Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Sep 11, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Bridge Damage Identification Using Time-Varying Filtering-Based Empirical Mode Decomposition and Pre-Trained

Shenghuan Zeng¹, Jian Cui², Ding Luo¹

¹Shenzhen Expressway Engineering Testing Co., Ltd., Shenzhen 518000, China.

Sensors (Basel, Switzerland)

|August 14, 2025

Summary

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

Improved catalytic efficiency of P450 OleP for converting lithocholic acid into murideoxycholic and ursodeoxycholic acids through semi-rational and rational design.

Synthetic and systems biotechnology·2026

Same author

A bibliometric analysis of research trends and future directions in early detection of pancreatic cancer.

Discover oncology·2026

Same author

Discovery of selective CDK9 degraders with anti-AML activity using PROTAC technology.

Bioorganic chemistry·2026

Same author

An unexpected NH<sub>4</sub>HSO<sub>4</sub>-catalyzed C3-H alkenylation of quinoxalin-2(1<i>H</i>)-ones with allenes.

Chemical communications (Cambridge, England)·2026

Same author

Weakly-supervised deep learning on pathological whole-slide images for cutaneous vasculitis and its mimickers: a high-performance diagnostic support tool.

Scientific reports·2026

Same author

Antibiotic-Loaded Polymethyl Methacrylate Cement Drives Fibroblast-Mediated Angiogenesis via LOXL2 to Accelerate Diabetic Foot Ulcer Healing.

FASEB journal : official publication of the Federation of American Societies for Experimental Biology·2026

This summary is machine-generated.

This study introduces a novel framework for bridge damage identification using time-varying filtering empirical mode decomposition (TVFEMD) and convolutional neural networks (CNNs). The method improves signal quality and enhances damage classification accuracy for better bridge health monitoring.

Area of Science:

Structural Engineering
Signal Processing
Artificial Intelligence

Background:

Bridge health monitoring is crucial for operational safety and maintenance.
Current methods face challenges with poor signal quality, feature extraction, and classification accuracy.

Purpose of the Study:

To develop an advanced framework for accurate bridge damage identification.
To overcome limitations in signal processing and classification for bridge health monitoring.

Main Methods:

Integration of time-varying filtering-based empirical mode decomposition (TVFEMD) with pre-trained convolutional neural networks (CNNs).
Adaptive denoising and time-frequency reconstruction to enhance signal features and suppress noise.
Comparative analysis of different CNN models (ResNet-50) for damage classification.

Keywords:

convolutional neural network signal processing structural damage identification structural health monitoring time-frequency analysis

More Related Videos

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Related Experiment Videos

Last Updated: Sep 11, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

Main Results:

TVFEMD demonstrated superior frequency separation and modal purity compared to traditional EMD.
ResNet-50 achieved optimal performance in damage classification with TVFEMD-processed signals.
Principal Component Analysis (PCA) visualization confirmed improved feature clustering and separability.

Conclusions:

The proposed TVFEMD-CNN framework significantly enhances bridge damage identification accuracy.
TVFEMD effectively preprocesses signals, improving CNN model adaptability and recognition.
This approach offers a robust solution for practical bridge health monitoring challenges.