Classification of durum wheat varieties by artificial neural networks

Öz

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.

Anahtar Kelimeler

• Artificial neural networks
• durum wheat
• physical properties

Yapay sinir ağları ile makarnalık buğday çeşitlerinin sınıflandırılması

Öz

Bu çalışmada, makarnalık buğday çeşitlerinin sınıflandırmasını yapmak amacıyla bir Yapay Sinir Ağları (YSA) modeli geliştirilmiştir. Bu amaçla makarnalık buğdaylara ait fiziksel özellikler belirlenmiş ve YSA teknikleri kullanılmıştır. Ülkemizde yetiştirilmekte olan on bir adet makarnalık buğday çeşidinin fiziksel özelliklerinden olan bin dane ağırlığı, geometrik ortalama çap, küresellik, dane hacmi, yüzey alanı, hacim ağırlığı, özgül ağırlık, porozite ve renk belirlenmiş ve bu özelliklerin çeşitlere göre istatistiksel olarak farklı olduğu tespit edilmiştir. YSA modeli olarak M-l, M-ll ve M-lll olmak üzere üç adet model geliştirilmiştir. Bu modellerin performansları karşılaştırılmıştır. En uygun modelin M-l modeli olduğu belirlenmiştir. M-l modelinde ağın yapısı, 11 giriş, 2 ara ve 1 çıkış katmanı olarak dizayn edilmiştir. Giriş parametresi olarak bin dane ağırlığı, geometrik ortalama çap, küresellik, dane hacmi, yüzey alanı, hacim ağırlığı, özgül ağırlık, porozite ve renk, çıkış parametresi olarak ise çeşitler kullanılmıştır. M-l modeli için R2 değeri %99.99, RMSE değeri 0.00074 ve ortalama hata değeri %0.009 olarak bulunmuştur. M-l modeli ile elde edilen tüm sonuçların gerçek veriler ile uyumluluk içinde olduğu görülmüştür. Bu model ile Ticaret Borsaları ve un fabrikalarında ürünleri sınıflandırma ve temizleme amacıyla otomasyon sistemleri oluşturmak mümkün olabilecektir.

Anahtar Kelimeler

• Fiziksel özellikler
• makarnalık buğday
• yapay sinir ağları

Kaynakça

1. Anonymous, 1996. www. hunterlab.com. CIE L* a* b*color scale.
2. Atlı, A., Koçak, N., Aktan, M. 1993. Ülkemiz çevre koşullarının kaliteli makarnalık buğday yetiştirmeye uygunluk yönünden değerlendirilmesi. Hububat Sempozyumu, 8-11 Haziran 1993, 345-351s., Konya.
3. Aviara, N.A., Gwandzang, M.I., Haque, M.A. 1999. Physical properties of guna seeds. Journal of Agricultural Engineering Research, 73: 105-111.
4. Aydoğan, H., Altun, A.A., Ozcelik, A.E. 2011. Performance analysis of a turbocharged diesel engine using biodiesel with back propagation artificial neural network. Energ Educ Sci Tech-A, 28: 459-468.
5. Babalık, A., Baykan, Ö.K., Botsalı, F.M. 2006. Determination of wheat kernel type by using image processing techniques and ANN. The International Conference on Modelling and Simulating, August 28-30, Konya.
6. Bağırkan, Ş. 1993. İstatistiksel Analiz. Bilim Teknik Yayınevi. s. 301. İstanbul.
7. Baykan, Ö.K., Babalık, A., Botsalı, F.M. 2005. Yapay sinir ağı kullanarak buğday türü tanınması. 4. Uluslararası İleri Teknolojiler Sempozyumu, Konya, Eylül 28-30, 188-190.
8. Bechtler, H., Browne, M.W., Bansal, P.K., Kecman, V. 2001. New approach to dynamic modelling of vapour-compression liquid chillers: artificial neural networks. Appl Therm Eng, 21: 941-53.

