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 Video

Updated: Apr 28, 2026

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

1.3K

An adaptive deep neural network for active road noise control.

Lu Bai1,2, Jin-Pei Xue1, Si-Yuan Lian1,2

  • 1Key Laboratory of Modern Acoustics and Institute of Acoustics, Nanjing University, Nanjing 210093, China.

The Journal of the Acoustical Society of America
|April 27, 2026
PubMed
Summary

Related Concept Videos

Active Filters01:25

Active Filters

1.4K
Active filters are electronic circuits that use operational amplifiers (op-amps), resistors, and capacitors to filter out unwanted frequency components from a signal. A first-order low-pass active filter is designed to pass signals with a frequency lower than a certain cutoff frequency and attenuate frequencies higher than that cutoff frequency. The transfer function for a first-order low-pass active filter is:
1.4K

You might also read

Related Articles

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

Sort by
Same author

Construction and multi-omics validation of a five-gene ferroptosis-based model for predicting prognosis and therapy response in pancreatic ductal adenocarcinoma with immune landscape analysis.

Discover oncology·2026
Same author

Chemical Proteomics Reveals a Novel Long-Acting Maleimide Algaecide Targeting Glyceraldehyde-3-Phosphate Dehydrogenase for Cyanobacterial Bloom Control.

Journal of agricultural and food chemistry·2026
Same author

Randomized trial of self-adaptive computerized cognitive remediation in schizophrenia.

NPJ digital medicine·2026
Same author

DeepDOX1: A Dual-Drive Framework Integrating Deep Learning and First-Principles Quantum Chemistry for Drug-Protein Affinity Prediction.

JACS Au·2026
Same author

Dual Photoredox/Cobalt Catalysis Enabled Regiospecific Markovnikov Hydroboration of Unactivated Mono-, Di-, and Trisubstituted Alkenes.

Nature communications·2026
Same author

Molecular mechanisms of the MLL4 complex in H3K4 methylation and p53-dependent transcription activation.

Molecular cell·2026

This study introduces an adaptive neural network for active road noise control (ARNC) that overcomes real-world noise variations. The novel approach enhances deep learning models with minimal cost, improving performance and generalization in practical applications.

Area of Science:

  • Automotive Engineering
  • Acoustics
  • Artificial Intelligence

Background:

  • Active road noise control (ARNC) systems are crucial for reducing low-frequency noise in vehicle cabins.
  • Deep neural network (DNN)-based frameworks like WaveNet-VNN show promise but struggle with real-world noise variations.
  • Limited training data and changing road conditions hinder the generalization of current DNN-based ARNC methods.

Purpose of the Study:

  • To develop an adaptive neural network for ARNC that maintains high performance while adapting to changing noise conditions.
  • To enhance the robustness and generalization of DNN-based ARNC systems for practical, real-world deployment.
  • To introduce a computationally efficient adaptation mechanism for pre-trained DNN models.

Main Methods:

Related Experiment Videos

Last Updated: Apr 28, 2026

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

1.3K
  • Integration of lightweight Adapter modules into a pre-trained WaveNet-VNN model for online adaptation.
  • Minimal increase in model parameters and computational cost (only 5%) through the use of adapter modules.
  • Experimental validation on a 42×2×2 ARNC system under various road conditions and vehicle speeds.

    • Main Results:

    • The proposed adaptive neural network outperforms the ideal Wiener solution under cross-day distribution shifts.
    • Consistent superior performance across different vehicle speeds was observed.
    • The approach demonstrated convergence speed comparable to state-of-the-art traditional algorithms and strong robustness.

    Conclusions:

    • The adaptive neural network offers a feasible and effective solution for real-world DNN-based ARNC systems.
    • The integration of adapter modules allows for efficient online adaptation without significant performance degradation.
    • The method successfully addresses the generalization limitations of DNN-based ARNC in dynamic environments.