EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning

Hongyu Yang, Rou Dong, Rong Guo, Yonglin Che, Xiaolong Xie, Jianke Yang, Jiajin Zhang

Sensors · 12.03.2025 · 25 (6) · 1746

DOI: 10.3390/s25061746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 12.03.2025. Verfasst von Hongyu Yang und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, China. Hauptthemen laut MEDLINE: Deep Learning, Acoustics. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Agricultural University, Joint Special Project of Basic Research of Yunnan Province, Research on Undergraduate Education and Teaching Reform of Yunnan Agricultural University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The demand for intelligent monitoring systems tailored to elderly living environments is rapidly increasing worldwide with population aging. Traditional acoustic scene monitoring systems that rely on cloud computing are limited by data transmission delays and privacy concerns. Hence, this study proposes an acoustic scene recognition system that integrates edge computing with deep learning to enable real-time monitoring of elderly individuals’ daily activities. The system consists of low-power edge devices equipped with multiple microphones, portable wearable components, and compact power modules, ensuring its seamless integration into the daily lives of the elderly. We developed four deep learning models—convolutional neural network, long short-term memory, bidirectional long short-term memory, and deep neural network—and used model quantization techniques to reduce the computational complexity and memory usage, thereby optimizing them to meet edge device constraints. The CNN model demonstrated superior performance compared to the other models, achieving 98.5% accuracy, an inference time of 2.4 ms, and low memory requirements (25.63 KB allocated for Flash and 5.15 KB for RAM). This architecture provides an efficient, reliable, and user-friendly solution for real-time acoustic scene monitoring in elderly care.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAcousticsHumansAgedNeural Networks, ComputerActivities of Daily LivingWearable Electronic Devices

Stichwörter der Autor:innen

Internet of Things (IoT)acoustic scene recognitiondeep learningedge computinghealth monitoring

Autor:innen und Institutionen

  • College of Mechanical and Electrical Engineering, Yunnan Agricultural University, Kunming 650201, China.
  • Center for Sports Intelligence Innovation and Application, Yunnan Agricultural University, Kunming 650201, China.
  • College of Physical Education, Yunnan Agricultural University, Kunming 650201, China.
  • College of Big Data, Yunnan Agricultural University, Kunming 650201, China.

Förderung

  • Yunnan Agricultural University
  • Joint Special Project of Basic Research of Yunnan Province
  • Research on Undergraduate Education and Teaching Reform of Yunnan Agricultural University

Zitieren

APA

Yang, H., Dong, R., Guo, R., Che, Y., Xie, X., Yang, J., & Zhang, J. (2025). Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning. Sensors, 25(6), 1746. https://doi.org/10.3390/s25061746

Vancouver

Yang H, Dong R, Guo R, Che Y, Xie X, Yang J, et al. Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning. Sensors. 2025;25(6):1746. doi:10.3390/s25061746

BibTeX
@article{Yang2025,
  author = {Yang, Hongyu and Dong, Rou and Guo, Rong and Che, Yonglin and Xie, Xiaolong and Yang, Jianke and Zhang, Jiajin},
  title = {Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {6},
  pages = {1746},
  doi = {10.3390/s25061746}
}
Kostenlos starten →