The safeguarding of extra virgin olive oil (EVOO) quality throughout its shelf life is imperative due to its vulnerability to quality deterioration caused by auto-oxidation and photo-oxidation. This study investigates machine learning (ML) capabilities applied to fluorescence spectroscopy to detect the ageing of EVOO. The quality of EVOO was assessed by UV-absorption spectroscopy measurements as mandated by European Regulations. In parallel, excitation-emission matrices (EEMs) were measured to determine the predictive potential of ML approaches applied to fluorescence data. First, two excitation wavelengths (480 nm and 300 nm) are identified as exhibiting the maximum relative change in fluorescence intensity, serving as potential indicators of EVOO ageing. Then, ML algorithms were developed to predict olive oil quality based on highly aggregated spectral data at these excitation wavelengths. The algorithms successfully identify still good EVOOs from aged EVOOs with over 90% accuracy, proposing an innovative approach that foregoes the need for detailed chemical analysis. This work shows the potential of ML-based approaches applied to fluorescence to replace traditional, labourintensive analyses. Therefore, it paves the way for the development of a compact, field-deployable fluorescence sensing device for rapid and objective quality control in olive oil production and early detection of oxidation or adulteration, and aiding in the classification of olive oils for market purposes.
In many optical experiments, a long measurement time is necessary to collect enough information and improve the signal-to-noise ratio. This happens, for example, in total luminescence spectroscopy (TLS) where the data is acquired as excitation-emission matrices (EEMs). An EEM is an unique chemical fingerprint of the analyzed substance that allows its comprehensive characterization. To collect a high-resolution EEM, it is necessary to scan both the excitation and the emission wavelengths in small steps and, for each step, to collect the light for a long time to maximize the signal-to-noise ratio. Therefore, acquiring a high-resolution excitation emission matrix can take more than an hour, depending on the size of the wavelength steps, the intensity of the signal, and the spectral range to be analyzed. This paper proposes a new method to reconstruct a high-resolution EEM from low-resolution one using deep learning super-resolution techniques. Specifically, this work proposes a new artificial neural network architecture, a sub-pixel convolutional neural network, designed to be applied to fluorescence EEM images. The code used is made available via a GitHub repository with instructions for applying transfer learning to different types of images.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.