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-18733
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMichelucci, Umberto-
dc.contributor.authorVenturini, Francesca-
dc.date.accessioned2019-11-20T09:38:48Z-
dc.date.available2019-11-20T09:38:48Z-
dc.date.issued2019-
dc.identifier.issn2076-3417de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/18733-
dc.description.abstractThe classical approach to non-linear regression in physics is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterized by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built in the models to compensate for the difficulty of modeling things that are, by construction, difficult to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here, the MTL architecture allows predicting multiple parameters, the oxygen concentration and temperature, from a single set of measurements.de_CH
dc.language.isoende_CH
dc.publisherMDPIde_CH
dc.relation.ispartofApplied Sciencesde_CH
dc.rightshttp://creativecommons.org/licenses/by/4.0/de_CH
dc.subjectArtificial intelligencede_CH
dc.subjectMachine learningde_CH
dc.subjectOxygen sensorde_CH
dc.subjectLuminescencede_CH
dc.subject.ddc004: Informatikde_CH
dc.subject.ddc530: Physikde_CH
dc.titleMulti-task learning for multi-dimensional regression : application to luminescence sensingde_CH
dc.typeBeitrag in wissenschaftlicher Zeitschriftde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Angewandte Mathematik und Physik (IAMP)de_CH
dc.identifier.doi10.3390/app9224748de_CH
dc.identifier.doi10.21256/zhaw-18733-
zhaw.funding.euNode_CH
zhaw.issue22de_CH
zhaw.originated.zhawYesde_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.volume9de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.webfeedPhotonicsde_CH
zhaw.author.additionalNode_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2019_Venturini_MultiTask Learning for MultiDimensional Regression_ApplSci.pdf1.49 MBAdobe PDFThumbnail
View/Open
Show simple item record
Michelucci, U., & Venturini, F. (2019). Multi-task learning for multi-dimensional regression : application to luminescence sensing. Applied Sciences, 9(22). https://doi.org/10.3390/app9224748
Michelucci, U. and Venturini, F. (2019) ‘Multi-task learning for multi-dimensional regression : application to luminescence sensing’, Applied Sciences, 9(22). Available at: https://doi.org/10.3390/app9224748.
U. Michelucci and F. Venturini, “Multi-task learning for multi-dimensional regression : application to luminescence sensing,” Applied Sciences, vol. 9, no. 22, 2019, doi: 10.3390/app9224748.
MICHELUCCI, Umberto und Francesca VENTURINI, 2019. Multi-task learning for multi-dimensional regression : application to luminescence sensing. Applied Sciences. 2019. Bd. 9, Nr. 22. DOI 10.3390/app9224748
Michelucci, Umberto, and Francesca Venturini. 2019. “Multi-Task Learning for Multi-Dimensional Regression : Application to Luminescence Sensing.” Applied Sciences 9 (22). https://doi.org/10.3390/app9224748.
Michelucci, Umberto, and Francesca Venturini. “Multi-Task Learning for Multi-Dimensional Regression : Application to Luminescence Sensing.” Applied Sciences, vol. 9, no. 22, 2019, https://doi.org/10.3390/app9224748.


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