EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Machine Learning Techniques for Sensor-Based Human Activity Recognition with Data Heterogeneity—A Review

Xiaozhou Ye iD, Kouichi Sakurai, Nirmal-Kumar C Nair, Kevin I-Kai Wang iD

Sensors · 13.12.2024 · 24 (24) · 7975

DOI: 10.3390/s24247975 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Sensors, online erschienen am 13.12.2024. Verfasst von Xiaozhou Ye und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical, Computer, and Software Engineering, The University of Auckland, Auckland 1010, New Zealand. Hauptthemen laut MEDLINE: Machine Learning, Human Activities. Die Arbeit wurde bisher 52-mal zitiert (Crossref) und nennt 123 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Te Hiranga Rū QuakeCoRE, an Aotearoa New Zealand Tertiary Education Commission-funded Centre, International Exchange, Foreign Researcher Invitation Program of National Institute of Information and Communications Technology (NICT).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sensor-based Human Activity Recognition (HAR) is crucial in ubiquitous computing, analyzing behaviors through multi-dimensional observations. Despite research progress, HAR confronts challenges, particularly in data distribution assumptions. Most studies assume uniform data distributions across datasets, contrasting with the varied nature of practical sensor data in human activities. Addressing data heterogeneity issues can improve performance, reduce computational costs, and aid in developing personalized, adaptive models with fewer annotated data. This review investigates how machine learning addresses data heterogeneity in HAR by categorizing data heterogeneity types, applying corresponding suitable machine learning methods, summarizing available datasets, and discussing future challenges.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningHuman ActivitiesHumansAlgorithms

Stichwörter der Autor:innen

data heterogeneitydata out of distributionhuman activity recognitiontime-series classification

Autor:innen und Institutionen

  • Department of Electrical, Computer, and Software Engineering, The University of Auckland, Auckland 1010, New Zealand.
  • Department of Informatics, Kyushu University, Fukuoka 819-0395, Japan.

ORCID-Profile: Xiaozhou Ye, Kevin I-Kai Wang

Förderung

  • Te Hiranga Rū QuakeCoRE, an Aotearoa New Zealand Tertiary Education Commission-funded Centre
  • International Exchange, Foreign Researcher Invitation Program of National Institute of Information and Communications Technology (NICT)

Zitieren

APA

Ye, X., Sakurai, K., Nair, N. C., & Wang, K. I. (2024). Machine Learning Techniques for Sensor-Based Human Activity Recognition with Data Heterogeneity—A Review. Sensors, 24(24), 7975. https://doi.org/10.3390/s24247975

Vancouver

Ye X, Sakurai K, Nair NC, Wang KI. Machine Learning Techniques for Sensor-Based Human Activity Recognition with Data Heterogeneity—A Review. Sensors. 2024;24(24):7975. doi:10.3390/s24247975

BibTeX
@article{Ye2024,
  author = {Ye, Xiaozhou and Sakurai, Kouichi and Nair, Nirmal-Kumar C and Wang, Kevin I-Kai},
  title = {Machine Learning Techniques for Sensor-Based Human Activity Recognition with Data Heterogeneity—A Review},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {24},
  pages = {7975},
  doi = {10.3390/s24247975}
}
Kostenlos starten →