Full metadata record
DC FieldValueLanguage
dc.contributor.authorFrick, Thomas-
dc.contributor.authorGlüge, Stefan-
dc.contributor.authorRahimi, Abbas-
dc.contributor.authorBenini, Luca-
dc.contributor.authorBrunschwiler, Thomas-
dc.date.accessioned2021-03-14T11:17:53Z-
dc.date.available2021-03-14T11:17:53Z-
dc.date.issued2021-02-21-
dc.identifier.isbn978-3-030-70568-8de_CH
dc.identifier.isbn978-3-030-70569-5de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/21995-
dc.description.abstractNeural Networks are powerful classifiers. However, they are black boxes and do not provide explicit explanations for their decisions. For many applications, particularly in health care, explanations are essential for building trust in the model. In the field of computer vision, a multitude of explainability methods have been developed to analyze Neural Networks by explaining what they have learned during training and what factors influence their decisions. This work provides an overview of these explanation methods in form of a taxonomy. We adapt and benchmark the different methods to time series data. Further, we introduce quantitative explanation metrics that enable us to build an objective benchmarking framework with which we extensively rate and compare explainability methods. As a result, we show that the Grad-CAM++ algorithm outperforms all other methods. Finally, we identify the limits of existing explanation methods for specific datasets, with feature values close to zero.de_CH
dc.language.isoende_CH
dc.publisherSpringerde_CH
dc.relation.ispartofseriesLecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineeringde_CH
dc.rightsLicence according to publishing contractde_CH
dc.subjectExplainable deep learningde_CH
dc.subjectConvolutional neural networkde_CH
dc.subjectExplanation quality metricde_CH
dc.subjectMedical time series datade_CH
dc.subject.ddc006: Spezielle Computerverfahrende_CH
dc.subject.ddc362: Gesundheits- und Sozialdienstede_CH
dc.titleExplainable deep learning for medical time series datade_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementLife Sciences und Facility Managementde_CH
zhaw.organisationalunitInstitut für Angewandte Simulation (IAS)de_CH
zhaw.publisher.placeChamde_CH
dc.identifier.doi10.1007/978-3-030-70569-5_15de_CH
zhaw.conference.detailsInternational Conference on Wireless Mobile Communication and Healthcare (MobiHealth), Online, 18 December 2020de_CH
zhaw.funding.euNode_CH
zhaw.originated.zhawYesde_CH
zhaw.pages.end256de_CH
zhaw.pages.start244de_CH
zhaw.publication.statuspublishedVersionde_CH
zhaw.series.number362de_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedingsWireless Mobile Communication and Healthcarede_CH
zhaw.webfeedBio-Inspired Modelling and Learning Systemsde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen Life Sciences und Facility Management

Files in This Item:
There are no files associated with this item.


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