Çok katmanlı algılayıcı ağı, uzun kısa süreli bellek ağı ve regresyon yöntemleri ile tarımsal kurutma tahmini

Year 2022, , 1188 - 1206, 15.10.2022

İlyas Kacar , Cem Korkmaz

https://doi.org/10.17714/gumusfenbil.1110463

Cited By: 4

Abstract

Tarımın önemli bir parçası olan gübrenin üretiminde kullanılan işlemlerden biri de kurutma işlemidir. Uygun kurutma parametrelerinin belirlenebilmesi, hem ürün kalitesi hem de üretim verimliliği açısından önemlidir. Kurutma işlem parametrelerinin belirlenmesinde regresyon yöntemleri sıklıkla kullanılmaktadır. Bu çalışmada regresyon yönteminin yanı sıra yapay sinir ağı, uzun kısa süreli bellek gibi makine öğrenme teknikleri de incelenmiştir. Modellemeler için %5 azot, %10 fosfor karışımından oluşan ticari bir organomineral gübrenin 70˚C, 75˚C ve 80˚C sıcaklıklarda kurutulması işleminden elde edilen veriler kullanılmıştır. Modellerden elde edilen sonuçlar ile deneysel sonuçlar kıyaslanmıştır. Her bir modelin tahmin performansları sunulmuştur. Uygun kurutma parametrelerini yakalamak, ürünün kurutma verimi açısından önemlidir. İlave olarak, kurutma simülasyonlarında, başarılı sonuçlar elde edilmesinde, model seçimi önemli rol oynamaktadır. Netice olarak, yapay sinir ağı ile oluşturulan modelin tahmin performansının diğerlerine göre daha başarılı olduğu tespit edilmiştir. Regresyonlar, mevcut verinin modellenmesinde verimli iken, ileriye yönelik tahminlerde başarılı olamamaktadırlar. Ayrıca kurutma verisi içerisindeki tepe ve çukurları tahmin etmede de yetersiz kalmaktadır.

Keywords

Çok katmanlı algılayıcı ağı, Makine öğrenmesi, Organik gübre, Regresyon, Tarımsal kurutma, Uzun kısa süreli bellek

Thanks

Dergi yönetimine bu çalışmamızın dergimizde yayınlanması için göstereceği gayret, ilgi ve alakaya şimdiden teşekkür ederiz

Prediction of agricultural drying using multi-layer perceptron network, long short term memory network and regression methods

Abstract

One of the processes used in the production of fertilizers, which has become an important part of agriculture, is the drying process. Determination of proper drying parameters is important both in terms of product quality and production efficiency. Regression methods are used to determine the drying process parameters frequently. In this study, in addition to the regression method, machine learning techniques are also examined such as artificial neural network, long short term memory method. The data obtained from the drying process of a commercial organomineral fertilizer consisting of a mixture of 5% nitrogen and 10% phosphorus at 70˚C, 75˚C, and 80˚C were used for modelling. The simulation results obtained from the models of the methods and the data obtained from the experiments were compared. The predictions and performances of each model were presented. Determination the appropriate drying parameters is It is important for the drying efficiency of the product. In addition, model selection plays an important role in obtaining successful results in drying simulations. As a result, it has been observed that the prediction performance of the model created with the artificial neural network is more successful than the others. While regressions are efficient in modelling existing data, they are not successful in predicting. Moreover, it is not enough to predict the peak and pits in the drying data.

Keywords

Multi layer perceptron network, Machine learning, Organic fertilizer, Regression, Agricultural drying, Long short time memory

