Advanced search
2 files | 3.43 MB Add to list

TALK : tracking activities by linking knowledge

Bram Steenwinckel (UGent) , Mathias De Brouwer (UGent) , Marija Stojchevska (UGent) , Filip De Turck (UGent) , Sofie Van Hoecke (UGent) and Femke Ongenae (UGent)
Author
Organization
Project
Abstract
Dependable and accurate monitoring of elderly at home becomes crucial to limit both the costs and human efforts of following up elderly for establishing a healthy care system. Human Activity Recognition (HAR) tools, based on sensors installed in smart homes, will become an important tool to provide useful information to the caregiver when something happens in the house of an elderly and care is required. The current available detection tools either exist out of interpretable knowledge-driven techniques or scalable data-driven ones. In this paper, a hybrid methodology that combines both approaches is designed and evaluated to Track Activities by Linking Knowledge (TALK). Both sensor data and their link to the relevant domain knowledge about where those sensors are installed, the performed activities that occur, and how the household is constructed, are generalized in a specific knowledge graph (KG) structure to represent continuous events. The interpretable knowledge graph embedding technique Instance Neighboring using Knowledge (INK) is then used to transform these events inside the KG to a tabular format, which can be used by any traditional machine learning classifier to create a HAR tool. The TALK methodology is evaluated on two HAR datasets and shows (a) that TALK outperforms both traditional automated data-driven as well as knowledge-driven techniques in terms of predictive performance, and (b) how TALK can be easily used in a more out of lab environment. All these results and the interpretable aspects show that TALK can become an important tool to monitor elderly in their homes efficiently, effectively and with less intrusive techniques.
Keywords
Human Activity Recognition (HAR), Hybrid Artificial Intelligence (AI), Knowledge Graph (KG) embedding, Ambient living, Smart monitoring, eHealth

Downloads

  • 8281 acc.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.68 MB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.75 MB

Citation

Please use this url to cite or link to this publication:

MLA
Steenwinckel, Bram, et al. “TALK : Tracking Activities by Linking Knowledge.” ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, vol. 122, 2023, doi:10.1016/j.engappai.2023.106076.
APA
Steenwinckel, B., De Brouwer, M., Stojchevska, M., De Turck, F., Van Hoecke, S., & Ongenae, F. (2023). TALK : tracking activities by linking knowledge. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 122. https://doi.org/10.1016/j.engappai.2023.106076
Chicago author-date
Steenwinckel, Bram, Mathias De Brouwer, Marija Stojchevska, Filip De Turck, Sofie Van Hoecke, and Femke Ongenae. 2023. “TALK : Tracking Activities by Linking Knowledge.” ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 122. https://doi.org/10.1016/j.engappai.2023.106076.
Chicago author-date (all authors)
Steenwinckel, Bram, Mathias De Brouwer, Marija Stojchevska, Filip De Turck, Sofie Van Hoecke, and Femke Ongenae. 2023. “TALK : Tracking Activities by Linking Knowledge.” ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 122. doi:10.1016/j.engappai.2023.106076.
Vancouver
1.
Steenwinckel B, De Brouwer M, Stojchevska M, De Turck F, Van Hoecke S, Ongenae F. TALK : tracking activities by linking knowledge. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE. 2023;122.
IEEE
[1]
B. Steenwinckel, M. De Brouwer, M. Stojchevska, F. De Turck, S. Van Hoecke, and F. Ongenae, “TALK : tracking activities by linking knowledge,” ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, vol. 122, 2023.
@article{01GY9Z247PAP5D6T8VJZTFBJCV,
  abstract     = {{Dependable and accurate monitoring of elderly at home becomes crucial to limit both the costs and human efforts of following up elderly for establishing a healthy care system. Human Activity Recognition (HAR) tools, based on sensors installed in smart homes, will become an important tool to provide useful information to the caregiver when something happens in the house of an elderly and care is required. The current available detection tools either exist out of interpretable knowledge-driven techniques or scalable data-driven ones. In this paper, a hybrid methodology that combines both approaches is designed and evaluated to Track Activities by Linking Knowledge (TALK). Both sensor data and their link to the relevant domain knowledge about where those sensors are installed, the performed activities that occur, and how the household is constructed, are generalized in a specific knowledge graph (KG) structure to represent continuous events. The interpretable knowledge graph embedding technique Instance Neighboring using Knowledge (INK) is then used to transform these events inside the KG to a tabular format, which can be used by any traditional machine learning classifier to create a HAR tool. The TALK methodology is evaluated on two HAR datasets and shows (a) that TALK outperforms both traditional automated data-driven as well as knowledge-driven techniques in terms of predictive performance, and (b) how TALK can be easily used in a more out of lab environment. All these results and the interpretable aspects show that TALK can become an important tool to monitor elderly in their homes efficiently, effectively and with less intrusive techniques.}},
  articleno    = {{106076}},
  author       = {{Steenwinckel, Bram and De Brouwer, Mathias and Stojchevska, Marija and De Turck, Filip and Van Hoecke, Sofie and Ongenae, Femke}},
  issn         = {{0952-1976}},
  journal      = {{ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE}},
  keywords     = {{Human Activity Recognition (HAR),Hybrid Artificial Intelligence (AI),Knowledge Graph (KG) embedding,Ambient living,Smart monitoring,eHealth}},
  language     = {{eng}},
  pages        = {{11}},
  title        = {{TALK : tracking activities by linking knowledge}},
  url          = {{http://doi.org/10.1016/j.engappai.2023.106076}},
  volume       = {{122}},
  year         = {{2023}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: