EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System

Haiyang Zhou, Yixin Zhao iD, Yanzhong Liu, Sichao Lu, Xiang An, Qiang Liu iD

Sensors · 14.05.2023 · 23 (10) · 4750

DOI: 10.3390/s23104750 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 14.05.2023. Verfasst von Haiyang Zhou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing 102617, China. Hauptthemen laut MEDLINE: Algorithms, Human Activities. Die Arbeit wurde bisher 50-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Education Commission, China, The Climbing Program Foundation from Beijing Institute of Petrochemical Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Human activity recognition (HAR) is becoming increasingly important, especially with the growing number of elderly people living at home. However, most sensors, such as cameras, do not perform well in low-light environments. To address this issue, we designed a HAR system that combines a camera and a millimeter wave radar, taking advantage of each sensor and a fusion algorithm to distinguish between confusing human activities and to improve accuracy in low-light settings. To extract the spatial and temporal features contained in the multisensor fusion data, we designed an improved CNN-LSTM model. In addition, three data fusion algorithms were studied and investigated. Compared to camera data in low-light environments, the fusion data significantly improved the HAR accuracy by at least 26.68%, 19.87%, and 21.92% under the data level fusion algorithm, feature level fusion algorithm, and decision level fusion algorithm, respectively. Moreover, the data level fusion algorithm also resulted in a reduction of the best misclassification rate to 2%~6%. These findings suggest that the proposed system has the potential to enhance the accuracy of HAR in low-light environments and to decrease human activity misclassification rates.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsHuman ActivitiesAgedHumansRadarRecognition, Psychology

Stichwörter der Autor:innen

CNN-LSTMfusion algorithmhuman activity recognitionmulti-sensor data fusion

Autor:innen und Institutionen

  • Academy of Artificial Intelligence, Beijing Institute of Petrochemical Technology, Beijing 102617, China.
  • Beijing Academy of Safety Engineering and Technology, Beijing 102617, China.

ORCID-Profile: Yixin Zhao, Qiang Liu

Förderung

  • Beijing Municipal Education Commission, China
  • The Climbing Program Foundation from Beijing Institute of Petrochemical Technology

Zitieren

APA

Zhou, H., Zhao, Y., Liu, Y., Lu, S., An, X., & Liu, Q. (2023). Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System. Sensors, 23(10), 4750. https://doi.org/10.3390/s23104750

Vancouver

Zhou H, Zhao Y, Liu Y, Lu S, An X, Liu Q. Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System. Sensors. 2023;23(10):4750. doi:10.3390/s23104750

BibTeX
@article{Zhou2023,
  author = {Zhou, Haiyang and Zhao, Yixin and Liu, Yanzhong and Lu, Sichao and An, Xiang and Liu, Qiang},
  title = {Multi-Sensor Data Fusion and CNN-LSTM Model for Human Activity Recognition System},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {10},
  pages = {4750},
  doi = {10.3390/s23104750}
}
Kostenlos starten →