Buğday Tohumlarının Derin Sinir Ağı Uygulaması ile Sınıflandırılması

Abstract

Son yıllarda, tarımla ilgili yapılan çalışmalar incelendiğinde sinir ağı ve büyük veri uygulamaları hızla artmaktadır. Bununla birlikte derinlemesine katmanların kullanıldığı Deep Neural Network (DNN) ile özellikle sınıflandırma alanında çok daha başarılı sonuçlar elde edilmektedir. Bu çalışmada UCI Machine Learning Repository’den alınan buğday tohumlarının sınıflandırılması için yeni bir DNN modeli önerilmiştir. Veri setinde Kama, Rosa ve Canadian olmak üzere 3 farklı buğday türünden toplam 210 veri bulunmaktadır. Veriler; %70 eğitim verisi ve %30 test verisi olarak ayrılarak geliştirilen model veri setine uygulandığında, verilerin sınıflandırılmasında %100 başarı oranı elde edilmiştir. Aynı zamanda Fuzzy C-Means tabanlı bir algoritma geliştirilerek 150.000 adet sentetik buğday tohum verisi üretilmiştir. Önerilen model UCI buğday tohumu ve sentetik olarak üretilen verileri kullanarak farklı eğitim ve test veri kombinasyonları üzerinde test edilmiş ve her birinde %100'lük bir başarı oranına sahip sınıflandırma elde edilmiştir. Önerilen model, buğday sınıflandırmaları için literatürdeki diğer çalışmalara kıyasla en iyi model olduğunu göstermektedir.

Keywords

• Büyük Veri,Sınıflandırma,Derin Öğrenme,Derin Sinir Ağı,Tohum,Buğday

An Application of Deep Neural Network for Classification of Wheat Seeds

Abstract

In recent years, applications of neural network and big data have increased rapidly in agriculture-related areas. At the same time, Deep Neural Network (DNN), in which deep layers are used, achieves much better results especially for classification of big datas properly. In this study, a new DNN model is proposed for the classification of wheat seeds which was taken from UCI Machine Learning Repository. There are totally 210 data from 3 different types of wheat, namely; Kama, Rosa and Canadian. The model is divided into 70% train data and 30% test data. When the developed model was applied to dataset, 100% success rate is achieved in classification of data. In addition, 150,000 pieces of synthetic wheat seed data are generated by using a Fuzzy C-Means based algorithm. The proposed model is tested on different train and test data combinations by using UCI wheat seed and synthetically generated datasets, and 100% success rate was achieved in classification. The proposed model shows that it is the best model compared to other studies in the literature for wheat classifications.

Keywords

• Big Data,Classification,Deep Learning,Deep Neural Network,Seed,Wheat

Thanks

This work was supported by Karamanoğlu Mehmetbey University, Karaman, Turkey.

References

1. Kamilaris, A. and F.X. Prenafeta-Boldu, Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 2018. 147: p. 70-90.
2. Rahman, A. and B. Cho, Assessment of seed quality using non-destructive measurement techniques: A review. Seed Science Research, 2016. 26(4): p. 285-305.
3. Lu, Y., et al., Identification of rice diseases using deep convolutional neural networks. Neurocomputing, 2017. 267: p. 378-384.
4. Amara, J., B. Bouaziz, and A. Algergawy, A Deep Learning-based Approach for Banana Leaf Diseases Classification in Datenbanksysteme für Business, Technologie und Web (BTW 2017). 2017. p. 79-88.
5. Wan, P., et al., A methodology for fresh tomato maturity detection using computer vision. Computers and Electronics in Agriculture, 2018. 146: p. 43-50.
6. Leemans, V. and M.F. Destain, A real-time grading method of apples based on features extracted from defects. Journal of Food Engineering, 2004. 61(1): p. 83-89.
7. Bakhshipour, A. and A. Jafari, Evaluation of support vector machine and artificial neural networks in weed detection using shape features. Computers and Electronics in Agriculture, 2018. 145: p. 153-160.
8. Chen, S.W., et al., Counting Apples and Oranges With Deep Learning: A Data-Driven Approach, in IEEE Robotics and Automation Letters 2017. p. 781-788.

