Makine Öğrenimi ve Derin Öğrenme Metotları Kullanılarak Hurma Meyvesi Türü Tespiti

Öz

Meyve ve sebze görüntülerinin analizi endüstriyel tarımda tanımlama ve sınıflandırma süreçlerinde önemli bir rol oynamaktadır. Hızla artan insan nüfusu ve bu doğrultuda yükselen tüketim miktarı analiz ve sınıflandırma işlemlerini otomatikleştirmeyi mecbur kılmaktadır. Geleneksel olarak uzmanlar tarafından yapılan görsel inceleme ve yorumlama yöntemleriyle gerçekleştirilen bu analiz süreci zaman alıcı ve öznel olabilir. Ancak son yıllarda derin öğrenme tekniklerinin gelişimi meyve ve sebze görüntülerinin otomatik analizinde büyük bir potansiyel sunmaktadır. Bu çalışmada klasik makine öğrenimi ve derin öğrenme modellerinin hurma meyvesinin türlerine ayrılması için nasıl kullanılabileceği incelenmektedir. Lojistik Regresyon, GaussianNB, KNN, SVM ve Random Forest gibi yaygın olarak kullanılan makine öğrenimi modelleri ile Evrişimli Sinir Ağları (ESA) temeline dayanan CNN, RNN ve ANN gibi derin öğrenme modelleri kullanılarak, hurma meyvesine ait görüntü tabanlı olmayıp morfolojik özelliklerden oluşan sayısal bir veri seti üzerinde eğitimler ve testler yapılmıştır. Ayrıca deneysel bir çalışma gerçekleştirilerek bu farklı makine öğrenimi ve derin öğrenme modellerinin performansı karşılaştırılmıştır. Yapılan testlere göre en yüksek %92.44 doğruluk oranı RNN modeli ile elde edilmiştir. Sonuç olarak makine öğrenimi ve derin öğrenme tabanlı modellerin meyve görüntülerinin analizi alanında önemli bir potansiyele sahip olduğu görülmektedir. Bu teknikler sınıflandırma aşamasında yüksek doğruluk ile süreçlere hız kazandırarak endüstriyel tarımın gelişimine katkı sağlayabilir.

Anahtar Kelimeler

• Meyve görüntüleri analizi
• Makine Öğrenimi
• ESA

Date Palm Fruit Type Detection Using Machine Learning and Deep Learning Methods

Öz

The analysis of fruit and vegetable images plays a crucial role in the detection and classification processes in industrial agriculture. The rapidly growing global population, coupled with the subsequent rise in consumption, necessitates the automation of these processes. This analysis process, traditionally carried out by experts through visual inspection and interpretation, can be subjective and time-consuming. However, the development of deep learning techniques in recent years offers great potential in the automatic analysis of fruit and vegetable images. In this study, we investigate how classical machine learning and deep learning models can be used to classify date palm fruit into species. Using widely used machine learning models such as Logistic Regression, GaussianNB, KNN, SVM and Random Forest, and deep learning models such as CNN, RNN and ANN based on Convolutional Neural Networks (CNN), training and testing were performed on a numerical dataset consisting of non-image based morphological features of date palm fruit. An experimental study was also conducted to compare the performance of these different machine learning and deep learning models. According to the tests, the highest accuracy rate of 92.44% was obtained with the RNN model. In conclusion, machine learning and deep learning-based models have significant potential in the field of fruit image analysis. These techniques can contribute to the development of industrial agriculture by accelerating the processes with high accuracy in the classification phase.

Anahtar Kelimeler

• Digital analysis of fruit images
• Machine learning
• CNN

Kaynakça

1. Abdullah, S. K., Lorca, L., & Jansson, H. (2010). Diseases of date palms (Phoenix dactylifera L.). Basrah Journal for Date Palm Researches, 9(2), 1-44.
2. Allbed, A., Kumar, L., & Shabani, F. (2017). Climate change impacts on date palm cultivation in Saudi Arabia. The Journal of Agricultural Science, 155(8), 1203-1218.
3. Alsirhani, A., Siddiqi, M. H., Mostafa, A. M., Ezz, M., & Mahmoud, A. A. (2023). A novel classification model of date fruit dataset using deep transfer learning. Electronics, 12(3), 665.
4. Amaya-Tejera, N., Gamarra, M., Vélez, J. I., & Zurek, E. (2024). A distance-based kernel for classification via Support Vector Machines. Frontiers in Artificial Intelligence, 7, 1287875.
5. Bargoti, S., & Underwood, J. (2017, May). Deep fruit detection in orchards. In 2017 IEEE international conference on robotics and automation (ICRA) (pp. 3626-3633). IEEE.
6. Bishop, C. M. (2006). Pattern recognition and machine learning. Springer google schola, 2, 645-678.
7. Bozkurt, F. (2022). A comparative study on classifying human activities using classical machine and deep learning methods. Arabian Journal for Science and Engineering, 47(2), 1507-1521.
8. Burges, C. J. (1998). A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery, 2(2), 121-167.

