EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition

Memoona, Muhammad Haseeb Hashir, Sung Won Kim iD

PLOS One · 30.10.2026 · 21 (10) · e0359774

DOI: 10.1371/journal.pone.0359774 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 30.10.2026. Verfasst von Memoona und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, Gyeongbuk, Republic of Korea. Hauptthemen laut MEDLINE: Wearable Electronic Devices, Human Activities. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yeungnam University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

UniHAR is a lightweight hierarchical multi-scale transformer based on wearable sensor data that has to be able to model time well; be able to recognize human activity across different datasets; and do so in real-time. There are several problems with what currently exists. UniHAR uses four major components: universal channel harmonization; adaptive multi-scale patch embedding; scale-adaptive Fourier cross-attention; factorized temporal-channel attention. The components allow for the ability to use various sensors and enables the low-complexity multi-scale fusion of features. UniHAR achieved an accuracy of 96.35%; 94.45%; 96.44%; and 99.23% on UCI-HAR, Opportunity, Daphnet, and PAMAP2 datasets, while being very lightweight and having high-speed inference capabilities; therefore, UniHAR is suitable for real-time healthcare applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Wearable Electronic DevicesHuman ActivitiesHumansAlgorithms

Autor:innen und Institutionen

  • Department of Information and Communication Engineering, Yeungnam University, Gyeongsan, Gyeongbuk, Republic of Korea.
  • School of Computer Science and Engineering, Yeungnam University, Gyeongsan, Gyeongbuk, Republic of Korea.

ORCID-Profile: Sung Won Kim

Förderung

  • Yeungnam University

Zitieren

APA

Memoona, Hashir, M. H., & Kim, S. W. (2026). UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition. PLOS One, 21(10), e0359774. https://doi.org/10.1371/journal.pone.0359774

Vancouver

Memoona, Hashir MH, Kim SW. UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition. PLOS One. 2026;21(10):e0359774. doi:10.1371/journal.pone.0359774

BibTeX
@article{Memoona2026,
  author = {Memoona and Hashir, Muhammad Haseeb and Kim, Sung Won},
  title = {UniHAR: A unified hierarchical transformer with multi-scale temporal modeling for wearable human activity recognition},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {10},
  pages = {e0359774},
  doi = {10.1371/journal.pone.0359774}
}
Kostenlos starten →