APPLICATION OF AUTOMATED MACHINE LEARNING AND BAGGING TECHNIQUES TO CLASSIFY RICE VARIETIES

Abstract

We have witnessed increased research investigating digitalisation in the agricultural sector in recent years. In particular, machine learning and artificial intelligence find applications in agricultural product classification, quality control and species identification. The fast-processing times, high accuracy levels and cost-effectiveness offered by digital solutions for quality control and classification accelerate these studies. This study proposes a collaborative learning model utilising Automated Machine Learning and Bagging techniques for rice species detection and classification. The model uses a dataset from the UCI Irvine Machine Learning Repository, which contains characteristics specific to the Osmancık and Cammeo rice varieties grown in Turkey. The data set consists of 3810 data points, 2180 of which belong to Osmancık rice and 1630 to Cammeo rice. During the analysis, MLBox, an Automated Machine Learning library, was used to determine the optimal algorithm (Light Gradient Boosting Machine - LGBM) and its hyperparameters. Later, by applying the Bagging technique within the developed learning model, an accuracy rate of 93.54% was achieved in rice-type classification.

Keywords

• Rice Types
• Machine Learning
• AutoML
• Bagging
• Classification

References

1. R. Alamyar, I. Boz, Marketing problems encountered by rice producers and their solutions: A case study of takhar-afghanistan, ISPEC Journal of Agricultural Sciences 5 (2) (2021) 381–392. doi:10.46291/ ISPECJASVOL5ISS2PP381-392.
2. E. Veziroglu, I. Pacal, A. Coskuncay, Derin evrişimli sinir ağları kullanılarak pirinç hastalıklarının sınıflandırılması, Journal of the Institute of Science and Technology 13 (2) (2023) 792–814. doi:10.21597/JIST.1265769. URL https://dergipark.org.tr/en/pub/jist/issue/77307/126576
3. Food and Agriculture Organization of the United Nations, FAOSTAT dataset, accessed: 2021 (2021). URL https://www.fao.org/faostat/en/#data
4. Z. C . Mutafcilar, Türkiye’de tescilli çeltik çeşitlerinin moleküler karakterizasyonu, Ph.d. thesis, Trakya University, (2018).
5. M. Koklu, I. Cinar, Y. S. Taspinar, Classification of rice varieties with deep learning methods, Computers and Electronics in Agriculture 187 (2021) 106285. doi:10.1016/j.compag.2021.106285.
6. D. I. Patricio, R. Rieder, Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review, Computers and Electronics in Agriculture 153 (2018) 69–81. doi:10.1016/j.compag.2018.08.001.
7. I. Cinar, M. Koklu, Classification of rice varieties using artificial intelligence methods, International Journal of Intelligent Systems and Applications in Engineering 7 (3) (2019) 188–194. doi:10.18201/IJISAE.2019355381.
8. U. Ilhan, A. Ilhan, K. Uyar, E. I. Iseri, Classification of osmancik and cammeo rice varieties using deep neural networks, in: ISMSIT 2021 - 5th International Symposium on Multidisciplinary Studies and Innovative Tech- nologies, Proceedings, Institute of Electrical and Electronics Engineers Inc., Ankara, Turkey, 2021, pp. 587–590. doi:10.1109/ISMSIT52890.2021.9604606.

9. B. Jin, C. Zhang, L. Jia, Q. Tang, L. Gao, G. Zhao, H. Qi, Identification of rice seed varieties based on near-infrared hyperspectral imaging technology combined with deep learning, ACS Omega 7 (6) (2022) 4735–4749. doi:10.1021/ acsomega.1c04102.
10. D. Jaithavil, S. Triamlumlerd, M. Pracha, Paddy seed variety classification using transfer learning based on deep learning, in: Proceedings of the 2022 International Electrical Engineering Congress, iEECON 2022, Institute of Electrical and Electronics Engineers Inc., Khon Kaen, Thailand, 2022, pp. 1–4. doi:10.1109/IEECON53204.2022.9741677.
11. J. Jumi, A. Zaenuddin, T. Mulyono, Identification of rice types based on shape, color and texture using k-nearest neigh- bors method as classifier, International Journal of Engineering Research Technology 9 (12) (2020). doi:10.17577/ IJERTV9IS120013.
12. V. T. Hoang, D. P. Van Hoai, T. Surinwarangkoon, H. T. Duong, K. Meethongjan, A comparative study of rice vari- ety classification based on deep learning and hand-crafted features, ECTI Transactions on Computer and Information Technology (ECTI-CIT) 14 (1) (2020) 1–10. doi:10.37936/ECTI-CIT.2020141.204170.
13. M. S. Mrutyunjaya, K. S. Harish Kumar, Non-destructive machine vision system based rice classification using ensem- ble machine learning algorithms, Recent Advances in Electrical Electronic Engineering (Formerly Recent Patents on Electrical Electronic Engineering) 16 (jul 2023). doi:10.2174/2352096516666230710144614.
14. I. Cinar, M. Koklu, Rice (cammeo and osmancik) (2019). doi:10.24432/C5MW4Z.
15. C. El Morr, M. Jammal, H. Ali-Hassan, W. El-Hallak, Data preprocessing, Springer International Publishing, Cham, 2022, pp. 117–163. doi:10.1007/978-3-031-16990-8_4.
16. V. Kovalevsky, E. Stankova, N. Zhukova, O. Ogiy, A. Tristanov, Automl framework for labor potential modeling, in: Advances in Intelligent Systems and Computing, Vol. 13957, Springer, Cham, 2023, pp. 87–98. doi:10.1007/ 978-3-031-36808-0_6.
17. Y. Sun, Q. Song, X. Gui, F. Ma, T. Wang, Automl in the wild: Obstacles, workarounds, and expectations, in: Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, Hamburg, Germany, 2023, pp. 1–15. doi:10.1145/3544548.3581082.
18. C. Wang, Z. Chen, M. Zhou, Automl from software engineering perspective: Landscapes and challenges, in: Proceedings - 2023 IEEE/ACM 20th International Conference on Mining Software Repositories, MSR 2023, IEEE Inc., Melbourne, Australia, 2023, pp. 39–51. doi:10.1109/MSR59073.2023.00019.
19. M. Vin´ıcius, C. Araga˜o, A. Guimara˜es Afonso, R. C. Ferraz, R. Gonca¸lves Ferreira, S. Gomes Leite, R. G. Ferreira, A practical evaluation of automl tools for binary, multiclass, and multilabel classification, TechRxiv (oct 2023). doi: 10.36227/TECHRXIV.21792959.V1.
20. S. Das, U. M. Cakmak, Hands-On Automated Machine Learning: A Beginner’s Guide to Building Automated Machine Learning Systems Using AutoML and Python, Packt Publishing, Birmingham, UK, 2018.
21. A. Aronio De Romblay, N. Cherel, M. Maskani, H. Gerard, Mlbox (2017).
22. S. Ozdemir, S. Orslu, Makine Öğrenmesinde Yeni Bir Bakış Açısı: Otomatik Makine Öğrenmesi (AutoML), Journal of Information Systems and Management Research 1 (1) (2019) 23–30.