Extracting physicochemical properties from fluorescence spectra using one-dimensional convolutional neural networks: Application to the olive oil industry has had a significant impact on the economy and lifestyle of the Mediterranean region. Many studies

Extract physicochemical properties from fluorescence spectra using one-dimensional convolutional neural networks: applied to olive oil

The olive oil industry has had a significant impact on the economy and lifestyle of the Mediterranean region. Many studies have attempted to optimize the different steps in the olive oil production process. One of the main challenges faced by olive oil producers is the ability to assess and control quality during the production cycle. To do this, several parameters need to be determined, such as acidity, UV absorption or ethyl ester content. To achieve this, samples must be sent to an accredited laboratory for chemical analysis. This method is expensive and cannot be performed very often, making quality control of olive oil a real challenge. This work explores a new method based on fluorescence spectroscopy and artificial intelligence (i.e., one-dimensional convolutional neural networks) to predict five chemical mass indicators of olive oil (acidity, peroxide value, UV spectroscopy parameters $K_{270}$ and $K_{232}$ and ethyl ester) from a simple fluorescence spectrum. Fluorescence spectroscopy is a very attractive optical technique because it does not require sample preparation, is non-destructive, and, as shown in this work, can be easily implemented in small and cost-effective sensors. The results of the study show that the proposed method gives special results in terms of quality determination and will make continuous quality control of olive oil during and after production a reality. In addition, this new method has the potential to serve as a support for the quality specifications of olive oil specified in European regulations.

《Physico-chemical properties extraction from the fluorescence spectrum with 1D-convolutional neural networks: application to olive oil》

Thesis Address: Web link