EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition

Josh Cherian iD, Samantha Ray iD, Paul Taele iD, Jung In Koh iD, Tracy Hammond iD

Sensors · 2024

DOI: 10.3390/s24123898 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2024. Verfasst von Josh Cherian und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA. Hauptthemen laut MEDLINE: Activities of Daily Living, Machine Learning, Human Activities. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 90 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monitoring activities of daily living (ADLs) plays an important role in measuring and responding to a person’s ability to manage their basic physical needs. Effective recognition systems for monitoring ADLs must successfully recognize naturalistic activities that also realistically occur at infrequent intervals. However, existing systems primarily focus on either recognizing more separable, controlled activity types or are trained on balanced datasets where activities occur more frequently. In our work, we investigate the challenges associated with applying machine learning to an imbalanced dataset collected from a fully in-the-wild environment. This analysis shows that the combination of preprocessing techniques to increase recall and postprocessing techniques to increase precision can result in more desirable models for tasks such as ADL monitoring. In a user-independent evaluation using in-the-wild data, these techniques resulted in a model that achieved an event-based F1-score of over 0.9 for brushing teeth, combing hair, walking, and washing hands. This work tackles fundamental challenges in machine learning that will need to be addressed in order for these systems to be deployed and reliably work in the real world.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Activities of Daily LivingMachine LearningHuman ActivitiesHumansAlgorithmsWalkingPattern Recognition, Automated

Stichwörter der Autor:innen

activities of daily livingclass imbalancehuman activity recognitionin-the-wildpostprocessingpreprocessingsmartwatch

Autor:innen und Institutionen

  • Department of Computer Science & Engineering, Texas A&M University, College Station, TX 77843, USA.

ORCID-Profile: Josh Cherian, Samantha Ray, Paul Taele, Jung In Koh, Tracy Hammond

Förderung

  • National Science Foundation

Zitieren

APA

Cherian, J., Ray, S., Taele, P., Koh, J. I., & Hammond, T. (2024). Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition. Sensors. https://doi.org/10.3390/s24123898

Vancouver

Cherian J, Ray S, Taele P, Koh JI, Hammond T. Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition. Sensors. 2024. doi:10.3390/s24123898

BibTeX
@article{Cherian2024,
  author = {Cherian, Josh and Ray, Samantha and Taele, Paul and Koh, Jung In and Hammond, Tracy},
  title = {Exploring the Impact of the NULL Class on In-the-Wild Human Activity Recognition},
  journal = {Sensors},
  year = {2024},
  doi = {10.3390/s24123898}
}
Kostenlos starten →