Fasulyede (Phaseolus vulgaris L.) Kırılma Direnci Değerlerinin Çoklu Lineer Regresyon ve Yapay Sinir Ağları ile Modellenmesi

Amaç: Bu çalışma fasulyenin kırılma direnci değerlerini çoklu liner regresyon (MLR) ve yapay sinir ağlarıyla (ANN) modellemek amacıyla yapılmıştır. Materyal ve Metot: Araştırmada dört farklı fasulye çeşidi (Akman, Topçu, Göynük ve Karacaşehir) beş farklı tohum nem içeriğinde (%14.28, %24.32, %33.45, %42.54 ve %53.48) kullanılmıştır. Çoklu liner regresyon ve yapay sinir ağı modellerinde tohumların; uzunluk, genişlik, kalınlık, aritmetik ortalama çap, geometrik ortalama çap, yüzey alanı ve küresellik değerleri giriş parametresi, kırılma direnci değerleri ise çıkış parametresi olarak dikkate alınmıştır. Ayrıca, yapay sinir ağı modellinde 24 farklı ağ yapısı dikkate alınmıştır. Bulgular: Araştırmada Akman (0.979) ve Karacaşehir (0.986) için en yüksek R2 değerleri Levenberg-Marquard öğrenme fonksiyonu ve logarithmic sigmoid – liner transfer fonksiyonlarının 12 nöron ile kullanıldığı ANN 11 ağında elde edilmiştir. Bununla beraber Topçu (0.963) ve Göynük (0.944) için en iyi tahmin değerleri sırasıyla ANN 7 ve ANN 2 ağlarında belirlenmiştir. Ayrıca Topçu ve Göynük için en iyi öğrenme fonksiyon çifti sırasıyla logarithmic sigmoid - symmetric sigmoid ve logarithmic sigmoid- lineer fonksiyon çiftlerinde belirlenmiştir Sonuç: Çalışma sonuçları açıklıkla göstermiştir ki tüm fasulye çeşitlerindeki kırılma dirençleri ANN ile başarılı bir şekilde modellenmiştir.

The modelling of rupture force of white kidney beans (Phaseolus vulgaris L.) using the multiple linear regression (MLP) and artificial neural networks (ANN)

Objective: The objective of this study modelling the rupture force of white kidneybeans with the multiple linear regression (MLR) and artificial neural networks (ANN).Material and Methods: It was used four different white kidney bean varieties (Akman,Topçu, Göynük and Karacaşehir) at the five different moisture contents (14.28%, 24.32%,33.45%, 42.54% and 53.48%). In the MLR and ANN models the moisture contents, length,width, thickness, arithmetic mean diameters, geometric mean diameters, surface areaand sphericity of the beans were used as input parameters while the rupture force asoutput parameter. In addition, 24 different ANN architectures were used in the ANN.Results: The highest R2 values for the Akman (0.979) and Karacaşehir (0.986) varietieswere obtained in the ANN11 architecture used by the Levenberg-Marquard learningfunction and the logarithmic sigmoid - linear transfer function pairs with 12 neurons.However, the best prediction values for Topçu (0.963) and Göynük (0.944) were obtainedin ANN 7 and ANN 2 architectures, respectively. In addition, the best pair of learningfunctions for Topçu and Göynük were observed in Logarithmic sigmoid - Symmetricsigmoid and Logarithmic sigmoid- linear transfer functions, respectively.Conclusion: The results of the study clearly showed that the ANN successfully modeledrupture force in all the white kidney bean varieties.

PDF

___

ASAE (1999). Moisture measurement – unground grain and seeds. S352.2, DEC97.ASAE Standards, Standards Engineering Practices Data. ASAE, St. Joseph, MI.
Droulia F, Lykoudis S, Tsiros I, Alvertos N, Akylas E , Garofalakis I (2009). Ground temperature estimations using simplified analytical and semi-empirical approaches. Solar Energy 83: 211- 219
Emamgholizadeh S, Parsaeian M, Baradaran M (2015). Seed yield prediction of sesame using artificial neural network. European Journal of Agronomy 68: 89-96.
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.
Franch LJ, Panigrahi S (1997). Artificial neural network models of wheat leaf wetness. Agricultural and Forest Meteorology 88: 57—65.
Gardner MW, Dorling SR (1998). Artificial neural networks (the multilayer perceptron) - a review of applications in the atmospheric science. Atmospheric Environment 32: 2627-2636.
Gevrekçi Y, Yeğenoğlu E, Akbaş Y, Sesli M (2011). Yapay sinir ağlarının tarımsal alanda kullanımı. Ege Üniversitesi Ziraat Fakültesi Dergisi, 48(1): 71-76.
Hernandez-Perez JA, Garcia-Alvarado MA, Trystram G, Heyd B (2004). Neural networks for heat and mass transfer prediction during drying of cassava and mango. Innovative Food Science Emergency Technology 5:57–64.
Jain RK, Bal S (1997). Physical properties of pearl millet. Journal of Agricultural Engineering Research, 56, 89-98.
Kerdpiboon S, Kerr WL, Devahastin S (2006). Neural network prediction of physical property changes of dried carrot as a function of fractal dimension and moisture content. Food Research International 39: 1110–1118.
Khazaei J, Shahbazi F, Massah J, Nikravesh M, Kianmehr M (2008). Evaluation and modeling of physical and physiological damage to wheat seeds under successive impact loadings: mathematical and neural networks modeling. Seed physiology, production & technology 48(4):1532-1544
Latrille E, Corrieu G, Thibault J (1993). pH prediction and final fermentation time determination in lactic acid batch fermentations. Escape 2. Computer Chemical Engineering 17: 423–428.
Martynenko AI, Yang SX (2006). Biologically inspired neural computation for ginseng drying rate. Biosystems Engineering 95 (3): 385–396.
Movagharnejad K, Nikzad M (2007). Modelling of tomato drying using artificial neural network. Computers and Electronics in Agriculture 59: 78–85
Nimkar PM, Mandwe DS, Dudhe RN (2005). Physical properties of moth gram. Biosystems Engineering 91 (2): 183–189.
Nizian M. Noori S, Abdipour M (2018). Modeling the seed yield of Ajowan (Trachyspermum ammiL.) using artificial neural network and multiple linear regression models. Industrial Crops & Products 117:224-234
Sehirali S (1988). Edible Pulses. Publications of Agricultural Faculty of Ankara University No: 1089. Ankara/Turkey (in Turkish).
Sivrikaya O (2009). Comparison of artificial neural networks models with correlative works on undrained shear strength. Eurasian Soil Science 42 (13): 1487–1496.
Sologubik CA, Campa˜none LA, Pagano AM, Gely MC (2013). Effect of moisture content on some physical properties of barley. Industrial Crops and Products: 43:762– 767
Sun DW, Woods JL (1994). Low temperature moisture transfer characteristics of barley: thin-layer models and equilibrium isotherms. J. Agric. Eng. Res. 59: 273–283
Trelea IC, Raoult-Wack AL, Trystram G (1997). Application of neural network modelling for the control of dewatering and impregnation soaking process (osmotic dehydration). Food Science and Technology International 3:459–465
Van Wijk M , Bouten T, Verstraten J M (2002). Comparison of different modeling strategies for simulating gas exchange of a douglas-fir forest. Ecological Modeling 158: 63—81