9. Bell, M., Fischer, R.A. 1994. Guide to plant and crop sampling: Measurement and observations for agronomic and physiological research in small grain cereals. Wheat Special Report. No. 32, CIMMYT, Mexico D.F.
10. Chen, X., Xun, Y., Li, W. and Zhang, J. 2010. Combining discriminant analysis and neural networks for corn variety identification. Computers and Electronics in Agriculture 71S, S48–S53.
11. Connolly, C., Fleiss, T. 1997. A study of efficiency and accuracy in the transformation from RGB to CIELAB colour space. IEEE Transactions on Image Processing, 6: 1046-1048.
12. Çölkesen, M., Öktem, A., Eren, N., Akıncı, C. 1993. Determination of suitable durum wheat varieties on dry and irrigated conditions in Şanlıurfa. The Symposium of Durum Wheat and Products, p. 573. Ankara.
13. Dubey, B.P., Bhagwat, S.G., Shouche, S.P., Sainis, J.K. 2006. Potential of Artificial Neural Networks in Varietal Identification using Morphometry of Wheat Grains. Biosystems Engineering 95: 61-67.
14. Dursun, E., Güner, M. 2003. Determination of mechanical behaviour of wheat and barley under compression loading. Journal of Agricultural Sciences, 9: 415-420.
15. Genç, İ., Yağbasanlar, T., Özkan, H., Kılınç, M. 1993. Seçilmiş bazı makarnalık buğday hatlarının Güneydoğu Anadolu bölgesi sulu koşullarına adaptasyonu üzerinde araştırmalar. Makarnalık Buğday ve Mamulleri Simpozyumu Kitabı, 261-272s, Ankara.
16. Güner, M. 2007. Pneumatic conveying characteristics of some agricultural seeds. Journal of Food Engineering, 80: 904-913.
17. Hacıseferoğulları, H., Demir, Ö., Çalışır, S. 2005. Some nutritional and technological properties of garlic (Allium sativum L.). Journal of Food Engineering, 68: 463-469.
18. Jacobs, R.A. 1988. Increased Rate of Convergence Through Learning Rate Adaptation. Neural Networks, 1(4): 295-307.
19. Jain, R.K., Bal, S. 1997. Properties of pearl millet. Journal of Agricultural Engineering Research, 66: 85-91.
20. Jayas, D.S., Paliwal, J., Visen, N.S. 2000. Multi-layer neural networks for image analysis of agricultural products. Journal of Agricultural Engineering Research, 77: 119-128.
21. Kalogirou, S.A. 1999. Applications of artificial neural networks in energy systems. Energy Conversion & Management 40: 1073-1087.
22. Kalogirou, S.A. 2001. Artificial neural networks in the renewable energy systems applications: A review. Renewable and Sustainable Energy Reviews, 5: 373-401.
23. Kün, E. 1988. Serin İklim Tahılları. Ankara Üniversitesi, Ziraat Fakültesi Yayınları, 1032, Ders Kitabı: 299. Ankara.
24. Levenberg, K. 1944. A Method For the Solution of Certain Nonlinear Problems in Least Squares. Quart. Appl. Math., 2: 164-168.
25. Liao, K., Paulsen, M.R., Reid, J.F., Ni, B.C., Bonifacio-Maghirang, E.P. 1993. Corn kernel breakage classification by machine vision using a neural network classifier. Transactions of the ASAE, 36: 1949-1953.
26. Marquardt, D.W. 1963. An Algorithm For Least-Squares Estimation Of Nonlinear Parameters. J. Soc. Indust. Appl. Math., 11: 431-441.
27. Minai, A.A., Williams, R.D. 1990. Back-Propagation Heuristics: a Study of The Extended Delta-bar-delta Algorithm” International Joint Conference on Neural Networks, vol.1, 595-600, San Diego, CA, USA.
28. Mohsenin, N.N. 1970. Physical properties of plant and animal materials. New York: Gordon and Breach Science Publishers Inc.
29. Nelson, S.O. 2002. Dimensional and density data for seeds of cereal grain and other crops. Trans. ASAE, 45: 165-170.
30. Ogunjimi, L.O., Aviara, N.A., Aregbesola, O. A. 2002. Some engineering properties of locust bean seed. Journal of Food Engineering, 55: 95-99.
31. Paliwal J., Visen N.S., Jayas, D.S., 2001. Evaluation of neural network architectures for cereal grain classification using morphological features. J. Agric. Engineering Resource, 79: 361-370.
32. Pazoki, A.R., Pazoki, Z. 2011. Classification system for rain fed wheat grain cultivars using artificial neural network. African J. Biotechnology. 10: 8031-8038.
33. Pourreza, A., Pourreza, H., Mohammad-Hossein Abbaspour-Fard, Sadrnia., H. 2012. Identification of nine Iranian wheat seed varieties by textural analysis with image processing. Computers and Electronics in Agriculture 83: 102-108.
34. Purushothaman, S., Srinivasa, Y.G. 1994. A back-propagation algorithm applied to tool wear monitoring. International Journal of Machine Tools and Manufacture, Vol. 34, No:5, pp: 625-631.
35. Romaniuk, M.D., Sokhansanj, S., Wood, H.C. 1993. Barley seed recognition using a multi-layer neural network. ASAE Paper No. 93: 65-69.
36. Sacilik, K., Oztürk, R. Keskin, R. 2003. Some physical properties of hemp seed. Biosystems Engineering, 86: 191-198.
37. Sitkei, G. 1986. Mechanics of agricultural materials. Budapest: Academia Kiado.
38. Sokhansanj, S., Lang, W. 1996. Prediction of kernel and bulk volüme of wheat and canola during adsorption and desorption. Journal of Agricultural Engineering Research, 63: 129-136.
39. Tabatabaeefar, A. 2003. Moisture-dependent physical properties of wheat. Int. Agrophysics, 17: 207-211.
40. Taner, A., Tekgüler, A., Sauk, H., Demirel, B. 2012. Yulaf Çeşitlerinin Yapay Sinir Ağları Kullanılarak Sınıflandırılması. 27. Tarımsal Mekanizasyon Ulusal Kongresi, Samsun.
41. Topal, A., Aydın, C., Akgün, N., Babaoglu, M. 2004. Diallel cross analysis in durum wheat (Triticum durum Desf.): identification of best parents for some kernel physical features. Field Crops Research, 87: 1-12.
42. TUİK. 2013. Türkiye İstatistik Kurumu. www.tuik.gov.tr.
43. Visen, N.S., Paliwal, J., Jayas, D.S., White, N.D.G. 2002. Specialist neural Networks for cereal grain classification. Biosystems Engineering, 82: 151-159.
44. Wang N., Dowell F., Zhang N. 2002. Determining wheat vitreousness using image processing and a neural network. ASAE Annual International Meeting, İllinois, July 28-31.
45. Wang, Z., Cong, P., Zhou, J., Zhu, Z. 2007. Method for identification of external quality of wheat grain based on image processing and artificial neural network. Transaction of the CSAE, 23: 158-161 (in Chinese).
46. Yun, L. 2004. Study on Grain Appearance Quality Inspection using Machine Vision. China Agriculture University, Beijing (in Chinese).
47. Yurtsever, N. 1984. Deneysel İstatistik Metotları. T.C.K.B. Köy Hizmetleri Genel Müdürlüğü Yayınları No: 124, Ankara.
48. Zapotoczny, P. 2011. Discrimination of wheat grain varieties using image analysis and neural networks. Part I. Single kernel texture. Journal of Cereal Science, 54: 60-68.