EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet

Yier Lin iD, Haobo Li iD, Daniele Faccio iD

Sensors · 22.08.2024 · 24 (16) · 5450

DOI: 10.3390/s24165450 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.08.2024. Verfasst von Yier Lin und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China. Hauptthemen laut MEDLINE: Principal Component Analysis, Algorithms. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC IAA OSVMNC.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study introduces an innovative approach by incorporating statistical offset features, range profiles, time–frequency analyses, and azimuth–range–time characteristics to effectively identify various human daily activities. Our technique utilizes nine feature vectors consisting of six statistical offset features and three principal component analysis network (PCANet) fusion attributes. These statistical offset features are derived from combined elevation and azimuth data, considering their spatial angle relationships. The fusion attributes are generated through concurrent 1D networks using CNN-BiLSTM. The process begins with the temporal fusion of 3D range–azimuth–time data, followed by PCANet integration. Subsequently, a conventional classification model is employed to categorize a range of actions. Our methodology was tested with 21,000 samples across fourteen categories of human daily activities, demonstrating the effectiveness of our proposed solution. The experimental outcomes highlight the superior robustness of our method, particularly when using the Margenau–Hill Spectrogram for time–frequency analysis. When employing a random forest classifier, our approach outperformed other classifiers in terms of classification efficacy, achieving an average sensitivity, precision, F1, specificity, and accuracy of 98.25%, 98.25%, 98.25%, 99.87%, and 99.75%, respectively.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Principal Component AnalysisAlgorithmsHumansHuman ActivitiesRadarNeural Networks, ComputerActivities of Daily Living

Stichwörter der Autor:innen

CNN-BiLSTMfeature fusionhuman activity recognitionmmWavepoint cloud

Autor:innen und Institutionen

  • School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
  • Beijing Vocational College of Transport, Beijing 102618, China.
  • Department of Biomedical Engineering, School of Science and Engineering, University of Dundee, Dundee DD1 4HN, UK.
  • Extreme Light Group, School of Physics & Astronomy, University of Glasgow, Glasgow G12 8QQ, UK.

ORCID-Profile: Yier Lin, Haobo Li, Daniele Faccio

Förderung

  • EPSRC IAA OSVMNC

Zitieren

APA

Lin, Y., Li, H., & Faccio, D. (2024). Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet. Sensors, 24(16), 5450. https://doi.org/10.3390/s24165450

Vancouver

Lin Y, Li H, Faccio D. Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet. Sensors. 2024;24(16):5450. doi:10.3390/s24165450

BibTeX
@article{Lin2024,
  author = {Lin, Yier and Li, Haobo and Faccio, Daniele},
  title = {Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {16},
  pages = {5450},
  doi = {10.3390/s24165450}
}
Kostenlos starten →