Virtual Booth

This study addresses the subjectivity inherent in conventional evaluation methods of Aquilaria species by introducing a machine learning approach for species classification. Relying on human perception as a starting point, the study utilises the analysis of chemical compounds in agarwood oil to classify samples. Six significant compounds are examined for classification, namely beta-selinene, dihyro-beta-agarofuran, delta-guaiene, 10-epi-gamma-eudesmol, gamma-eudesmol, and pentadecanoic acid. Employing the K-Nearest Neighbours (K-NN) algorithm, it accurately identifies Aquilaria beccariana, Aquilaria malaccensis, Aquilaria crassna, and Aquilaria subintegra. Results demonstrate the effectiveness of this objective approach, paving the way for precise species classification in Aquilaria oil studies.