Application of Artificial Intelligence in the authentication of Essential Oils

Essential oils are concentrated aromatic liquids which are extracted from different plant parts. They find application in food and beverage industry, perfumery and cosmetics, pharmaceutical industry and in aromatherapy. Scarce production, labour-intensive extraction process, limited yields and specialized applications in perfume industry make them products of high economic value. This makes them prone to adulteration with unwanted substances, primarily for monetary gain. The National and International authorities recognise Gas Chromatography-Mass Spectrometry and Gas Chromatography-Flame Ionization Detection as the standard method for authenticating essential oils. But the above instrumentations have an inherent disadvantage of inability to identify adulterants of non-volatile nature. The ongoing study proposes leveraging the strength of the state-of-the art optical spectroscopic techniques and Artificial Intelligence algorithms to provide a reliable authentication framework for authenticating essential oils. The talk focuses on the study of Mentha arvensis and Cymbopogon citratus essential oils, acquiring their fingerprint information using Fourier Transform Infrared spectroscopy and Raman spectroscopy, application of some classical Machine learning algorithms, followed by future perspectives of research.