Date Received: 26-09-2025
Date Accepted: 05-05-2026
Date Published: 25-06-2026
##submissions.doi##: https://doi.org/10.31817/tckhnnvn.2026.24.6.08
Views
Downloads
How to Cite:
Classification of Brown Rice Samples using Machine Learning Method
Keywords
Black brown rice, red brown rice, machine learning
Abstract
Brown Rice is whole grain high in fiber, antioxidants, and many important vitamins and minerals. This product is suitable for people who on a diet or those with medical conditions such as diabetes type 2, high blood pressure, obesity, risk of heart stroke or high cholesterol. This study aimed to classify black brown and red brown rice based on the morphological characteristics. Images of brown rice samples were pre-processed to separate each separately, accompanied by corresponding image mask using the SAM. Each of these seeds was further analyzed to extract important morphological information related to the geometric structure including 19 independent features. These features were analyzed using machine learning models: decision tree (DT), random forest (RF) and support véc tơ machine (SVM). The results show that all three algorithms resulted highly accurate results, especially SVM, with an accuracy of 76%. The SVM model also outperformed the DT and RF models with Recall and F1-Score indexes reaching 83% and 80.2%, respectively, for the black brown rice sample. However, these indexes for the red brown sample were only below 70% due to the overlapping nature of the attributes in the feature space.
References
Alexander K., Eric M., Nikhila R., Hanzi M., Chloe R., Laura G., Tete X., Spencer W., Alexander C. B., Wan Y.L., Piotr D. & Ross G. (2023). Segment anything. IEEE/CVF International Conference on Computer Vision (ICCV). pp. 3992-4003. Berrar D. (2018). Cross-Validation. Reference Module in Life Sciences. doi:10.1016/b978-0-12-809633-8.20349-x Benesty J., Chen J., Huang Y. & Cohen I. (2009). Pearson correlation coefficient. In Noise reduction in speech processing. Springer. pp. 37-40. Breiman L. (2001). Random Forests. Machine Learning. 45: 5-32. https://doi.org/10.1023/A: 1010933404324 Cinar I. & Koklu M. (2019). Classification of rice varieties using artificial intelligence methods. Internaional Jounal of Intelligent Systems and Applications in Engineering. ISSN: 2147-6799. Cortes C. & Vapnik V. (1995). Support-Vector Networks. Machine Learning. 20: 273-297. http://dx.doi.org/10.1007/BF00994018. Jeremy F., Alex H. & Derek T. (2021). PyLabel. Retrieved from https://github.com/pylabel-project/pylabel on Jun 15, 2024. Kim T.H., Kim E.K., Lee M.S., Lee H.K., Hwang W.S., Choe S.J., Kim T.Y., Han S.J., Kim H.J., Kim D.J. & Lee K.W. (2011). Intake of brown rice lees reduces waist circumference and improves metabolic parameters in type 2 diabetes. Nutr. Res. 31(2): 131-138. https:// doi.org/10.1016/ j.nutres.2011.01.010
Nguyễn Thị Lang, Lê Hoàng Phương, Bùi Chí Hiếu, Nguyễn Trọng Phước & Bùi Chí Bửu (2021). Phân tích chất lượng của giống lúa mùa AG3 tại An Giang. Tạp chí Nông nghiệp và Phát triển nông thôn. 11: 3-9. Quinlan J.R. (1985). Induciton of Decision Trees. Machine Learning. 1: 81-106. Tập đoàn Giống cây trồng Việt Nam (Vinaseed). Gạo lứt Phúc Thọ. Truy cập từ https://vinaseed.com.vn/vi/ product/m7/gao-lut-phuc-tho-den-63.htm ngày 02/07/2024. Tianqi C. & Carlos G. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. pp. 785-794. https://doi.org/10.1145/2939672.293978
Trần Thị Thanh Thúy, Nguyễn Tấn & Võ Công Thành (2021). Nghiên cứu phục tráng giống lúa thơm đặc sản VD20 phục vụ cho xuất khẩu tại đồng bằng sông Cửu Long. Tạp chí Khoa học và Công nghệ Nông nghiệp Việt Nam. 4(125).
Vũ Mạnh Ẩn, Hoàng Ngọc Đỉnh, Trần Hiền Linh, Phạm Xuân Hội & Hoàng Thị Giang (2023). Đánh giá một số chỉ tiêu chất lượng gạo của các giống lúa địa phương. Tạp chí Khoa học và Công nghệ Nông nghiệp Việt Nam (ISSN1859-1558). 2(144).