EUVIMEDOpdag EUVIMED
Open access

A Context-Assisted, Semi-Automated Activity Recall Interface Allowing Uncertainty

H A LE, Veronika Potter, Akshat Choube, Rithika Lakshminarayanan, Varun Mishra, Stephen Intille

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · 2025-12-02 · 9 (4) · 1-34

DOI: 10.1145/3770710 ↗

At a glance

Journal article in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, published online on 2025-12-02. Written by H A LE and 5 co-authors. Institution: Khoury College of Computer Sciences, Northeastern University, USA. Cited 5 times so far (Crossref); 115 references. The full text is freely available in PubMed Central. Funded by: NIDA NIH HHS, NCI NIH HHS, NIH.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Measuring activities and postures is an important area of research in ubiquitous computing, human-computer interaction, and personal health informatics. One approach that researchers use to collect large amounts of labeled data to develop models for activity recognition and measurement is asking participants to self-report their daily activities. Although participants can typically recall their sequence of daily activities, remembering the precise start and end times of each activity is significantly more challenging. ACAI is a novel, context-assisted Activity Annotation Inttivity Annotation Interface that enables participants to efficiently label their activities by accepting or adjusting system-generated activity suggestions while explicitly expressing uncertainty about temporal boundaries. We evaluated ACAI using two complementary studies: a usability study with 11 participants and a two-week, free-living study with 14 participants. We compared our activity annotation system with the current gold-standard methods for activity recall in health sciences research: 24PAR and its computerized version, ACT24. Our system reduced annotation time and perceived effort while significantly improving data validity and fidelity compared to both standard human-supervised and unsupervised activity recall approaches. We discuss the limitations of our design and implications for developing adaptive, human-in-the-loop activity recognition systems used to collect self-report data on activity.

Subjects

Author keywords

Context-assisted RecallEcological Momentary AssessmentPhysical Activity MeasurementsWearable computing

Authors and institutions

  • Khoury College of Computer Sciences, Northeastern University, USA.
  • Khoury College of Computer Sciences and Bouvé College of Health Sciences, Northeastern University, USA.

Funding

  • NIDA NIH HHS
  • NCI NIH HHS
  • NIH
  • NSF

Cite

APA

LE, H. A., Potter, V., Choube, A., Lakshminarayanan, R., Mishra, V., & Intille, S. (2025). A Context-Assisted, Semi-Automated Activity Recall Interface Allowing Uncertainty. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 9(4), 1-34. https://doi.org/10.1145/3770710

Vancouver

LE HA, Potter V, Choube A, Lakshminarayanan R, Mishra V, Intille S. A Context-Assisted, Semi-Automated Activity Recall Interface Allowing Uncertainty. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2025;9(4):1-34. doi:10.1145/3770710

BibTeX
@article{LE2025,
  author = {LE, H A and Potter, Veronika and Choube, Akshat and Lakshminarayanan, Rithika and Mishra, Varun and Intille, Stephen},
  title = {A Context-Assisted, Semi-Automated Activity Recall Interface Allowing Uncertainty},
  journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
  year = {2025},
  volume = {9},
  number = {4},
  pages = {1--34},
  doi = {10.1145/3770710}
}
Start for free →