Generic semi-supervised adversarial subject translation for sensor-based activity recognition: Performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data. Though, data collection and manual labeling in the HAR domain are prohibitively expensive due to human resource dependence in both steps. Hence, domain adaptation techniques are proposed to adapt the knowledge from the existing source of data. More recently, adversarial transfer learning methods have shown promisin

Generic semi-supervised adversarial subject translation for sensor-based activity recognition: Performance of Human Activity Recognition (HAR) models, particularly deep neural networks, is highly contingent upon the availability of the massive amount of annotated training data. Though, data collection and manual labeling in the HAR domain are prohibitively expensive due to human resource dependence in both steps. Hence, domain adaptation techniques are proposed to adapt the knowledge from the existing source of data. More recently, adversarial transfer learning methods have shown promisin

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) 2022-08, Vol.500, p.649-661
Hauptverfasser: Soleimani, Elnaz, Khodabandelou, Ghazaleh, Chibani, Abdelghani, Amirat, Yacine
Format: Artikel
Sprache:eng
Schlagworte:
Artificial Intelligence
Computer Science
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:
ISSN:0925-2312
DOI:10.1016/j.neucom.2022.05.075