Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition
Sensors · 06.01.2023 · 23 (2) · 683
DOI: 10.3390/s23020683 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 06.01.2023. Verfasst von Keshav Thapa und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Rehabilitation Medical Engineering, Daegu Haany University, Gyeongsan-si 38610, Republic of Korea. Hauptthemen laut MEDLINE: Algorithms, Human Activities. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Basic Science Research Program through the National Foundation of Korea (NRF) funded by the Ministry of Education.
Abstract (Originalsprache)
The study of human activity recognition concentrates on classifying human activities and the inference of human behavior using modern sensing technology. However, the issue of domain adaptation for inertial sensing-based human activity recognition (HAR) is still burdensome. The existing requirement of labeled training data for adapting such classifiers to every new person, device, or on-body location is a significant barrier to the widespread adoption of HAR-based applications, making this a challenge of high practical importance. We propose the semi-supervised HAR method to improve reconstruction and generation. It executes proper adaptation with unlabeled data without changes to a pre-trained HAR classifier. Our approach decouples VAE with adversarial learning to ensure robust classifier operation, without newly labeled training data, under changes to the individual activity and the on-body sensor position. Our proposed framework shows the empirical results using the publicly available benchmark dataset compared to state-of-art baselines, achieving competitive improvement for handling new and unlabeled activity. The result demonstrates SAA has achieved a 5% improvement in classification score compared to the existing HAR platform.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Rehabilitation Medical Engineering, Daegu Haany University, Gyeongsan-si 38610, Republic of Korea.
- Department of Geriatric Rehabilitation, Daegu Haany University, Gyeongsan-si 38610, Republic of Korea.
- Department of Electronic Engineering, Kwangwoon University, Seoul 01897, Republic of Korea.
ORCID-Profile: Keshav Thapa
Förderung
- Basic Science Research Program through the National Foundation of Korea (NRF) funded by the Ministry of Education
Zitieren
APA
Thapa, K., Seo, Y., Yang, S. H., & Kim, K. (2023). Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition. Sensors, 23(2), 683. https://doi.org/10.3390/s23020683
Vancouver
Thapa K, Seo Y, Yang SH, Kim K. Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition. Sensors. 2023;23(2):683. doi:10.3390/s23020683
BibTeX
@article{Thapa2023,
author = {Thapa, Keshav and Seo, Yousung and Yang, Sung-Hyun and Kim, Kyong},
title = {Semi-Supervised Adversarial Auto-Encoder to Expedite Human Activity Recognition},
journal = {Sensors},
year = {2023},
volume = {23},
number = {2},
pages = {683},
doi = {10.3390/s23020683}
}
EUVIMED