References

• Adıyaman, F. (2007). Talep Tahmininde Yapay Sinir Ağlarının Kullanılması. [Yüksek Lisans Tezi, İstanbul Teknik Üniversitesi Fen Bilimleri Enstitüsü].
• Amini, G., Salehi F., & Rasouli M. (2021). Drying kinetics of basil seed mucilage in an infrared dryer: Application of GA-ANN and ANFIS for the prediction of drying time and moisture ratio. Journal of Food Processing and Preservation, 45(3): e15258. https://doi.org/10.1111/jfpp.15258
• Anderson, D., & McNeill, G. (1992)., Artificial neural networks technology. Rome Laboratory. A011. Bayır, F. (2006)., Yapay Sinir Ağları ve Tahmin Modellemesi Üzerine Bir Uygulama. [Yüksek Lisans Tezi, İstanbul Üniversitesi Sosyal Bilimler Enstitüsü].
• Beigi, M., & Torki, M. (2021). Experimental and ANN modelling study on microwave dried onion slices. Heat and Mass Transfer, 57: 787–796. https://doi.org/10.1007/s00231-020-02997-5
• Bidgoli, M.R., Kolahchi R., & Karimi M.S. (2016). An experimental study and new correlations of viscosity of ethylene glycol-water based nanofluid at various temperatures and different solid concentrations. Structural Engineering and Mechanics, 58(1): 93-102. https://doi.org/10.12989/sem.2016.58.1.093
• Brownlee, J. (2018). A gentle introduction to K-fold cross-validation. Machine Learning Mastery, 1-10.
• Çavuşlu, M.A., Becerikli, Y., & Karakuzu, C. (2012). Levenberg-Marquardt algoritması ile YSA eğitiminin donanımsal gerçeklenmesi. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 5(1).
• Çelen, S., Buluş, H. N. Moralar, A., Haksever, A., & Özsoy, E. (2016). Availability and Modelling of Microwave Belt Dryer in Food Drying. Journal of Tekirdag Agricultural Faculty, 13(04): 71-83.
• Eaton J. W. (2022). GNU Octave. Free Software Foundation. Association of volunteers.
• Erenturk, S., & Erenturk, K. (2007). Comparison of genetic algorithm and neural network approaches for the drying process of carrot. Journal of Food Engineering, 78: 905-912. https://doi.org/10.1016/j.jfoodeng.2005.11.031
• Estiati, I., Freire, F. B., Freire, J. T., Aguado, R., & Olazar, M. (2016). Fitting performance of artificial neural networks and empirical correlations to estimate higher heating values of biomass. Fuel, 180: 377-383. https://doi.org/10.1016/j.fuel.2016.04.051
• Heris, S.M.K. (2015). Time-series prediction using ANFIS. Yarpiz©.
• Karacabey, E., Aktaş, T., Taşeri, L., & Seçkin, G. U. (2020). Sultani çekirdeksiz üzüm çeşidinde farklı kurutma yöntemlerinin kurutma kinetiği, enerji tüketimi ve ürün kalitesi açısından incelenmesi. Journal of Tekirdag Agricultural Faculty, 17(1): 53-65. https://doi.org/10.33462/jotaf.578962
• Kaveh, M., Sharabiani, V. R., Chayjan, R. A., Taghinezhad, E., Abbaspour-Gilandeh, Y., & Golpour, I. (2018). ANFIS and ANNs model for prediction of moisture diffusivity and specific energy consumption potato, garlic and cantaloupe drying under a convective hot air dryer. Information Processing in Agriculture, 18(1): 45. https://doi.org/10.1016/j.inpa.2018.05.003
• Khanlari, A., Güler, H.O., Tuncer, A.D., Sirin, C., Bilge, Y.C., Yılmaz, Y., & Güngor, A. (2020). Experimental and numerical study of the effect of integrating plusshaped perforated baffles to solar air collector in drying application. Renew. Energy, 145: 1677–1692. https://doi.org/10.1016/j.renene.2019.07.076
• Kılıç, F. (2021). Effects of three drying methods on kinetics and energy consumption of carrot drying process and modelling with artificial neural networks. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 43(12): 1468-1485. https://doi.org/10.1080/15567036.2020.1832163
• Köklü, N., Büyüköztürk, Ş., & Çokluk-Bökeoğlu Ö. (2006). Sosyal Bilimler İçin İstatistik (25. baskı), Ankara: Pegem Yayıncılık.
• Lertworasirikul, S., &Tipsuwan, Y. (2008). Moisture content and water activity prediction of semi-finished cassava crackers from drying process with artificial neural network. Journal of Food Engineering, 84: 65-74. https://doi.org/10.1016/j.jfoodeng.2007.04.019
• Mansuroğlu, N.P., Yazıcı, E., Önder, S., & Karaç, A.C. (2020). Maltodekstrin-nohut proteini izolati matrisinde karabiber tohumu yağinin püskürtmeli kurutma metodu ile enkapsülasyonu. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 9(2): 877-882. https://doi.org/10.28948/ngmuh.649969
• MathWorks. (2022, July 30). Kernel (Covariance) Function Options. https://www.mathworks.com/help/stats/kernel-covariance-function-options.html.
