EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches

Deepika Singh, Erinc Merdivan, Johannes Kropf, Andreas Holzinger

Universal Access in the Information Society · 2025-06 · 24 (2) · 1173-1191

DOI: 10.1007/s10209-024-01123-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Universal Access in the Information Society, online erschienen am 13.06.2024. Verfasst von Deepika Singh und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Informatics, Statistics and Documentation, Medical University Graz, Graz, Austria. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Austrian Science Fund, University of Natural Resources and Life Sciences Vienna.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recognizing multiple residents’ activities is a pivotal domain within active and assisted living technologies, where the diversity of actions in a multi-occupant home poses a challenge due to their uneven distribution. Frequent activities contrast with those occurring sporadically, necessitating adept handling of class imbalance to ensure the integrity of activity recognition systems based on raw sensor data. While deep learning has proven its merit in identifying activities for solitary residents within balanced datasets, its application to multi-resident scenarios requires careful consideration. This study provides a comprehensive survey on the issue of class imbalance and explores the efficacy of Long Short-Term Memory and Bidirectional Long Short-Term Memory networks in discerning activities of multiple residents, considering both individual and aggregate labeling of actions. Through rigorous experimentation with data-level and algorithmic strategies to address class imbalances, this research scrutinizes the explicability of deep learning models, enhancing their transparency and reliability. Performance metrics are drawn from a series of evaluations on three distinct, highly imbalanced smart home datasets, offering insights into the models’ behavior and contributing to the advancement of trustworthy multi-resident activity recognition systems.

Schlagwörter

Stichwörter der Autor:innen

BiLSTM networksClass imbalanceExplainabilityHuman activity recognitionLSTMMultiple residentsTrust

Autor:innen und Institutionen

  • Institute for Medical Informatics, Statistics and Documentation, Medical University Graz, Graz, Austria.
  • AIT Austrian Institute of Technology (AIT), Vienna, Austria.
  • Human-Centered AI Lab, Institute of Forest Engineering, Department of Forest and Soil Sciences, University of Natural Resources and Life Sciences Vienna, Vienna, Austria.

Förderung

  • Austrian Science Fund
  • University of Natural Resources and Life Sciences Vienna

Zitieren

APA

Singh, D., Merdivan, E., Kropf, J., & Holzinger, A. (2025). Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches. Universal Access in the Information Society, 24(2), 1173-1191. https://doi.org/10.1007/s10209-024-01123-0

Vancouver

Singh D, Merdivan E, Kropf J, Holzinger A. Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches. Universal Access in the Information Society. 2025;24(2):1173-1191. doi:10.1007/s10209-024-01123-0

BibTeX
@article{Singh2025,
  author = {Singh, Deepika and Merdivan, Erinc and Kropf, Johannes and Holzinger, Andreas},
  title = {Class imbalance in multi-resident activity recognition: an evaluative study on explainability of deep learning approaches},
  journal = {Universal Access in the Information Society},
  year = {2025},
  volume = {24},
  number = {2},
  pages = {1173--1191},
  doi = {10.1007/s10209-024-01123-0}
}
Kostenlos starten →