Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks

Sperti, Michela; Gucciardi, Arnaud; Michelucci, Umberto; Venturini, Francesca; Deriu, Marco Agostino  .

doi:10.1117/12.2621666

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks
Authors:	Sperti, Michela Gucciardi, Arnaud Michelucci, Umberto Venturini, Francesca Deriu, Marco Agostino .
et. al:	No
DOI:	10.1117/12.2621666
Page(s):	121391K
Conference details:	SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022
Issue Date:	May-2022
Publisher / Ed. Institution:	SPIE
ISBN:	9781510651548 9781510651555
Language:	English
Subjects:	Sensor; Fluorescence; Artificial intelligence; Machine learning
Subject (DDC):	006: Special computer methods 664: Food technology
Abstract:	The chemical analysis of food is essential to monitor and guarantee its quality. The determination of the chemical parameters, like the concentration of particular substances, is performed by specialized laboratories and is a time-consuming and costly process. Therefore, alternative methods with easier handling are of great interest. Among these fluorescence spectroscopy offers great opportunities. Fluorescence spectra are one-dimensional arrays of values already successfully employed together with artificial neural networks for classification problems in chemistry, physics, and other fields. However, the extraction of specific quantities from the spectra poses a much harder challenge. This work analyzes and compares the ability of feed-forward neural networks (FFNN) and one-dimensional convolutional neural networks (1D-CNN) to extract relevant features from fluorescence spectra of olive oils. The results indicate that 1D-CNN, contrary to FFNN, successfully predicts the chemical parameters with high accuracy. The great advantages of the proposed method are: 1) the possibility of using optical methods instead of time-consuming chemical ones, like chromatography, 2) the lack of any special sample handling, like dilution and 3) the lack of any pre-processing of the data. The problem of small datasets, which may arise for novel techniques like the proposed one, is also addressed statistically by using the leave-one-out resampling technique.
Further description:	Optical Sensing and Detection VII: 12139-81
URI:	https://digitalcollection.zhaw.ch/handle/11475/25768
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Applied Mathematics and Physics (IAMP)
Published as part of the ZHAW project:	Self-learning optical sensor
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

Sperti, M., Gucciardi, A., Michelucci, U., Venturini, F., & Deriu, M. Agostino. (2022). Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks [Conference paper]. SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022, 121391K. https://doi.org/10.1117/12.2621666

Sperti, M. et al. (2022) ‘Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks’, in SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022. SPIE, p. 121391K. Available at: https://doi.org/10.1117/12.2621666.

M. Sperti, A. Gucciardi, U. Michelucci, F. Venturini, and M. Agostino. Deriu, “Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks,” in SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022, May 2022, p. 121391K. doi: 10.1117/12.2621666.

SPERTI, Michela, Arnaud GUCCIARDI, Umberto MICHELUCCI, Francesca VENTURINI und Marco Agostino . DERIU, 2022. Chemical analysis of olive oils from fluorescence spectra thanks to one-dimensional convolutional neural networks. In: SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022. Conference paper. SPIE. Mai 2022. S. 121391K. ISBN 9781510651548

Sperti, Michela, Arnaud Gucciardi, Umberto Michelucci, Francesca Venturini, and Marco Agostino . Deriu. 2022. “Chemical Analysis of Olive Oils from Fluorescence Spectra Thanks to One-Dimensional Convolutional Neural Networks.” Conference paper. In SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022, 121391K. SPIE. https://doi.org/10.1117/12.2621666.

Sperti, Michela, et al. “Chemical Analysis of Olive Oils from Fluorescence Spectra Thanks to One-Dimensional Convolutional Neural Networks.” SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022, SPIE, 2022, p. 121391K, https://doi.org/10.1117/12.2621666.