• MathWorks. (2022, July 30). Statistics and Machine Learning Toolbox. https://www.mathworks.com/help/stats/index.html?s_tid=CRUX_lftnav.
• Million, E. (2022, April 12). The Hadamard Product. Linear Algebra. buzzard.ups.edu.
• Moreno, J.J.M., Pol, A.P., Abad, A.S., & Blasco, B.C., (2013). Using the R-MAPE index as a resistant measure of forecast accuracy. Psicothema, 25(4): 500-506. https://doi.org/10.7334/psicothema2013.23
• Nakilcioğlu-Taş, E., & Ötleş S. (2021). Zeytin çekirdeği antioksidanlarının dondurarak kurutma tekniği ile mikroenkapsülasyonu: Toz ürünün fiziksel ve kimyasal karakterizasyonu. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 10(1): 140-149. https://doi.org/10.28948/ngmuh.740797
• Naqvi, S.R., Rumaisa, T., Zeeshan,, H., Imtiaz A., Syed A. T., Muhammad N., Niazi, M. B. K., Tayyaba N, & Wasif F., (2018). Pyrolysis of high-ash sewage sludge: Thermo-kinetic study using TGA and artificial neural networks. Fuel, 233: 529-538. https://doi.org/10.1016/j.fuel.2018.06.089
• Omari, A., N. Behroozi-Khazaei, & F. Sharifian, (2018). Drying kinetic and artificial neural network modelling of mushroom drying process in microwave-hot air dryer. Journal of Food Process Engineering, e12849. https://doi.org/10.1111/jfpe.12849
• Onu, C. E., Igbokwe, P. K., Nwabanne, J. T., & Ohale, P.E. (2022). ANFIS, ANN, and RSM modelling of moisture content reduction of cocoyam slices. Journal of Food Processing and Preservation, 46(1): e16032. https://doi.org/10.1111/jfpp.16032
• Öğündür, G., (2019, April 08). Overfitting (aşırı öğrenme), underfitting (eksik öğrenme) ve bias-variance çelişkisi. Medium. https://medium.eom/@gulcanogundur/overfi tting-aşırı-öğrenme-underfitting-eksik-öğrenme-ve-bias-variance-çelişkisi-b92bef2f770d
• Park I., Kim, H. S., Lee J., Kim, J. H., Song, C. H., & Kim, H. K. (2019). Temperature prediction using the missing data refinement model based on a long short-term memory neural network. Atmosphere (Basel), 10: 1-16. https://doi.org/10.3390/atmos10110718
• Perazzini, H., Freire, F., & Freire, J. (2013). Drying kinetics prediction of solid waste using semi-empirical and artificial neural network models. Chemical Engineering & Technology, 36(7). https://doi.org/10.1002/ceat.201200593
• Polatoğlu, B., & Beşe, A.V. (2017). Kızılcık meyvesinin (cornus mas. L) konvektif kurutulması: kuruma kinetiği ve c vitamini bozulması. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 6(2): 406-414. https://doi.org/10.28948/ngumuh.341200
• Poonnoy, P., Tansakul, A., & M. Chinnan, (2007). Artificial neural network modelling for temperature and moisture content prediction in tomato slices undergoing microwave-vacuum drying. JFS E: Food Engineering and Physical Properties, 72(1): 42-47. https://doi.org/10.1111/j.1750-3841.2006.00220.x
• Sekertekin, A., Bilgili, M., Arslan, N., Yildirim, A., Celebi, K., & Ozbek, A. (2021). Short‑term air temperature prediction by adaptive neuro‑fuzzy inference system (ANFIS) and long short‑term memory (LSTM) network. Meteorology and Atmospheric Physics, 133(3). https://doi.org/10.1007/s00703-021-00791-4
• Sit, H., (2019, January 18). Quick start to Gaussian process regression. Towards data science. https://towardsdatascience.com/quick-start-to-gaussian-process-regression-36d838810319
• 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
• Tarafdar, A., Jothi, N., & Kaur, B. (2021). Mathematical and artificial neural network modeling for vacuum drying kinetics of moringa olifera leaves followed by determination of energy consumption and mass transfer parameters. Journal of Applied Research on Medicinal and Aromatic Plants, 24(100306). https://doi.org/10.1016/j.jarmap.2021.100306
• Topuz, A., (2010). Predicting moisture content of agricultural products using artificial neural networks. Advances in Engineering Software, 41(3): 464-470. https://doi.org/10.1016/j.advengsoft.2009.10.003
• Yifei, S., Lina, L., Qiang, W., Xiaoyi, Y., & Xin, T., (2016). Pyrolysis products from industrial waste biomass based on a neural network model. Journal of Analytical and Applied Pyrolysis, 120: 94-102. https://doi.org/10.1016/j.jaap.2016.04.013
• Zadhossein, S., Abbaspour-Gilandeh, Y., Kaveh, M., Szymanek, M., Khalife, E., Samuel, O. D., Amiri M., & Dziwulski, J. (2021). Exergy and energy analyses of microwave dryer for cantaloupe slice and prediction of thermodynamic parameters using ANN and ANFIS algorithms. Energies, 14(16): 4838. https://doi.org/10.3390/en14164838