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

Uniform Depth Channel Flow: Problem Solving01:18

Uniform Depth Channel Flow: Problem Solving

To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...
Buoyancy and Stability for Submerged and Floating Bodies01:11

Buoyancy and Stability for Submerged and Floating Bodies

In fluid mechanics, buoyancy and stability are key concepts for understanding the behavior of submerged and floating bodies. When a stationary body is fully or partially submerged in a fluid, the fluid exerts a force on the body known as the buoyant force. This force acts vertically upward through a point called the center of buoyancy, which is the center of the displaced fluid volume. According to Archimedes' principle, the magnitude of the buoyant force is equal to the weight of the fluid...

You might also read

Related Articles

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

Sort by
Same author

Migration Patterns and Meteorological Drivers of the Rice Leaf Roller in Western Hunan Province, China.

Insects·2026
Same author

Computational insights on the molecular interplay between KRas (G12D mutation) and SOS1 modulated by the inhibitor BI-3406.

PLoS computational biology·2026
Same author

An isaindigotone-based NIR fluorogenic probe for visualizing mitochondrial DNA G-quadruplexes in living cells.

Chemical communications (Cambridge, England)·2026
Same author

Construction and application of multiple nucleotide polymorphism-based DNA fingerprinting for <i>Polygonatum cyrtonema</i> identification.

Frontiers in plant science·2026
Same author

Impact of 2 types of El Niño events and La Niña events on the occurrence degree and immigration period of Nilaparvata lugens (Stål) in the rice-growing regions of South China.

Journal of economic entomology·2026
Same author

Predicting wheat powdery mildew epidemics in China using meteorological data and machine learning approaches.

Pest management science·2025

Related Experiment Video

Updated: Jul 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

A multi-task neural network for source localization in shallow-water environment with depth classification.

Jing Guo1,2, Juan Zeng1

  • 1Key Laboratory of Underwater Acoustic Environment, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China.

JASA Express Letters
|July 15, 2026
PubMed
Summary

This study introduces a novel multi-task neural network to improve deep learning-based source localization. The network effectively mitigates overfitting and enhances performance, even with limited data, by incorporating depth classification.

Related Experiment Videos

Last Updated: Jul 17, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Area of Science:

  • Acoustics
  • Machine Learning
  • Signal Processing

Background:

  • Deep learning models for source localization often suffer from overfitting and poor generalization due to limited high-quality training data.
  • This degradation in performance is particularly problematic in realistic, complex environments.
  • Existing methods struggle to effectively regularize depth estimation, a critical component of accurate localization.

Purpose of the Study:

  • To develop a novel multi-task neural network architecture for improved deep-learning-based source localization.
  • To address the challenges of overfitting and weak generalization in source localization models.
  • To enhance the performance of source localization systems using limited measurement data through transfer learning.

Main Methods:

  • A multi-task neural network was designed, featuring a depth-classification branch alongside a range-regression branch.
  • The depth-classification branch leverages the characteristics of a vertical line array and depth-dependent localization ambiguity surfaces.
  • Transfer learning techniques were employed, bridging the gap between simulated and experimental data for model fine-tuning.

Main Results:

  • The proposed depth-classification branch effectively regularized depth estimation and reduced model complexity, mitigating overfitting in the range-regression task.
  • The multi-task network demonstrated significantly improved source localization performance compared to baseline methods.
  • Validation using both simulated and experimental datasets confirmed the network's enhanced accuracy and robustness.

Conclusions:

  • The developed multi-task neural network with a depth-classification branch offers a robust solution for deep-learning-based source localization.
  • The integration of depth classification and transfer learning successfully overcomes the limitations of sparse data and improves generalization.
  • This approach provides a promising direction for enhancing the reliability and accuracy of acoustic source localization systems in practical applications.