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 Experiment Videos

Comparison of different classification algorithms for underwater target discrimination.

Donghui Li1, Mahmood R Azimi-Sadjadi, Marc Robinson

  • 1Department of Electrical and Computer Engineering, Colorado State University, Fort Collins, CO 80523, USA.

IEEE Transactions on Neural Networks
|September 25, 2004
PubMed
Summary

This study benchmarks acoustic classification algorithms for underwater targets using backscattered signals. It evaluates classifier performance and feature space properties against reverberation effects.

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

A Cohort Study of Emergency Department Trauma Evaluation and Outcomes by Incarceration Status.

Journal of correctional health care : the official journal of the National Commission on Correctional Health Care·2026
Same author

Plasmonic Re-Excitation Enables Superoxide-Mediated Ethane Conversion to Acetic Acid under Visible Light.

Journal of the American Chemical Society·2026
Same author

Integrative machine learning and experimental validation reveal the molecular mechanisms of 2-bromo-4,6-dinitroaniline nephrotoxicity: CD45 and cyclophilin C as early response biomarkers of renal tubular injury.

Toxicology and applied pharmacology·2026
Same author

Interacting and joint effects of frailty and depressive symptoms in relation to risk of cardio-oncology comorbidity in older adults from three prospective cohorts.

BMC geriatrics·2026
Same author

Addressing phase instability and charge recombination in pyrolysis-synthesized BiVO<sub>4</sub> via DFT-guided Mo doping for enhanced performance.

National science review·2026
Same author

Denitrification vs. assimilation: shifting metabolic pathways to enable N recovery from low-strength municipal wastewater.

Bioresource technology·2026

Area of Science:

  • Acoustics and Signal Processing
  • Underwater Target Recognition

Background:

  • Accurate classification of underwater targets is crucial for naval operations and marine research.
  • Acoustic backscattered signals provide rich information for target identification but are susceptible to environmental noise and reverberation.

Purpose of the Study:

  • To classify underwater targets using acoustic backscattered signals.
  • To benchmark various classification algorithms for performance and feature space insights.
  • To assess classifier robustness against reverberation.

Main Methods:

  • Utilized a wideband 80-kHz acoustic backscattered data set.
  • Collected data from six distinct underwater objects.
  • Applied and evaluated several different classification algorithms.

Related Experiment Videos

  • Benchmarked algorithm performance using Receiver Operating Characteristic (ROC) curves.

    • Main Results:

    • Presented classification performance metrics for tested algorithms.
    • Gained insights into the properties of the feature space for target classification.
    • Demonstrated the impact of reverberation on classifier robustness.

    Conclusions:

    • Specific classification algorithms show varying degrees of success in identifying underwater targets.
    • Understanding feature space properties is key to improving classification accuracy.
    • Classifier robustness to reverberation is a critical factor for real-world applications.