EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LW-MS-LFTFNet: A Lightweight Multi-Scale Network Integrating Low-Frequency Temporal Features for Ship-Radiated Noise Recognition

Yu Feng, Zhangxin Chen, Yixuan Chen, Ziqin Xie, Jiale He, Jiachang Li, Houqian Ding, Tao Guo, Kai Chen

Journal of Marine Science and Engineering · 31.10.2025 · 13 (11) · 2073

DOI: 10.3390/jmse13112073 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 31.10.2025. Verfasst von Yu Feng und 8 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ship-radiated noise (SRN) recognition is vital for underwater acoustics, with applications in both military and civilian fields. Traditional manual recognition by sonar operators is inefficient and error-prone, motivating the development of automated recognition systems. However, most existing deep learning approaches demand high computational resources, limiting their deployment on resource-constrained edge devices. To overcome this challenge, we propose LW-MS-LFTFNet, a lightweight model informed by time-frequency analysis of SRN that highlights the critical role of low-frequency components. The network integrates a multi-scale depthwise separable convolutional backbone with CBAM attention for efficient spectral representation, along with two LSTM-based modules to capture temporal dependencies in low-frequency bands. Experiments on the DeepShip dataset show that LW-MS-LFTFNet achieves 75.04% accuracy with only 0.85 M parameters, 0.38 GMACs, and 3.27 MB of storage, outperforming representative lightweight architectures. Ablation studies further confirm that low-frequency temporal modules contribute complementary gains, improving accuracy by 2.64% with minimal overhead. Guided by domain-specific priors derived from time-frequency pattern analysis, LW-MS-LFTFNet achieves efficient and accurate SRN recognition with strong potential for edge deployment.

Zitieren

APA

Feng, Y., Chen, Z., Chen, Y., Xie, Z., He, J., Li, J., Ding, H., Guo, T., & Chen, K. (2025). LW-MS-LFTFNet: A Lightweight Multi-Scale Network Integrating Low-Frequency Temporal Features for Ship-Radiated Noise Recognition. Journal of Marine Science and Engineering, 13(11), 2073. https://doi.org/10.3390/jmse13112073

Vancouver

Feng Y, Chen Z, Chen Y, Xie Z, He J, Li J, et al. LW-MS-LFTFNet: A Lightweight Multi-Scale Network Integrating Low-Frequency Temporal Features for Ship-Radiated Noise Recognition. Journal of Marine Science and Engineering. 2025;13(11):2073. doi:10.3390/jmse13112073

BibTeX
@article{Feng2025,
  author = {Feng, Yu and Chen, Zhangxin and Chen, Yixuan and Xie, Ziqin and He, Jiale and Li, Jiachang and Ding, Houqian and Guo, Tao and Chen, Kai},
  title = {LW-MS-LFTFNet: A Lightweight Multi-Scale Network Integrating Low-Frequency Temporal Features for Ship-Radiated Noise Recognition},
  journal = {Journal of Marine Science and Engineering},
  year = {2025},
  volume = {13},
  number = {11},
  pages = {2073},
  doi = {10.3390/jmse13112073}
}
Kostenlos starten →