Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

FAK co-inhibition in KRAS<sup>G12C</sup>-mutated non-small-cell lung cancer.

The Lancet. Respiratory medicine·2026
Same author

Molecular residual disease-based novel modality of postoperative management for non-small-cell lung cancer (REMODEL): Protocol for a prospective multicenter study.

Journal of translational internal medicine·2026
Same author

Brief Report: Aumolertinib as a Switch Therapy in Osimertinib-Intolerant NSCLC: The ACTIVE Trial.

Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer·2026
Same author

Resistance architecture and breeding implications of blast and bacterial blight resistance genes in core WDR parents.

BMC plant biology·2026
Same author

Aumolertinib with or without chemotherapy in EGFR-mutated advanced non-small-cell lung cancer (AENEAS2): an open-label, multicentre, randomised, controlled, phase 3 trial.

The Lancet. Oncology·2026
Same author

MYBL2 impedes cisplatin sensitivity through suppressing GSDME-mediated pyroptosis in lung adenocarcinoma.

Cell death discovery·2026

Related Experiment Video

Updated: May 10, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K

Underwater Target Recognition Method Based on Singular Spectrum Analysis and Channel Attention Convolutional Neural

Fang Ji1, Shaoqing Lu1, Junshuai Ni1

  • 1China Ship Research and Development Academy, Beijing 100101, China.

Sensors (Basel, Switzerland)
|April 26, 2025
PubMed
Summary

A novel Singular Spectrum Analysis and Channel Attention Convolutional Neural Network (SSA-CACNN) model enhances underwater acoustic target recognition by efficiently separating noise. This SSA-CACNN model achieves high accuracy and robust performance with fewer parameters.

Keywords:
channel attention mechanismconvolutional neural networksingular spectrum analysisunderwater acoustic target recognition

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

430
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.2K

Related Experiment Videos

Last Updated: May 10, 2025

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

12.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

430
Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools
09:32

Development of New Methods for Quantifying Fish Density Using Underwater Stereo-video Tools

Published on: November 20, 2017

9.2K

Area of Science:

  • Acoustics
  • Signal Processing
  • Machine Learning

Background:

  • Underwater acoustic target recognition is crucial for marine applications.
  • Deep learning models face challenges in processing noisy radiated noise signals.
  • Existing methods often struggle with efficiency and robustness in complex acoustic environments.

Purpose of the Study:

  • To introduce an efficient and robust deep network model for underwater acoustic target recognition.
  • To improve the accuracy and reduce the computational complexity of radiated noise signal processing.
  • To enhance the model's ability to discern essential signal characteristics despite noise interference.

Main Methods:

  • Singular Spectrum Analysis (SSA) for noise separation and signal reconstruction.
  • Channel Attention Convolutional Neural Network (CACNN) for feature extraction and noise reduction.
  • Utilizing the first three orders of reconstructed signals as input to the CACNN model.

Main Results:

  • The SSA-CACNN model achieved 98.64% recognition accuracy on the ShipsEar dataset.
  • The model demonstrated robustness to noise, maintaining 84.61% accuracy at -10 dB SNR.
  • Achieved a low parameter count (0.26 M), indicating high efficiency.
  • Transfer learning to the DeepShip dataset yielded 94.98% accuracy.

Conclusions:

  • The SSA-CACNN model effectively processes radiated noise signals for underwater acoustic target recognition.
  • The model offers a superior balance of accuracy, efficiency, and noise robustness compared to other deep models.
  • The proposed method shows promise for real-world applications requiring reliable underwater acoustic target identification.