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

Multiple Pipe Systems01:21

Multiple Pipe Systems

738
Multipipe systems consist of complex configurations of interconnected pipes designed to transport fluids efficiently across intricate networks. They are essential in engineering applications requiring precise control over flow distribution, pressure, and head loss. They are categorized into series, parallel, loop, and network configurations, each distinguished by unique flow characteristics and applications.
Series Configuration
In a series configuration, fluid flows sequentially from one pipe...
738
Design Example: Designing a Residential Plumbing System01:25

Design Example: Designing a Residential Plumbing System

671
The design of residential plumbing systems requires carefully evaluating water demand, flow rates, and pressure dynamics to ensure both efficiency and reliability. The nature of water flow within pipes is defined by its Reynolds number, which classifies flow as either laminar (smooth) or turbulent.
671
Rapidly Varying Flow01:24

Rapidly Varying Flow

57
Rapidly varying flow (RVF) in open channels is characterized by abrupt changes in flow depth over a short distance, with the rate of depth change relative to distance often approaching unity. These flows are inherently complex due to their transient and multi-dimensional nature, making exact analysis difficult. However, approximate solutions using simplified models provide valuable insights into their behavior.Key Features of Rapidly Varying FlowRVF is commonly observed in scenarios involving...
57

You might also read

Related Articles

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

Sort by
Same author

Spatial organization of the TNBC tumor microenvironment: multicellular niches, T-cell bottlenecks, and therapeutic opportunities.

Journal of translational medicine·2026
Same author

Sivelestat sodium alleviates sepsis-associated acute lung injury by inhibiting ferroptosis via the Nrf2/SLC7A11/GPX4 axis.

PloS one·2026
Same author

Co-delivery of glabridin and uralsaponin X with lipid nanoparticles inhibits melanogenesis and melanin transfer.

Colloids and surfaces. B, Biointerfaces·2026
Same author

Fenazaquin impairs liver development and metabolic homeostasis in zebrafish (Danio rerio) by disrupting glucose and lipid metabolism.

Toxicology letters·2026
Same author

Morphology Engineering of Co<sub>3</sub>O<sub>4</sub> via Cetyltrimethylammonium Bromide-Mediated ZIF-67 Synthesis for Efficient Photo-Assisted Electrooxidation of Methanol.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

Solvation Chemistry Reimagined: LiPF6-Enabled Suppression of Gas Evolution for Ultra-Stable 200 Ah Anode-Free Lithium-Metal Batteries.

Advanced materials (Deerfield Beach, Fla.)·2026

Related Experiment Video

Updated: Jun 22, 2025

Design and Use of a Full Flow Sampling System FFS for the Quantification of Methane Emissions
08:18

Design and Use of a Full Flow Sampling System FFS for the Quantification of Methane Emissions

Published on: June 12, 2016

16.7K

Advancing deep learning-based acoustic leak detection methods towards application for water distribution systems from

Yipeng Wu1, Xingke Ma1, Guancheng Guo1

  • 1School of Environment, Tsinghua University, 100084, Beijing, China.

Water Research
|June 28, 2024
PubMed
Summary

Data augmentation significantly improves deep learning for acoustic leak detection in water distribution systems (WDSs). Techniques like IAAFT and masking enhance accuracy by increasing data diversity and focusing on global features.

Keywords:
Acoustic leak detectionConvolutional neural networkData augmentationTime–frequency spectrogramWater distribution system

More Related Videos

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds
06:37

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds

Published on: November 13, 2017

9.2K
Studying Cavitation Enhanced Therapy
07:36

Studying Cavitation Enhanced Therapy

Published on: April 9, 2021

5.2K

Related Experiment Videos

Last Updated: Jun 22, 2025

Design and Use of a Full Flow Sampling System FFS for the Quantification of Methane Emissions
08:18

Design and Use of a Full Flow Sampling System FFS for the Quantification of Methane Emissions

Published on: June 12, 2016

16.7K
Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds
06:37

Continuous Hydrologic and Water Quality Monitoring of Vernal Ponds

Published on: November 13, 2017

9.2K
Studying Cavitation Enhanced Therapy
07:36

Studying Cavitation Enhanced Therapy

Published on: April 9, 2021

5.2K

Area of Science:

  • Engineering
  • Computer Science
  • Environmental Science

Background:

  • Water distribution systems (WDSs) face significant leakage challenges.
  • Deep learning for acoustic leak detection is promising but data-dependent.
  • Existing research often overlooks data augmentation's role.

Purpose of the Study:

  • To investigate the impact of data augmentation on deep learning-based acoustic leak detection.
  • To evaluate five random transformation-based augmentation techniques.
  • To enhance the performance and reliability of AI-driven leak detection in WDSs.

Main Methods:

  • Applied jittering, scaling, warping, iterated amplitude adjusted Fourier transform (IAAFT), and masking to acoustic signals from a real-world WDS.
  • Used convolutional neural network (CNN) classifiers to analyze augmented acoustic signal spectrograms.
  • Implemented data augmentation prior to data splitting to avoid data leakage.

Main Results:

  • Data augmentation is crucial for preventing data leakage and overly optimistic results.
  • IAAFT improved recognition accuracy by over 7% by increasing data volume and diversity.
  • Masking improved performance by encouraging the CNN to learn global spectrogram features.
  • Sequential application of IAAFT and masking further boosted leak detection performance.
  • Data augmentation enhanced the effectiveness of transfer learning with complex models.

Conclusions:

  • Data augmentation is vital for advancing AI-driven acoustic leak detection technology.
  • IAAFT and masking are effective techniques for improving leak detection accuracy.
  • A data-centric approach, including augmentation, is key for mature applications in WDSs.