Intelligent Acidity Estimation in Olive Oil Using an Electronic Nose and Artificial Intelligence

Quality control of olive oil is important not only to maintain the product value but also to ensure consumer confidence, since the processes of oxidation and rancidity directly affect its chemical properties and also lead to a degradation of its quality. The standard chemical analysis methods are often expensive, time-consuming, and require laboratory equipment and trained personnel, which limits their use for rapid and on-site assessment. This study proposes a smart approach based on an electronic nose and artificial intelligence techniques for detecting oxidation and estimating the acidity of olive oil. The developed system uses MOS gas sensors, specifically the Grove Multichannel Gas Sensor and the Bosch BME688, to analyze the volatile organic compounds generated during the degradation and rancidity processes of the oil. The data acquired from the different sample classes were analyzed using machine learning techniques to classify the freshness status and estimate the level of deterioration in the analyzed oils. The experimental results show that the obtained olfactory signatures exhibit an interesting correlation with oxidation processes and changes in oil quality. The developed models demonstrated promising performance in distinguishing oils with different quality levels. This approach offers a fast, portable, and less expensive solution than conventional chemical analysis methods for the intelligent monitoring of olive oil quality.