Classification of durum wheat varieties by artificial neural networks

• Published in: Anadolu tarım bilimleri dergisi (Online) Vol. 30; no. 1; p. 51
• Main Authors: Taner, Alper, Tekgüler, Ali, Sauk, Hüseyin
• Format: Journal Article
• Language: English; Turkish
• Published: Samsun Ondokuz Mayis University (OMU), Ziraat Fakultesi Kurupelit 01.02.2015
• Subjects: Agricultural production; Neural networks; Selective breeding; Wheat
• ISSN: 1308-8750; 1308-8769
• DOI: 10.7161/anajas.2015.30.1.51-59

In this study, an Artificial Neural Network (ANN) was developed in order to classify durum wheat varieties. For this purpose, physical properties of durum wheat varieties were determined and ANN techniques were used. The physical properties of 11 durum wheat varieties grown in our country, namely thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and color parameters of grain, were determined and it was found that these properties were statistically significant with respect to varieties. As ANN model, three models, M-l, M-ll and M-lll were constructed. The performances of these models were compared. It was determined that the best fit model was M-1. In the M-1 model, the structure of the model was designed to be 11 input layers, 2 hidden layers and 1 output layer. Thousand kernel weight, geometric mean diameter, sphericity, kernel volume, surface area, bulk density, true density, porosity and color parameters of grain were used as input parameter; and varieties as output parameter. R2, RMSE and mean error for the M-l model were found as 99.99%, 0.00074 and 0.009%, respectively. All results obtained by the M-l model were observed to have been quite consistent with real data. By this model, it would be possible to construct automation systems for classification and cleaning in Commodity (Grain) Exchange and flour mills.