Conformer-Based Human Activity Recognition Using Inertial Measurement Units
Sensors · 23.08.2023 · 23 (17) · 7357
DOI: 10.3390/s23177357 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 23.08.2023. Verfasst von Sowmiya Seenath und 1 weiteren Autor:innen. Beteiligte Einrichtung: Noorul Islam Centre for Higher Education, Kanyakumari 629180, TamilNadu, India. Hauptthemen laut MEDLINE: Human Activities, Exercise. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Human activity recognition (HAR) using inertial measurement units (IMUs) is gaining popularity due to its ease of use, accurate and reliable measurements of motion and orientation, and its suitability for real-time IoT applications such as healthcare monitoring, sports and fitness tracking, video surveillance and security, smart homes and assistive technologies, human–computer interaction, workplace safety, and rehabilitation and physical therapy. IMUs are widely used as they provide precise and consistent measurements of motion and orientation, making them an ideal choice for HAR. This paper proposes a Conformer-based HAR model that employs attention mechanisms to better capture the temporal dynamics of human movement and improve the recognition accuracy. The proposed model consists of convolutional layers, multiple Conformer blocks with self-attention and residual connections, and classification layers. Experimental results show that the proposed model outperforms existing models such as CNN, LSTM, and GRU. The attention mechanisms in the Conformer blocks have residual connections, which can prevent vanishing gradients and improve convergence. The model was evaluated using two publicly available datasets, WISDM and USCHAD, and achieved accuracy of 98.1% and 96%, respectively. These results suggest that Conformer-based models can offer a promising approach for HAR using IMU.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Noorul Islam Centre for Higher Education, Kanyakumari 629180, TamilNadu, India.
ORCID-Profile: Sowmiya Seenath
Zitieren
APA
Seenath, S., & Dharmaraj, M. (2023). Conformer-Based Human Activity Recognition Using Inertial Measurement Units. Sensors, 23(17), 7357. https://doi.org/10.3390/s23177357
Vancouver
Seenath S, Dharmaraj M. Conformer-Based Human Activity Recognition Using Inertial Measurement Units. Sensors. 2023;23(17):7357. doi:10.3390/s23177357
BibTeX
@article{Seenath2023,
author = {Seenath, Sowmiya and Dharmaraj, Menaka},
title = {Conformer-Based Human Activity Recognition Using Inertial Measurement Units},
journal = {Sensors},
year = {2023},
volume = {23},
number = {17},
pages = {7357},
doi = {10.3390/s23177357}
}
EUVIMED