1
Tekirdag Namık Kemal University, Corlu Faculty of Engineering, Tekirdag
2
Tekirdag Namık Kemal University, Corlu Faculty of Engineering, Tekirdag
Abstract
Predicting product drying kinetics is crucial for achieving optimal drying processes without compromising product quality. This prediction technique necessitates the development of numerical drying models. The aim of this research is to compare prediction models developed using two popular machine learning approaches in recent years: Adaptive Neuro-Fuzzy Inference Systems (ANFIS) and Artificial Neural Networks (ANN). In this study, kiwi slices of three different thicknesses were dried using 90 W microwave power. Prediction models were developed using experimental data. The input for the training algorithm included kiwi slice thickness and drying time, while the output was the moisture content of the product. The performance of the models was evaluated by comparing the obtained outputs with experimental data from test sets. These models were assessed using mean absolute percentage error, correlation coefficient, root mean square error and mean bias error metrics. The ANN-based prediction model demonstrated better performance compared to the ANFIS model. The results of these tests indicate that both methods can be used for predicting the moisture content of kiwi slices.
Keywords
Anfis,kiwi,machine learning,microwave drying
How to Cite
BULUS , H. N. ., & CELEN , S. . (2025). Prediction of Moisture Content in Kiwi (Actinidia deliciosa) Dried Using Machine Learning Approaches. ISPEC Journal of Agricultural Sciences, 9(1), 74–88. https://doi.org/10.5281/zenodo.14564833
📄Acar, B., Dağdeviren A., Özkaymak M., Guinaleh, A.R., 2023. Freeze drying process of kiwi slices with various thicknesses and investigation drying characteristic of process, Journal of Polytechnic, 26(1): 415-423.
📄Akal, D., Çelen, S., Kahveci, K., Akyol, U., 2014. An Experimental study on microwave drying behavior of kiwi, Materials, Methods and Technologies, 8: 449-456.
📄Ali, N.S., Mohd-Yusof, K., Othman, M.F., Latip, R.A., Ismail, M.S.N., 2019. Adaptive neuro fuzzy İnference system (ANFIS) modelling for quality estimation in palm oil refining process, Journal of Mechanical Engineering, 8(1): 36-47.
📄Bakar, M.A.A., Ghani, A.T.A., Abdullah, M.L., Ismail, N., Aziz, A.S., 2022. Adaptive neuro-fuzzy inference system (ANFIS) formulation to predict students' neuroscience mechanistic: a concept of an ıntelligent model to enhance mathematics learning ability, TEM Journal, 11(4): 1942-1951.
📄Beşirik, B.A., 2016. A case study on predicting trading decisions in the cryptocurrency market using fuzzy logic and fuzzy artificial neural networks (ANFIS) techniques, Master Thesis, Dokuz Eylül University, Institute of Natural and Applied Sciences, İzmir.
📄Bulus, H.N., 2024. Adaptive neuro-fuzzy inference system and artificial neural network models for predicting time-dependent moisture levels in hazelnut shells (Corylus avellana L.) and prina (Oleae europaeae L.), Processes, 12: 1703.
📄Çelen S., Arda S.O., Karataşer M.A., 2018. Modeling of drying behavior using microwave conveyor dryer assisted solar energy, El-Cezerî. 5: 267-271.
📄Darvishi, H., Mohammadi, P., Azadbakht, M., Farhudi, Z., 2018. Effect of different drying conditions on the mass transfer characteristics of kiwi slices, Journal of Agricultural Science and Technology. 20: 249-264.
📄Demirci, E., 2020. Anfis and natural gas request estimated; the case of Turkey. International Journal of Social Sciences Academy, (3): 495-511.
📄Habashy, D.M., Lebda, H.I., 2022. Comparison between artificial neural network and adaptive neuro-fuzzy ınference system for the baryon-to-meson ratios in proton-proton collisions, arXiv:2209.12709.
📄Kacar, İ., Korkmaz, C., 2022. Prediction of agricultural drying using multi-layer perceptron network, long short-term memory network and regression methods, Gümüşhane University Journal of Science and Technology, 12(4): 1188-1206.
📄Kaplan, R., 2019. Artificial neural networks method and a research on forecasting economics indicators, Master’s Thesis, Dokuz Eylul University, Institute of Natural and Applied Sciences, İzmir.
