One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra

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

doi:10.1117/12.2621646

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25330

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra
Authors:	Venturini, Francesca Michelucci, Umberto Sperti, Michela Gucciardi, Arnaud Deriu, Marco A.
et. al:	No
DOI:	10.1117/12.2621646 10.21256/zhaw-25330
Proceedings:	Optical Sensing and Detection VII
Editors of the parent work:	Berghmans, Francis Zergioti, Ioanna
Page(s):	1213917
Conference details:	SPIE Photonics Europe, Strasbourg, France, 3-7 April 2022
Issue Date:	May-2022
Series:	Proceedings of SPIE
Series volume:	12139
Publisher / Ed. Institution:	Society of Photo-Optical Instrumentation Engineers (SPIE)
ISBN:	9781510651548 9781510651555
ISSN:	0277-786X 1996-756X
Language:	English
Subjects:	Fluorescence spectroscopy; Fluorescence sensor; Olive oil; Machine learning; Artificial neural networks; Quality control
Subject (DDC):	006: Special computer methods 621.3: Electrical, communications, control engineering
Abstract:	Optical spectra, and particularly fluorescence spectra, contain a large quantity of information about the substances and their interaction with the environment. It is of great interest, therefore, to try to extract as much of this information as possible, as optical measurements can be easy, non-invasive, and can happen in-situ making the data collection a very appealing method of gathering knowledge. Artificial neural networks are known for their feature extraction capabilities and are therefore well suited for this challenge. In this work, inspired by convolutional neural network (CNN) architectures in 2D and their success with images, a novel approach using one-dimensional convolutional neural networks (1D-CNN) is used to extract information on the measured spectra by using explainability techniques. The 1D-CNN architecture has as input the entire fluorescence spectrum and takes advantage in its design of prior knowledge about the instrumentation and sample characteristics as, for example, spectrometer resolution or the expected number of relevant features in the spectrum. Even if network performance is good, it remains an open question if the features used for the predictions make sense from a physical and chemical point of view and if they match what is known from existing studies. This work studies the output of the convolutional layers, known as feature maps, to understand which features the network has effectively used for the predictions, and thus which part of the measured spectra contains the relevant information about the phenomena at the basis of what has to be predicted. The proposed approach is demonstrated by applying it to the determination of the UV absorbance at 232 nm, K232, from fluorescence spectra using a dataset of 18 Spanish olive oils, which were chemically analyzed from certified laboratories. The 1D-CNN successfully predicts the parameter K232 and enables, by studying feature maps, the clear identification of the relevant spectral features. The main contributions of this work are two. Firstly, it describes how designing the neural network architecture with prior knowledge (spectrometer resolution, etc.) will help the network in learning features that have a clear connection to the chemical composition of the substances, and thus are clearly explainable. Secondly, it shows how, in the case of olive oil, the identified features match perfectly the relevant features known from existing previous studies, thus confirming that the network is learning from the underlying chemical process.
URI:	https://digitalcollection.zhaw.ch/handle/11475/25330
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)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2022_Venturini-etal_One-dimensional-convolutinal_SPIE_1213917.pdf		520.06 kB	Adobe PDF	View/Open

Show full item record

Venturini, F., Michelucci, U., Sperti, M., Gucciardi, A., & Deriu, M. A. (2022). One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra [Conference paper]. In F. Berghmans & I. Zergioti (Eds.), Optical Sensing and Detection VII (p. 1213917). Society of Photo-Optical Instrumentation Engineers (SPIE). https://doi.org/10.1117/12.2621646

Venturini, F. et al. (2022) ‘One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra’, in F. Berghmans and I. Zergioti (eds) Optical Sensing and Detection VII. Society of Photo-Optical Instrumentation Engineers (SPIE), p. 1213917. Available at: https://doi.org/10.1117/12.2621646.

F. Venturini, U. Michelucci, M. Sperti, A. Gucciardi, and M. A. Deriu, “One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra,” in Optical Sensing and Detection VII, May 2022, p. 1213917. doi: 10.1117/12.2621646.

VENTURINI, Francesca, Umberto MICHELUCCI, Michela SPERTI, Arnaud GUCCIARDI und Marco A. DERIU, 2022. One-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectra. In: Francis BERGHMANS und Ioanna ZERGIOTI (Hrsg.), Optical Sensing and Detection VII. Conference paper. Society of Photo-Optical Instrumentation Engineers (SPIE). Mai 2022. S. 1213917. ISBN 9781510651548

Venturini, Francesca, Umberto Michelucci, Michela Sperti, Arnaud Gucciardi, and Marco A. Deriu. 2022. “One-Dimensional Convolutional Neural Networks Design for Fluorescence Spectroscopy with Prior Knowledge : Explainability Techniques Applied to Olive Oil Fluorescence Spectra.” Conference paper. In Optical Sensing and Detection VII, edited by Francis Berghmans and Ioanna Zergioti, 1213917. Society of Photo-Optical Instrumentation Engineers (SPIE). https://doi.org/10.1117/12.2621646.

Venturini, Francesca, et al. “One-Dimensional Convolutional Neural Networks Design for Fluorescence Spectroscopy with Prior Knowledge : Explainability Techniques Applied to Olive Oil Fluorescence Spectra.” Optical Sensing and Detection VII, edited by Francis Berghmans and Ioanna Zergioti, Society of Photo-Optical Instrumentation Engineers (SPIE), 2022, p. 1213917, https://doi.org/10.1117/12.2621646.