EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction

Yu-Hsuan Tseng, Chih-Yu Wen iD

Sensors · 2023

DOI: 10.3390/s23187802 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Yu-Hsuan Tseng und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science and Engineering, National Chung Hsing University, Taichung 40227, Taiwan. Hauptthemen laut MEDLINE: Learning, Computer Systems. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Smart Sustainable New Agriculture Research Center (SMARTer) from the NSTC of Taiwan, Innovation and Development Center of Sustainable Agriculture" from the Featured Areas Re-search Center Program within the framework of the Higher Education Spr…, Smart Sustainable New Agriculture Research Center (SMARTer) at the NSTC of Taiwan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LearningComputer SystemsHumansHuman ActivitiesMovementRecognition, Psychology

Stichwörter der Autor:innen

generative adversarial networkshuman activity recognitionvariational autoencoder

Autor:innen und Institutionen

  • Department of Computer Science and Engineering, National Chung Hsing University, Taichung 40227, Taiwan.
  • Department of Electrical Engineering, National Chung Hsing University, Taichung 40227, Taiwan.
  • Smart Sustainable New Agriculture Research Center (SMARTer), National Chung Hsing University, Taichung 40227, Taiwan.
  • Innovation and Development Center of Sustainable Agriculture (IDCSA), National Chung Hsing University, Taichung 40227, Taiwan.

ORCID-Profile: Chih-Yu Wen

Förderung

  • The Smart Sustainable New Agriculture Research Center (SMARTer) from the NSTC of Taiwan
  • Innovation and Development Center of Sustainable Agriculture" from the Featured Areas Re-search Center Program within the framework of the Higher Education Spr…
  • Smart Sustainable New Agriculture Research Center (SMARTer) at the NSTC of Taiwan
  • Innovation and Development Center of Sustainable Agriculture

Zitieren

APA

Tseng, Y. H., & Wen, C. Y. (2023). Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction. Sensors. https://doi.org/10.3390/s23187802

Vancouver

Tseng YH, Wen CY. Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction. Sensors. 2023. doi:10.3390/s23187802

BibTeX
@article{Tseng2023,
  author = {Tseng, Yu-Hsuan and Wen, Chih-Yu},
  title = {Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23187802}
}
Kostenlos starten →