Publikationstyp: Konferenz: Paper
Art der Begutachtung: Peer review (Publikation)
Titel: Explainable deep learning for medical time series data
Autor/-in: Frick, Thomas
Glüge, Stefan
Rahimi, Abbas
Benini, Luca
Brunschwiler, Thomas
et. al: No
DOI: 10.1007/978-3-030-70569-5_15
Tagungsband: Wireless Mobile Communication and Healthcare
Seiten: 244
Seiten bis: 256
Angaben zur Konferenz: International Conference on Wireless Mobile Communication and Healthcare (MobiHealth), Online, 18 December 2020
Erscheinungsdatum: 21-Feb-2021
Reihe: Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Reihenzählung: 362
Verlag / Hrsg. Institution: Springer
Verlag / Hrsg. Institution: Cham
ISBN: 978-3-030-70568-8
Sprache: Englisch
Schlagwörter: Explainable deep learning; Convolutional neural network; Explanation quality metric; Medical time series data
Fachgebiet (DDC): 006: Spezielle Computerverfahren
362: Gesundheits- und Sozialdienste
Zusammenfassung: Neural 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.
Volltext Version: Publizierte Version
Lizenz (gemäss Verlagsvertrag): Lizenz gemäss Verlagsvertrag
Departement: Life Sciences und Facility Management
Organisationseinheit: Institut für Angewandte Simulation (IAS)
Enthalten in den Sammlungen:Publikationen Life Sciences und Facility Management

Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.

Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.