Robust Feature Representation Using Multi-Task Learning for Human Activity Recognition

Robust Feature Representation Using Multi-Task Learning for Human Activity Recognition

Learning underlying patterns from sensory data is crucial in the Human Activity Recognition (HAR) task to avoid poor generalization when coping with unseen data. A key solution to such an issue is representation learning, which becomes essential when input signals contain activities with similar pat...

Full description

Bibliographic Details
Main Authors: Behrooz Azadi, Michael Haslgrübler, Bernhard Anzengruber-Tanase, Georgios Sopidis, Alois Ferscha
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Sensors
Subjects:
human activity recognition
wearable
deep learning
representation learning
multi-task learning
alpine skiing
Online Access:https://www.mdpi.com/1424-8220/24/2/681

Internet

https://www.mdpi.com/1424-8220/24/2/681

Similar Items