Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Applying generative models and transfer learning to physiological data classification

Title: Applying generative models and transfer learning to physiological data classification
Authors: Núñez Rodríguez, José Fernando; Arjona Martínez, Jamie; Tormos Llorente, Adrián; Garcia Gasulla, Dario; Béjar Alonso, Javier
Contributors: Universitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial; Universitat Politècnica de Catalunya. Departament de Ciències de la Computació; Barcelona Supercomputing Center; Universitat Politècnica de Catalunya. IMP - Information Modeling and Processing; Universitat Politècnica de Catalunya. IDEAI-UPC - Intelligent Data sciEnce and Artificial Intelligence Research Group
Publisher Information: IOS Press
Publication Year: 2023
Collection: Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge
Subject Terms: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial; Transfer learning (Machine learning); Synthetic data; Transfer learning; Time series; Physiological signals; ECG; Aprenentatge profund
Description: The scarcity and imbalance of datasets for training deep learning models in a specific task is a common problem. This is especially true in the physiological domain where many applications use complex data collection processes and protocols, and it is difficult to gather a significant number of subjects. In this paper, we evaluate generative deep learning algorithms by training them to create data based on open physiological datasets and conduct a study on their potential for transfer learning. We measure the performance change of classifiers when the training data is augmented with the synthetic samples and also perform experiments in which we fine-tune classification models trained with the generated data adding increasing amounts of the real data to investigate the transfer learning capabilities of synthetic datasets. Finally, we advise and provide the best option for researchers interested in augmenting ECG datasets using these algorithms and the best fine-tuning strategies that would generalize correctly when tested on new data from the same domain but for a different classification task. ; This research has been financed by the Artificial Intelligence for Healthy Aging (AI4HA, MIA.2021.M02.0007) project from the Programa Misiones de I+D en Inteligencia Artificial 2021. ; Peer Reviewed ; Postprint (published version)
Document Type: conference object
File Description: 10 p.; application/pdf
Language: English
Relation: https://ebooks.iospress.nl/volume/artificial-intelligence-research-and-development-proceedings-of-the-25th-international-conference-of-the-catalan-association-for-artificial-intelligence; info:eu-repo/grantAgreement/MINECO//MIA.2021.M02.0007; https://hdl.handle.net/2117/404985
DOI: 10.3233/FAIA230656
Availability: https://hdl.handle.net/2117/404985; https://doi.org/10.3233/FAIA230656
Rights: http://creativecommons.org/licenses/by-nc/4.0/ ; Open Access ; Attribution-NonCommercial 4.0 International
Accession Number: edsbas.F1D313A9
Database: BASE