9. Büyükarıkan, B., & Ülker, E. (2020). Aydınlatma özniteliği kullanılarak evrişimsel sinir ağı modelleri ile meyve sınıflandırma. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 25(1), 81-100.
10. Çelik, E., Dal, D., & Aydin, T. (2021). Duygu Analizi İçin Veri Madenciliği Sınıflandırma Algoritmalarının Karşılaştırılması. Avrupa Bilim ve Teknoloji Dergisi, (27), 880-889.
11. Date Fruit Datasets. (2021). Erişim adresi: https://www.kaggle.com/datasets/muratkokludataset/date- fruit-datasets/data (Erişim adresi: 3 Mayıs, 2024)
12. Eberhart, R., & Kennedy, J. (1995, October). A new optimizer using particle swarm theory. In MHS'95. Proceedings of the sixth international symposium on micro machine and human science (pp. 39- 43). Ieee.
13. Elleuch, M., Besbes, S., Roiseux, O., Blecker, C., Deroanne, C., Drira, N. E., & Attia, H. (2008). Date flesh: Chemical composition and characteristics of the dietary fibre. Food chemistry, 111(3), 676- 682.
14. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. nature, 542(7639), 115-118.
15. Gazalba, I., & Reza, N. G. I. (2017, November). Comparative analysis of k-nearest neighbor and modified k-nearest neighbor algorithm for data classification. In 2017 2nd international conferences on information technology, information systems and electrical engineering (ICITISEE) (pp. 294-298). IEEE.
16. Godfray, H. C. J., Beddington, J. R., Crute, I. R., Haddad, L., Lawrence, D., Muir, J. F., ... & Toulmin, C. (2010). Food security: the challenge of feeding 9 billion people. science, 327(5967), 812-818.
17. Gulzar, Y., Hamid, Y., Mehmood, A., & Soomro, A. B. (2022). A Deep Learning-Based Model for Date Fruit Classification: Sustainability (Switzerland). Sustainability, 14(10).
18. Hasan, M. S., & Sattar, A. (2021, February). Arabian date classification using CNN algorithm with various pre-trained models. In 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV) (pp. 1431-1436). IEEE.
19. Haykin, S. (2009). Neural networks and learning machines, 3/E. Pearson Education India.
20. Holmes, W. (2019). Artificial intelligence in education: Promises and implications for teaching and learning. Center for Curriculum Redesign.
21. Jordan, M. I., & Mitchell, T. M. (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245), 255-260.
22. Joseph, J. L., Kumar, V. A., & Mathew, S. P. (2021). Fruit classification using deep learning. In Innovations in Electrical and Electronic Engineering: Proceedings of ICEEE 2021 (pp. 807- 817). Springer Singapore.
23. Kaftan, İ. (2010). Batı Türkiye gravite ve deprem katalog verilerinin yapay sinir ağları ile değerlendirilmesi (Tez No. 276504) [Doktora tezi, Dokuz Eylül Üniversitesi-İzmir]. Yükseköğretim Kurulu Ulusal Tez Merkezi.
24. Kamilaris, A., & Prenafeta-Boldú, F. X. (2018). Deep learning in agriculture: A survey. Computers and electronics in agriculture, 147, 70-90.
25. Koklu, M., Kursun, R., Taspinar, Y. S., & Cinar, I. (2021). Classification of date fruits into genetic varieties using image analysis. Mathematical Problems in Engineering, 2021, 1-13.
26. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
27. Kunduracioglu, I. (2024). CNN models approaches for robust classification of apple diseases. Computer and Decision Making: An International Journal, 1, 235-251.
28. Kunduracioglu, I., & Pacal, I. (2024). Advancements in deep learning for accurate classification of grape leaves and diagnosis of grape diseases. Journal of Plant Diseases and Protection, 131(3), 1061- 1080.
29. Kursa, M. B., & Rudnicki, W. R. (2010). Feature selection with the Boruta package. Journal of statistical software, 36, 1-13.
30. LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989). Backpropagation applied to handwritten zip code recognition. Neural computation, 1(4), 541-551.
31. LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278-2324.
32. Lin, Y., & Jeon, Y. (2006). Random forests and adaptive nearest neighbors. Journal of the American Statistical Association, 101(474), 578-590.
33. McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5, 115-133.
34. Mikołajczyk, A., & Grochowski, M. (2018, May). Data augmentation for improving deep learning in image classification problem. In 2018 international interdisciplinary PhD workshop (IIPhDW) (pp. 117-122). IEEE.
35. Mitchell, T. M. (1997). Machine learning (Vol. 1, No. 9). New York: McGraw-hill.
36. Nasiri, A., Taheri-Garavand, A., & Zhang, Y. D. (2019). Image-based deep learning automated sorting of date fruit. Postharvest biology and technology, 153, 133-141.
37. Nishimura, J., & Shimasaki, S. (2017). Combining the complex Langevin method and the generalized Lefschetz-thimble method. Journal of High Energy Physics, 2017(6), 1-16.
38. Pacal, I., Kunduracioglu, I., Alma, M. H., Deveci, M., Kadry, S., Nedoma, J., ... & Martinek, R. (2024). A systematic review of deep learning techniques for plant diseases. Artificial Intelligence Review, 57(11), 304.
39. Paçal, İ., & Kunduracıoğlu, İ. (2024). Data-efficient vision transformer models for robust classification of sugarcane. Journal of Soft Computing and Decision Analytics, 2(1), 258-271.
40. Pan, Z., Rust, A. G., & Bolouri, H. (2000, July). Image redundancy reduction for neural network classification using discrete cosine transforms. In Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium (Vol. 3, pp. 149-154). IEEE.
41. Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... & Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
42. Picon, A., Alvarez-Gila, A., Seitz, M., Ortiz-Barredo, A., Echazarra, J., & Johannes, A. (2019). Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild. Computers and Electronics in Agriculture, 161, 280-290.
43. Ranjana, R., Narendra Kumar Rao, B., Raja, J., Panini Challa, N., & Madhavi, K. R. (2023). Machine learning and computer vision-beyond modeling, training, and algorithms. Institution of Engineering and Technology (pp. 293-307).
44. Ryman-Tubb, N. F., Krause, P., & Garn, W. (2018). How Artificial Intelligence and machine learning research impacts payment card fraud detection: A survey and industry benchmark. Engineering Applications of Artificial Intelligence, 76, 130-157
45. Sağ, R., & Tuğcu, Z. H. (2022). Akıllı Şebeke Uygulamalarında Derin Öğrenme Tekniklerinin Kullanımına İlişkin Kısa Bir İnceleme. EMO Bilimsel Dergi, 13(1), 41-61.
46. Savary, S., Willocquet, L., Pethybridge, S. J., Esker, P., McRoberts, N., & Nelson, A. (2019). The global burden of pathogens and pests on major food crops. Nature ecology & evolution, 3(3), 430-439.
47. Selçuk, F., & Gülümser, A. A. (2023). İKLİM DEĞİŞİKLİĞİ ETKİSİNDE TÜRKİYE’DE TARIMSAL ÜRÜN VERİMLİLİĞİ: BÖLGESEL BİR DEĞERLENDİRME. Bölgesel Kalkınma Dergisi, 1(04), 425-451.
48. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1-9).
49. Şeker, A., Diri, B., & Balık, H. H. (2017). Derin öğrenme yöntemleri ve uygulamaları hakkında bir inceleme. Gazi Mühendislik Bilimleri Dergisi, 3(3), 47-64.
50. Uğuz, S. (2019). Makine öğrenmesi teorik yönleri ve Python uygulamaları ile bir yapay zekâ ekolü. Nobel Yayıncılık. Ankara.
51. Van Zonneveld, M., Volk, G. M., Dulloo, M. E., Kindt, R., Mayes, S., Quintero, M., ... & Guarino, L. (2023). Safeguarding and using fruit and vegetable biodiversity. In Science and Innovations for Food Systems Transformation (pp. 553-567). Cham: Springer International Publishing.
52. Vapnik, V. (2013). The nature of statistical learning theory. Springer science & business media.
53. Yasrab, R., Zhang, J., Smyth, P., & Pound, M. P. (2021). Predicting plant growth from time-series data using deep learning. Remote Sensing, 13(3), 331.
54. Zeiler, M. D., & Fergus, R. (2013). Stochastic pooling for regularization of deep convolutional neural networks. arXiv preprint arXiv:1301.3557.
55. Zhang, Y. D., Dong, Z., Chen, X., Jia, W., Du, S., Muhammad, K., & Wang, S. H. (2019). Image based fruit category classification by 13-layer deep convolutional neural network and data augmentation. Multimedia Tools and Applications, 78, 3613-3632.