EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living

Peng Su iD, Dejiu Chen iD

Sensors · 17.04.2024 · 24 (8) · 2567

DOI: 10.3390/s24082567 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 17.04.2024. Verfasst von Peng Su und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Engineering Design, KTH Royal Institute of Technology, 100 44 Stockholm, Sweden. Hauptthemen laut MEDLINE: Activities of Daily Living, Neural Networks, Computer. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: KTH Royal Institute of Technology, Sweden.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human Activity Recognition (HAR) refers to a field that aims to identify human activities by adopting multiple techniques. In this field, different applications, such as smart homes and assistive robots, are introduced to support individuals in their Activities of Daily Living (ADL) by analyzing data collected from various sensors. Apart from wearable sensors, the adoption of camera frames to analyze and classify ADL has emerged as a promising trend for achieving the identification and classification of ADL. To accomplish this, the existing approaches typically rely on object classification with pose estimation using the image frames collected from cameras. Given the existence of inherent correlations between human–object interactions and ADL, further efforts are often needed to leverage these correlations for more effective and well justified decisions. To this end, this work proposes a framework where Graph Neural Networks (GNN) are adopted to explicitly analyze human–object interactions for more effectively recognizing daily activities. By automatically encoding the correlations among various interactions detected through some collected relational data, the framework infers the existence of different activities alongside their corresponding environmental objects. As a case study, we use the Toyota Smart Home dataset to evaluate the proposed framework. Compared with conventional feed-forward neural networks, the results demonstrate significantly superior performance in identifying ADL, allowing for the classification of different daily activities with an accuracy of 0.88. Furthermore, the incorporation of encoded information from relational data enhances object-inference performance compared to the GNN without joint prediction, increasing accuracy from 0.71 to 0.77.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Activities of Daily LivingNeural Networks, ComputerHumansAlgorithmsWearable Electronic DevicesHuman Activities

Stichwörter der Autor:innen

activities of daily living analysisgraph neural networkscene understanding

Autor:innen und Institutionen

  • Department of Engineering Design, KTH Royal Institute of Technology, 100 44 Stockholm, Sweden.

ORCID-Profile: Peng Su, Dejiu Chen

Förderung

  • KTH Royal Institute of Technology, Sweden

Zitieren

APA

Su, P., & Chen, D. (2024). Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living. Sensors, 24(8), 2567. https://doi.org/10.3390/s24082567

Vancouver

Su P, Chen D. Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living. Sensors. 2024;24(8):2567. doi:10.3390/s24082567

BibTeX
@article{Su2024,
  author = {Su, Peng and Chen, Dejiu},
  title = {Adopting Graph Neural Networks to Analyze Human–Object Interactions for Inferring Activities of Daily Living},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {8},
  pages = {2567},
  doi = {10.3390/s24082567}
}
Kostenlos starten →