From Movements to Metrics: Evaluating Explainable AI Methods in Skeleton-Based Human Activity Recognition

The advancement of deep learning in human activity recognition (HAR) using 3D skeleton data is critical for applications in healthcare, security, sports, and human–computer interaction. This paper tackles a well-known gap in the field, which is the lack of testing in the applicability and reliabilit...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Sensors (Basel, Switzerland) Jg. 24; H. 6; S. 1940
Hauptverfasser:	Pellano, Kimji N., Strümke, Inga, Ihlen, Espen A. F.
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Switzerland MDPI AG 18.03.2024 MDPI
Schlagworte:	Accuracy CAM Data analysis Datasets Decision making Deep learning explainable AI Grad-CAM Human Activities human activity recognition Human mechanics Humans Kinematics Methods Movement Musculoskeletal System Neural networks Reproducibility of Results Sensors Skeleton skeleton data skeleton data explainable AI Grad-CAM human activity recognition CAM
ISSN:	1424-8220, 1424-8220
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!