Evaluating the Impact of Data Normalization on Rice Classification Using Machine Learning Algorithms

Rice is a staple food for a significant portion of the global population, particularly in countries where it constitutes the primary source of sustenance.Accurate classification of rice varieties is critical for enhancing both agricultural yield and economic outcomes.Traditional classification methods are often inefficient, leading to increased costs, higher misclassification rates, and time loss.To address these limitations, automated classification systems employing machine learning (ML) algorithms have gained attention.However, when raw data is inadequately organized or scattered, classification accuracy can decline.To improve data organization, normalization processes are often employed.Despite its widespread use, the specific contribution of normalization to classification performance requires further validation.In this study, a dataset comprising two rice varieties Osmancik and Cammeo produced in Turkey was utilized to evaluate the impact of normalization on classification outcomes.The k-Nearest Neighbor (KNN) algorithm was applied to both normalized and non-normalized datasets, and their respective performances were compared across various training and testing ratios.The normalized dataset achieved a classification accuracy of 0.950, compared to 0.921 for the non-normalized dataset.This approximately 3% improvement demonstrates the positive effect of data normalization on classification accuracy.These findings underscore the importance of incorporating normalization in ML models for rice classification to optimize performance and accuracy.