EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Real-Time Multi-Class Human Activity Monitoring System Using mmWave Radar

Doheon Kim, Sol Lee, Myeongjin Lee iD

Sensors · 2026

DOI: 10.3390/s26103145 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2026. Verfasst von Doheon Kim und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronics and Information Engineering, Korea Aerospace University, Goyang 10540, Gyeonggi, Republic of Korea. Hauptthemen laut MEDLINE: Radar, Human Activities. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Information & Communications Technology Planning & Evaluation, Ministry of the Interior and Safety, Korea Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents a robust and efficient mmWave radar-based human activity recognition (HAR) framework optimized for practical real-time indoor deployment. Addressing computational inefficiencies and limited recognition scopes in existing systems, the framework introduces two core contributions: Multi-class Spatio-Temporal Network (MuST-Net), a lightweight, multi-class network, and an online detection process for enhanced temporal stability. MuST-Net utilizes a hybrid 2D convolutional neural network and temporal convolutional network architecture to recognize seven distinct classes, significantly broadening the system’s recognition repertoire. The online detection process implements a novel sliding-window post-processing chain that employs an activity-buffering mechanism, which maintains temporal continuity and effectively suppresses spurious detections at activity boundaries. Experimental results demonstrate the superior performance of our unified framework, attaining over 98.6% accuracy for multi-class classification by MuST-Net and achieving at least 97% accuracy for activity detection and a crucial 100% recall for fall detection. Robustness is validated across three distinct indoor environments and nine subjects—with two of the three sites entirely unseen during training—confirming strong generalization under installation, environment, and subject variations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadarHuman ActivitiesHumansAlgorithmsConvolutional Neural NetworksNeural Networks, ComputerMonitoring, Physiologic

Stichwörter der Autor:innen

human activity recognitionmmWave radaronline activity monitoringrange–Doppler map

Autor:innen und Institutionen

  • School of Electronics and Information Engineering, Korea Aerospace University, Goyang 10540, Gyeonggi, Republic of Korea.
  • Department of Smart Air Mobility, Korea Aerospace University, Goyang 10540, Gyeonggi, Republic of Korea.

ORCID-Profile: Myeongjin Lee

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation
  • Ministry of the Interior and Safety
  • Korea Government

Zitieren

APA

Kim, D., Lee, S., & Lee, M. (2026). A Real-Time Multi-Class Human Activity Monitoring System Using mmWave Radar. Sensors. https://doi.org/10.3390/s26103145

Vancouver

Kim D, Lee S, Lee M. A Real-Time Multi-Class Human Activity Monitoring System Using mmWave Radar. Sensors. 2026. doi:10.3390/s26103145

BibTeX
@article{Kim2026,
  author = {Kim, Doheon and Lee, Sol and Lee, Myeongjin},
  title = {A Real-Time Multi-Class Human Activity Monitoring System Using mmWave Radar},
  journal = {Sensors},
  year = {2026},
  doi = {10.3390/s26103145}
}
Kostenlos starten →