Formulation of K-Nearest Neighbor Model by Varying the Distance Metrics of Mahalanobis, Correlation and Cosine in Discriminating Different Grades of Aquilaria Oil

This article delves into the development and refinement of a K-Nearest Neighbor (K-NN) model for discriminating different grades of Aquilaria oil. The background highlights the significance of Aquilaria oil, a prized essential oil derived from Aquilaria trees, known for its diverse applications in perfumery and traditional medicine. With varying grades of Aquilaria oil available, the need for an effective model to discern these grades becomes imperative for quality control and market competitiveness. Traditional classification methods may fall short in capturing the intricacies of the oil's composition, prompting the exploration of advanced machine learning techniques. The methodology section outlines the approach taken to formulate the K-NN model, with a specific focus on the variation of distance metrics—Mahalanobis, Correlation, and Cosine. The utilization of these metrics aims to enhance the model's ability to discriminate between oil grades based on their distinct chemical profiles. The article discusses the data collection process, feature selection, and the parameters considered in implementing the K-NN algorithm. The experimentation with diverse distance metrics is anticipated to reveal nuances in classification that were previously unexplored. Insights gained from this study could potentially revolutionize the classification of essential oils, providing a robust framework for quality assessment.