ABSTRACT
This research introduces a precise Rice Type Classification model employing the Radial Basis Function (RBF) Kernel Support Vector Machine (SVM). With an accuracy of 92.85%, log loss of 2.57, and an F1 score of 93.77, our model excels in capturing intricate rice type patterns. By harnessing the discriminative power of the RBF kernel, our approach offers an efficient solution for differentiating rice types based on essential features. Accurate rice classification is crucial for agricultural applications, aiding in breeding programs, crop management, and quality evaluation. Traditional methods often struggle with accuracy and scalability, especially when dealing with diverse datasets. To address these limitations, we propose a novel approach utilizing RBF Kernel SVM. Our methodology involves training an SVM model with an RBF kernel on a comprehensive dataset comprising various rice types and essential features such as grain size, length-width ratio, and color intensity. The exceptional performance of our model can be attributed to the RBF kernel's capability to capture complex patterns and relationships in the data. By leveraging its flexibility and nonlinearity, our model excels in accurately classifying rice types, offering a practical solution for automated classification tasks. This paper presents a precise Rice Type Classification model utilizing RBF Kernel SVM, contributing to advancing agricultural science, facilitating improved crop management practices, and bolstering global food security efforts.