9. Dyrmann, M., H. Karstoft, and H.S. Midtiby, Plant species classification using deep convolutional neural network. Biosystems Engineering, 2016. 151: p. 72-80.
10. Sadeghi-Tehran, P., et al., Automated Method to Determine Two Critical Growth Stages of Wheat: Heading and Flowering. Frontiers in Plant Science, 2017. 8.
11. Sabancı, K. and M. Akkaya, Classification of Different Wheat Varieties by Using Data Mining Algorithms. International Journal of Intelligent Systems and Applications in Engineering 2016. 4(2): p. 40-44.
12. Parnian, A.R. and R. Javidan, Autonomous Wheat Seed Type Classifier System. International Journal of Computer Applications, 2014. 96(12): p. 14-17.
13. Lalis, J.T., A New Multiclass Classification Method for Objects with Geometric Attributes Using Simple Linear Regression. IAENG International Journal of Computer Science, 2016. 43(2): p. 198-203.
14. Sujatha, R. and D. Ezhilmaran, Evaluation of Classifiers to Enhance Model Selection. International Journal of Computer Science & Engineering Technology (IJCSET), 2013. 4(1): p. 16-21.
15. Ajaz, R.H. and L. Hussain, Seed Classification using Machine Learning Techniques. Journal of Multidisciplinary Engineering Science and Technology, 2015. 2(5): p. 1098-1102.
16. Abad, M.S.J., A.A. Abkar, and B. Mojaradi, Effect of the Temporal Gradient of Vegetation Indices on Early-Season Wheat Classification Using the Random Forest Classifier. Appl. Sci., 2018. 8(1216): p. 1-20.
17. Basati, Z., M. Rasekh, and Y. Abbaspour-Gilandeh, Using different classification models in wheat grading utilizing visual features. Int. Agrophys., 2018. 32: p. 225-235.
18. Charytanowicz, M., et al., Discrimination of Wheat Grain Varieties Using X-Ray Images. Information Technologies in Medicine, 2016: p. 39-50.
19. Charytanowicz, M., et al., An evaluation of utilizing geometric features for wheat grain classification using X-ray images. Computers and Electronics in Agriculture, 2018. 144: p. 260-268.
20. Aslan, M.F., K. Sabancı, and A. Durdu, Different Wheat Species Classifier Application of ANN and ELM. Journal of Multidisciplinary Engineering Science and Technology (JMEST), 2017. 4(9): p. 8194-8198.
21. Qiongyan, L., et al., Detecting spikes of wheat plants using neural networks with Laws texture energy. Plant Methods, 2017. 13(83): p. 1-13.
22. Vlasov, A.V. and A.S. Fadeev, A machine learning approach for grain crop’s seed classification in purifying separation Journal of Physics Conference Series 2017. 803(1): p. 1-6.
23. Sabancı, K., A. Kayabaşı, and A. Toktaş, Computer vision-based method for classification of wheat grains using artificial neural network J Sci Food Agric, 2017. 97: p. 2588-2593.
24. Kayabaşı, A., An Application of ANN Trained by ABC Algorithm for Classification of Wheat Grains. International Journal of Intelligent Systems and Applications in Engineering, 2018. 6(1): p. 85-91.
25. Schmidhuber, J., Deep learning in neural networks: An overview. Neural Networks, 2015. 61: p. 85-117.
26. LeCun, Y., Y. Bengio, and G. Hinton, Deep learning. Nature 2015. 521: p. 436-444
27. Basu, S., et al., Deep neural networks for texture classification—A theoretical analysis. Neural Networks, 2018. 97: p. 173-182.
28. Xavier, G. and B. Yoshua, Understanding the difficulty of training deep feedforward neural networks. 2010, PMLR. p. 249-256.
29. Chen, X.W. and X. Lin, Big Data Deep Learning: Challenges and Perspectives. IEEE Access, 2014. 2: p. 514-525.
30. Najafabadi, M.M., et al., Deep learning applications and challenges in big data analytics. Journal of Big Data, 2015. 2(1): p. 1.
31. UCI. 2018 [cited 10.03.2018; Available from: https://archive.ics.uci.edu/ml/datasets/seeds.
32. Charytanowicz, M., et al., A Complete Gradient Clustering Algorithm for Features Analysis of X-ray Images. Information Technologies in Biomedicine, 2010: p. 15-24.
33. Torrecilla, J.L. and J. Romo, Data learning from big data. Statistics and Probability Letters, (Article In Press), 2018.
34. Jan, B., et al., Deep learning in big data Analytics: A comparative study. Computers & Electrical Engineering, 2017.
35. Bezdek, J.C., R. Ehrlich, and W. Full, FCM: The fuzzy c-means clustering algorithm. Computers & Geosciences, 1984. 10(2): p. 191-203.
36. Liew, S.S., M. Khalil-Hani, and R. Bakhteri, Bounded activation functions for enhanced training stability of deep neural networks on visual pattern recognition problems. Neurocomputing, 2016. 216: p. 718-734.
37. Eldem, A., H. Eldem, and D. Üstün. A Model of Deep Neural Network for Iris Classification With Different Activation Functions. in 2018 International Conference on Artificial Intelligence and Data Processing (IDAP). 2018.
38. Chen, L., et al., Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction. Information Sciences, 2018. 428: p. 49-61.