1. ZHAW digitalcollection
  2. School of Engineering
  3. Publikationen
  4. Publikationen School of Engineering
Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25330
Full metadata record
DC FieldValueLanguage
dc.contributor.authorVenturini, Francesca-
dc.contributor.authorMichelucci, Umberto-
dc.contributor.authorSperti, Michela-
dc.contributor.authorGucciardi, Arnaud-
dc.contributor.authorDeriu, Marco A.-
dc.date.accessioned2022-07-27T07:30:57Z-
dc.date.available2022-07-27T07:30:57Z-
dc.date.issued2022-05-
dc.identifier.isbn9781510651548de_CH
dc.identifier.isbn9781510651555de_CH
dc.identifier.issn0277-786Xde_CH
dc.identifier.issn1996-756Xde_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/25330-
dc.description.abstractOptical 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.de_CH
dc.language.isoende_CH
dc.publisherSociety of Photo-Optical Instrumentation Engineers (SPIE)de_CH
dc.relation.ispartofseriesProceedings of SPIEde_CH
dc.rightsLicence according to publishing contractde_CH
dc.subjectFluorescence spectroscopyde_CH
dc.subjectFluorescence sensorde_CH
dc.subjectOlive oilde_CH
dc.subjectMachine learningde_CH
dc.subjectArtificial neural networksde_CH
dc.subjectQuality controlde_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.subject.ddc621.3: Elektro-, Kommunikations-, Steuerungs- und Regelungstechnikde_CH
dc.titleOne-dimensional convolutional neural networks design for fluorescence spectroscopy with prior knowledge : explainability techniques applied to olive oil fluorescence spectrade_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Angewandte Mathematik und Physik (IAMP)de_CH
dc.identifier.doi10.1117/12.2621646de_CH
dc.identifier.doi10.21256/zhaw-25330-
zhaw.conference.detailsSPIE Photonics Europe, Strasbourg, France, 3-7 April 2022de_CH
zhaw.funding.euNode_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.start1213917de_CH
zhaw.parentwork.editorBerghmans, Francis-
zhaw.parentwork.editorZergioti, Ioanna-
zhaw.publication.statuspublishedVersionde_CH
zhaw.series.number12139de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedingsOptical Sensing and Detection VIIde_CH
zhaw.webfeedPhotonicsde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Venturini-etal_One-dimensional-convolutinal_SPIE_1213917.pdf520.06 kBAdobe PDFThumbnail
View/Open
Show simple 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.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.