2021/04/09 by Francesca Venturini, Venturini, Francesca, Michela Sperti +13
Chemistry · Engineering · #Advanced Chemical Sensor Technologies #Artificial Intelligence (cs.AI) #Edible Oils Quality and Analysis #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Signal Processing (eess.SP) #Spectroscopy and Chemometric Analyses #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2104.06310
openalex publication_date 2021/04/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Extra virgin olive oil (EVOO) is the highest quality of olive oil and is\ncharacterized by highly beneficial nutritional properties. The large increase\nin both consumption and fraud, for example through adulteration, creates new\nchallenges and an increasing demand for developing new quality assessment\nmethodologies that are easier and cheaper to perform. As of today, the\ndetermination of olive oil quality is performed by producers through chemical\nanalysis and organoleptic evaluation. The chemical analysis requires the\nadvanced equipment and chemical knowledge of certified laboratories, and has\ntherefore a limited accessibility. In this work a minimalist, portable and\nlow-cost sensor is presented, which can perform olive oil quality assessment\nusing fluorescence spectroscopy. The potential of the proposed technology is\nexplored by analyzing several olive oils of different quality levels, EVOO,\nvirgin olive oil (VOO), and lampante olive oil (LOO). The spectral data were\nanalyzed using a large number of machine learning methods, including artificial\nneural networks. The analysis performed in this work demonstrates the\npossibility of performing classification of olive oil in the three mentioned\nclasses with an accuracy of 100 %. These results confirm that this minimalist\nlow-cost sensor has the potential of substituting expensive and complex\nchemical analysis.\n