Biophysics, 20(1), 12. https://doi.org/10.1007/s11483-024-09898-8
32. Taheri, S., Brodie, G., & Gupta, D. (2021). Optimised ANN and SVR models for online prediction of moisture content and temperature of lentil seeds in a microwave fluidised bed dryer. Computers and Electronics in Agriculture, 182, 106003. https://doi.org/10.1016/j.compag.2021.106003
33. Tepe, T. K. (2024). Convective Drying of Potato Slices: Impact of Ethanol Pretreatment and Time on Drying Behavior, Comparison of Thin-Layer and Artificial Neural Network Modeling, Color Properties, Shrinkage Ratio, and Chemical and ATR-FTIR Analysis of Quality Parameters. Potato Research, 67(3), 759–783. https://doi.org/10.1007/s11540-023-09663-3
34. 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
35. Touil, A., Chemkhi, S., & Zagrouba, F. (2014). Moisture Diffusivity and Shrinkage of Fruit and Cladode of Opuntia ficus-indica during Infrared Drying. Journal of Food Processing, 2014(1), 175402. https://doi.org/10.1155/2014/175402
36. Tran, D. A. T., Van, T. N., & Ho, T. K. P. (2025). Studies comparing the effectiveness of models for drying bitter gourd slices. Czech Journal of Food Sciences, 43(3), 205–215. https://doi.org/10.17221/255/2024-CJFS
37. Yang, T., Zheng, X., Xiao, H., Shan, C., & Zhang, J. (2024). Online monitoring system of material moisture content based on the Kalman filter fusion algorithm in air-impingement dryer. Frontiers in Sustainable Food Systems, 7, 1325367. https://doi.org/10.3389/fsufs.2023.1325367
38. Yu, P., Zhu, W., Shen, C., Qiao, Y., Zhang, W., Zhu, Y., Gong, J., & Cai, J. (2025). Current Status of Grain Drying Technology and Equipment Development: A Review. Foods, 14(14), 2426. https://doi.org/10.3390/foods14142426
39. Zartha Sossa, J. W., Orozco, G. L., García Murillo, L. M., Peña Osorio, M., & Sánchez Suarez, N. (2021). Infrared Drying Trends Applied to Fruit. Frontiers in Sustainable Food Systems, 5. https://doi.org/10.3389/fsufs.2021.650690
40. Zhang, J., Zheng, X., Xiao, H., Shan, C., Li, Y., & Yang, T. (2024). Quality and Process Optimization of Infrared Combined Hot Air Drying of Yam Slices Based on BP Neural Network and Gray Wolf Algorithm. Foods, 13(3). https://doi.org/10.3390/foods13030434
41. Zuo, Y., Jibril, A. N., Yan, J., Xia, Y., Liu, R., & Chen, K. (2025). Optimization of Online Moisture Prediction Model for Paddy in Low-Temperature Circulating Heat Pump Drying System with Artificial Neural Network. Sensors, 25(7). https://doi.org/10.3390/s25072308