📄Karabulut, M., 2024. An application in Red Crescent businesses for predicting breakage risks in supply chains using artificial intelligence methods, PhD Thesis, İnönü University, Institute of Natural and Applied Sciences, Malatya.
📄Kaya, A., Aydın, O., Dincer, I., 2008. Experimental and numerical investigation of heat and mass transfer during drying of Hayward kiwi fruits (Actinidia Deliciosa Planch), Journal of Food Engineering, 88: 323–330.
📄Kaynar, O., Zontul, M., Demirkoparan, F., 2010. Crude oil price forecasting by using ANFIS. Journal of Anadolu Bil Vocational School of Higher Education, 17: 3–14.
📄Khazaei, N.B., 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. Computers and Electronics in Agriculture. 98: 205–213.
📄Mousavifard, S.M., Attar, M.M., Ghanbari, A., Dadgar, M., 2015. Application of artificial neural network and adaptive neuro-fuzzy inference system to investigate corrosion rate of zirconium-based nano-ceramic layer on galvanized steel in 3.5% NaCl solution. Journal of Alloys and Compounds, 639: 315-324.
📄Levent, M., 2023. Modeling of drying processes with fuzzy logic and artifical neural network methods, MSc. Thesis, Institute of Natural and Applied Sciences, Tekirdağ Namik Kemal University, Tekirdağ.
📄Levent, M., Buluş, H.N., Moralar, A., Çelen, S., 2023. Fındık kabuğu kurutma parametre tahmininde yapay sinir ağı modellerinin karşılaştırılması, Bilgisayar ve Elektronik Bilimlerinde Güncel Gelişmeler 2, Iksad Publishing House, Ankara, 24-46.
📄Oğuz Erenler, G., 2023. Prediction of wind power with fuzzy logic and artificial neural networks, MSc Thesis, Institute of Natural and Applied Sciences, Tekirdağ Namik Kemal University, Tekirdağ.
📄Putra, V.G.V., Mohanad, J.N., 2023. Adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANNs) for optimizing electrospun PVA/TIO2 fiber diameter, The Journal of The Textile Institute, 114(12): 1898-1908.
📄Solichin, A., Saputri, F.H., 2021.An adaptive neuro-fuzzy inference system (ANFIS) method for recommending employee mutations in a manufacturing company, Journal of Physics: Conference Series. 1908 012016.
📄Şencan, D., Şencan Şahin, A., 2022. Forecasting GDP in Türkiye using Anfis method. Kafkas University Journal of Economics and Administrative Sciences Faculty, 13(26): 953–71.
📄Şevik, S., Aktaş, M., Özdemir, M.B., Doğan, H., 2014. Modeling of drying behaviors of mushroom in a solar assisted heat pump dryer by using artificial neural network. Journal of Agricultural Sciences. 20: 187-202.
📄Sonmez, A.Y., Kale, S., Ozdemir, R.C., Kadak, A.E., 2018. An adaptive neuro-fuzzy inference system (ANFIS) to predict of cadmium (cd) concentrations in the Filyos River, Turkey, Turkish Journal of Fisheries and Aquatic Sciences, 18:1333-1343.
📄Taşova, M., Erdoğan, M., Başakın, E.E., 2020. Determination of drying machine potential by different estimation methods, Yuzuncu Yil University Journal of the Institute of Natural and Applied Sciences, 25(2): 49-55.
📄Tektaş, A., Karataş, A., 2004. Yapay sinir ağları ve finans alanına uygulaması: Hisse senedi fiyat tahminlemesi, Journal of Economics and Administrative Sciences, 18(3-4): 337-349.
📄Tınmaz Köse, E., Çelen, S., Çelik, S.Ö., 2019. Conventional and microwave drying of hydrocarbon cutting sludge, Environmental Progress & Sustainable Energy, 38(4): 1-7.
📄Turan, T., Turan, G., Köse, U., 2022. Prediction of the Covid-19 number of death in Turkey by adaptive neuro-fuzzy ınference system and artifical neural networks. Journal of Information Technologies, 15(2): 97–105.
📄Walia, N., Singh, H., Sharma, A., 2015. ANFIS: Adaptive neuro-fuzzy inference system- a survey, International Journal of Computer Applications, 123(13): 32-38.
,
Soner CELEN
2