EUVIMEDEUVIMED entdecken
Crossref

Deep transfer learning-based variable Doppler underwater acoustic communications

Yufei Liu, Yunjiang Zhao, Peter Gerstoft iD, Feng Zhou, Gang Qiao, Jingwei Yin

The Journal of the Acoustical Society of America · 01.07.2023 · 154 (1) · 232-244

DOI: 10.1121/10.0020147 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 13.07.2023. Verfasst von Yufei Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: National Key Laboratory of Underwater Acoustic Technology, Harbin Engineering University, Harbin 150001, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Acoustics. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 51 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a deep transfer learning (DTL)-based variable Doppler frequency-hopping binary frequency-shift keying underwater acoustic communication system. The system uses a convolutional neural network (CNN) as the demodulation module of the receiver. This approach directly demodulates the received signal without estimating the Doppler. The DTL first uses the simulated communication signal data to complete the CNN training. It then copies a part of the convolution layers from the pre-trained CNN to the target CNN. After randomly initializing the remaining layers for the target CNN, it is trained by the data samples from the specific communication scenarios. During the training process, the CNN learns the corresponding frequency from each symbol in the selected frequency-hopping group through the Mel-spectrograms. Simulation and experimental data processing results show that the performance of the proposed system is better than conventional systems, especially when the transmitter and receiver of the communication system are in variable speed motion in shallow water acoustic channels.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerAcousticsComputer SimulationLearningMachine Learning

Autor:innen und Institutionen

  • National Key Laboratory of Underwater Acoustic Technology, Harbin Engineering University, Harbin 150001, China.
  • Yichang Testing Technique Research Institute, Yichang City Hubei Province 443003, China.
  • NoiseLab, Scripps Institution of Oceanography, University of California San Diego, La Jolla, California 92093-0238, USA.

ORCID-Profile: Peter Gerstoft

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, Y., Zhao, Y., Gerstoft, P., Zhou, F., Qiao, G., & Yin, J. (2023). Deep transfer learning-based variable Doppler underwater acoustic communications. The Journal of the Acoustical Society of America, 154(1), 232-244. https://doi.org/10.1121/10.0020147

Vancouver

Liu Y, Zhao Y, Gerstoft P, Zhou F, Qiao G, Yin J. Deep transfer learning-based variable Doppler underwater acoustic communications. The Journal of the Acoustical Society of America. 2023;154(1):232-244. doi:10.1121/10.0020147

BibTeX
@article{Liu2023,
  author = {Liu, Yufei and Zhao, Yunjiang and Gerstoft, Peter and Zhou, Feng and Qiao, Gang and Yin, Jingwei},
  title = {Deep transfer learning-based variable Doppler underwater acoustic communications},
  journal = {The Journal of the Acoustical Society of America},
  year = {2023},
  volume = {154},
  number = {1},
  pages = {232--244},
  doi = {10.1121/10.0020147}
}
Kostenlos starten →