The paper examines the characterization of Aquilaria essential oils from different species, namely Aquilaria malaccensis, Aquilaria beccariana, Aquilaria crassna, and Aquilaria subintegra, renowned for agarwood production in Malaysia. Gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detector (GC-FID) were employed for extracting essential oil data, facilitating compound identification. Subsequently, a preliminary analysis focused on classifying significant chemical compounds in the samples. The study then utilized boxplot pre-processing for visualizing and interpreting data distribution. The statistical analyses were performed using MATLAB software version R2021b, considering two key parameters which are the peak area (%) of significant chemical compounds and the classification of Aquilaria species (A. beccariana, A. malaccensis, A. crassna, and A. subintegra) based on their chemical composition. The results, presented through boxplot analyses, demonstrated a clear representation of the parameters and their distribution in the data. This method not only confirmed the potential of boxplot analysis in statistical evaluation of significant compounds in Aquilaria essential oil but also suggested its applicability for further classification work.

Accurate classification of Aquilaria oil species is essential for ensuring the quality and authenticity of agarwood oils, which are widely used in perfumes and traditional medicine. This study investigated the effectiveness of the k-nearest neighbours (k-NN) machine learning model for classifying Aquilaria oil species based on four significant chemical compounds: dihyro-βagarofuran, δ-guaiene, 10-epi-γ-eudesmol, and γ-eudesmol. The dataset comprised 480 samples of Aquilaria oil, which were analyzed using gas chromatography-mass spectrometry (GC-MS) and gas chromatography-flame ionization detector (GC-FID). The k-NN model, with an optimal k-value of 10 and using euclidean distance as the distance metric, achieved 100% accuracy, sensitivity, specificity, and precision in both training and testing datasets. These results demonstrate the robustness of k-NN in species identification, highlighting the discriminative power of the selected compounds. This study verifies that the integration of chemical profiling with machine learning offers a scalable solution for accurate species identification in the essential oil industry. Future work could explore hybrid models and data expansion techniques to further enhance the classification performance in more complex environmental conditions.