EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An IMU Dataset for Human Activity Recognition to Support Independent Living in Smart Homes (IMU-HAR-IL)

Moid Sandhu, Wei Lu, Brano Kusy, David Silvera-Tawil

Scientific Data · 16.11.2026

DOI: 10.1038/s41597-026-08666-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Data, online erschienen am 16.11.2026. Verfasst von Moid Sandhu und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The majority of existing human activity recognition (HAR) datasets rely on wearable or object-mounted inertial measurement unit (IMU) sensors, yet they fall short in a critical dimension – they are not purposefully designed to capture the specific activities that serve as meaningful indicators of independent living among older adults. This document introduces HAR-IMU-IL, a dataset developed for HAR using IMU sensors within a smart home environment with a focus to support objective functional assessment of older adults’ independent living (IL). In particular, HAR-IMU-IL includes recordings of 50 participants performing 17 clinically relevant activities of daily living, spanning 4 functional domains essential for independent living: mobility, hygiene, nutrition and hydration, and medication intake. The dataset was collected using 30 IMU sensors, comprising both wearable and object-mounted devices integrated within a real-world residential setting. The dataset includes multi-sensor inertial data captured under realistic, unconstrained conditions, together with detailed annotations ensuring high temporal accuracy and consistency across sensors. A comprehensive data collection protocol was implemented to preserve ecological validity and enable reliable multi-sensor synchronisation. HAR-IMU-IL provides a large-scale, functionally grounded resource for advancing and benchmarking machine learning and artificial intelligence approaches for HAR in home settings. Its utility is further demonstrated by developing models capable of accurately recognising both activities and broader functional areas using wearable and object-mounted sensors. These capabilities highlight potential of the dataset to enable applications in continuous activity monitoring, functional health assessment, smart home automation, and assistive technologies that support independent living. By bridging the gap between raw motion sensing and semantic understanding of human activities, this work advances a foundational capability with broad implications for bioengineering systems design, robotic assistance, and clinical rehabilitation, where accurate, real-time recognition of purposeful human action is essential for responsive, adaptive, and personalised interventions.

Zitieren

APA

Sandhu, M., Lu, W., Kusy, B., & Silvera-Tawil, D. (2026). An IMU Dataset for Human Activity Recognition to Support Independent Living in Smart Homes (IMU-HAR-IL). Scientific Data. https://doi.org/10.1038/s41597-026-08666-2

Vancouver

Sandhu M, Lu W, Kusy B, Silvera-Tawil D. An IMU Dataset for Human Activity Recognition to Support Independent Living in Smart Homes (IMU-HAR-IL). Scientific Data. 2026. doi:10.1038/s41597-026-08666-2

BibTeX
@article{Sandhu2026,
  author = {Sandhu, Moid and Lu, Wei and Kusy, Brano and Silvera-Tawil, David},
  title = {An IMU Dataset for Human Activity Recognition to Support Independent Living in Smart Homes (IMU-HAR-IL)},
  journal = {Scientific Data},
  year = {2026},
  doi = {10.1038/s41597-026-08666-2}
}
Kostenlos starten →