EUVIMEDEUVIMED entdecken
Crossref

Underwater target classification based on the combination of dolphin click trains and convolutional neural networks

Wenjie Xiang, Zhongchang Song, Zhanyuan Gao, Boyu Zhang, Weijie Fu, Chuang Zhang, Yu Zhang iD

The Journal of the Acoustical Society of America · 01.02.2025 · 157 (2) · 647-658

DOI: 10.1121/10.0035571 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, online erschienen am 03.02.2025. Verfasst von Wenjie Xiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Key Laboratory of Underwater Acoustic Communication and Marine Information Technology of the Ministry of Education, College of Ocean and Earth Scienc…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Foundation for Innovative Research Groups of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sonar remains a major way to detect and discriminate underwater targets by interpreting the echoes. In this study, we used broadband dolphin clicks to detect and classify targets. The peak and notch features of the echo spectra were coded, and echoes were obtained using five-click trains, with the number of clicks changing from 1 to 50. Codes containing the target interpretation were classified by convolutional neural networks (CNNs). Compared to a single click, the increasing number of clicks to 5, 10, 20, and 50 in a train would gradually improve the classification rate of targets by 3%, 6.1%, 8.2%, and 10.5% on average with a signal-to-noise ratio ranging from –10 to 15 dB. The 50-click train outperformed other click trains in target detection and classification. The CNNs achieved an average classification accuracy of 95.2% for a 50-click train, higher than that of the nearest neighbor method by 10.3% across signal-to-noise ratios. Therefore, the usage of dolphin clicks and CNN-based echo encoding technologies constitutes an effective method for enhancing target classification, offering valuable insights for future applications in detecting underwater targets.

Autor:innen und Institutionen

  • Key Laboratory of Underwater Acoustic Communication and Marine Information Technology of the Ministry of Education, College of Ocean and Earth Sciences, Xiamen University, Xiamen, 361005, China.

ORCID-Profile: Yu Zhang

Förderung

  • Foundation for Innovative Research Groups of the National Natural Science Foundation of China

Zitieren

APA

Xiang, W., Song, Z., Gao, Z., Zhang, B., Fu, W., Zhang, C., & Zhang, Y. (2025). Underwater target classification based on the combination of dolphin click trains and convolutional neural networks. The Journal of the Acoustical Society of America, 157(2), 647-658. https://doi.org/10.1121/10.0035571

Vancouver

Xiang W, Song Z, Gao Z, Zhang B, Fu W, Zhang C, et al. Underwater target classification based on the combination of dolphin click trains and convolutional neural networks. The Journal of the Acoustical Society of America. 2025;157(2):647-658. doi:10.1121/10.0035571

BibTeX
@article{Xiang2025,
  author = {Xiang, Wenjie and Song, Zhongchang and Gao, Zhanyuan and Zhang, Boyu and Fu, Weijie and Zhang, Chuang and Zhang, Yu},
  title = {Underwater target classification based on the combination of dolphin click trains and convolutional neural networks},
  journal = {The Journal of the Acoustical Society of America},
  year = {2025},
  volume = {157},
  number = {2},
  pages = {647--658},
  doi = {10.1121/10.0035571}
}
Kostenlos starten →