Applications of artificial intelligence in analyzing Aquilaria essential oils: a review of current machine learning techniques

Abstract

This study explores the application of machine learning (ML) techniques in the classification of agarwood oil, focusing on the use of various algorithms such as k-nearest neighbors (KNN), support vector machines (SVM), random forest (RF), and artificial neural networks (ANN). Since 2013, ML has played a pivotal role in analyzing agarwood oil, particularly by leveraging data from a variety of chemical compounds found in the Aquilaria genus. Through a systematic review and bibliometric analysis using the SCOPUS database, this study compiles and highlights recent works that have successfully employed ML techniques for the quality assessment of agarwood oil. These studies utilize chemical data, such as gas chromatography-mass spectrometry (GC-MS) and nuclear magnetic resonance (NMR), for the classification and detection of different oil grades. The review reveals a broad range of ML applications, demonstrating their growing importance in the field of essential oil analysis. By systematically presenting the findings from recent research, this work emphasizes the potential for further exploration of ML in the standardization and improvement of agarwood oil classification techniques.