EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A New Deep-Learning Method for Human Activity Recognition

Roberta Vrskova iD, Patrik Kamencay iD, Robert Hudec iD, Peter Sykora

Sensors · 04.03.2023 · 23 (5) · 2816

DOI: 10.3390/s23052816 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 04.03.2023. Verfasst von Roberta Vrskova und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Multimedia and Information-Communication Technologies, University of Zilina, 010 26 Zilina, Slovakia. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 71-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Slovak Research and Development Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Currently, three-dimensional convolutional neural networks (3DCNNs) are a popular approach in the field of human activity recognition. However, due to the variety of methods used for human activity recognition, we propose a new deep-learning model in this paper. The main objective of our work is to optimize the traditional 3DCNN and propose a new model that combines 3DCNN with Convolutional Long Short-Term Memory (ConvLSTM) layers. Our experimental results, which were obtained using the LoDVP Abnormal Activities dataset, UCF50 dataset, and MOD20 dataset, demonstrate the superiority of the 3DCNN + ConvLSTM combination for recognizing human activities. Furthermore, our proposed model is well-suited for real-time human activity recognition applications and can be further enhanced by incorporating additional sensor data. To provide a comprehensive comparison of our proposed 3DCNN + ConvLSTM architecture, we compared our experimental results on these datasets. We achieved a precision of 89.12% when using the LoDVP Abnormal Activities dataset. Meanwhile, the precision we obtained using the modified UCF50 dataset (UCF50mini) and MOD20 dataset was 83.89% and 87.76%, respectively. Overall, our work demonstrates that the combination of 3DCNN and ConvLSTM layers can improve the accuracy of human activity recognition tasks, and our proposed model shows promise for real-time applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansNeural Networks, ComputerHuman ActivitiesRecognition, Psychology

Stichwörter der Autor:innen

3DCNNConvLSTMdeep learninghuman activity recognition

Autor:innen und Institutionen

  • Department of Multimedia and Information-Communication Technologies, University of Zilina, 010 26 Zilina, Slovakia.

ORCID-Profile: Roberta Vrskova, Patrik Kamencay, Robert Hudec

Förderung

  • Slovak Research and Development Agency

Zitieren

APA

Vrskova, R., Kamencay, P., Hudec, R., & Sykora, P. (2023). A New Deep-Learning Method for Human Activity Recognition. Sensors, 23(5), 2816. https://doi.org/10.3390/s23052816

Vancouver

Vrskova R, Kamencay P, Hudec R, Sykora P. A New Deep-Learning Method for Human Activity Recognition. Sensors. 2023;23(5):2816. doi:10.3390/s23052816

BibTeX
@article{Vrskova2023,
  author = {Vrskova, Roberta and Kamencay, Patrik and Hudec, Robert and Sykora, Peter},
  title = {A New Deep-Learning Method for Human Activity Recognition},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2816},
  doi = {10.3390/s23052816}
}
Kostenlos starten →