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

You might also read

Related Articles

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

Sort by
Same author

Core-shell CuFeMnHCF@CuHCF: a high-rate and durable Prussian blue cathode for sodium-ion batteries.

Chemical communications (Cambridge, England)·2026
Same author

Injectable thermosensitive hydrogel embedding lignin-modified PLGA microspheres enables sustained lidocaine release and prolonged neuromodulation.

International journal of biological macromolecules·2026
Same author

Pharmacological Strategies for Preventing Postoperative Recurrence in Crohn's Disease: A Systematic Review and Network Meta-Analysis of Randomized Controlled Trials.

Medicina (Kaunas, Lithuania)·2026
Same author

Lactylation and targeted therapy resistance in hepatocellular carcinoma.

Clinical epigenetics·2026
Same author

Nano-geo interfaces in urinary stone formation: linking drinking water geochemistry to calcium oxalate crystallization dynamics.

Environmental geochemistry and health·2026
Same author

Clustering ensemble method integrating Gaussian mixture model and three-way decision (GMM-3WD-CE).

Scientific reports·2026

Related Experiment Video

Updated: May 13, 2025

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K

Spatio-temporal crash severity analysis with cost-sensitive multi-graphs attention network.

Jianwu Wan1, Siying Zhu2, Yunpeng Ma1

  • 1School of Information Science and Engineering, Hohai University, PR China.

Accident; Analysis and Prevention
|April 17, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a cost-sensitive multi-graphs attention network (CSmGAT) for crash severity analysis. The novel model significantly reduces misclassification losses by prioritizing severe crash factors and capturing spatio-temporal patterns.

Keywords:
Attention mechanismCost-sensitive learningCrash severity analysisSpatio-temporal heterogeneityUnequal misclassification losses

More Related Videos

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.4K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K

Related Experiment Videos

Last Updated: May 13, 2025

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.4K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K

Area of Science:

  • Transportation Engineering
  • Data Science
  • Machine Learning

Background:

  • Conventional crash severity models assume equal losses for all errors, overlooking the greater importance of identifying factors for severe crashes.
  • Existing models struggle with spatio-temporal heterogeneity, often using simpler statistical or machine learning approaches.

Purpose of the Study:

  • To reformulate crash severity analysis as a cost-sensitive learning problem, assigning differential costs to misclassification errors.
  • To develop an advanced deep learning model for accurately capturing spatio-temporal crash severity structures.
  • To propose a novel cost-sensitive multi-graphs attention network (CSmGAT) for improved crash analysis.

Main Methods:

  • Developed a cost matrix to define unequal misclassification losses in crash severity analysis.
  • Introduced a multi-graphs attention mechanism based on graph convolutional networks to model spatio-temporal heterogeneity.
  • Proposed the CSmGAT model integrating cost-sensitivity and graph attention for learning optimal spatio-temporal crash affiliations.

Main Results:

  • The CSmGAT model reduced overall misclassification losses by at least 11.31% compared to 23 state-of-the-art models.
  • Effectively filtered erroneous affiliations in pre-defined spatio-temporal graphs using multi-graphs attention convolutions.
  • Identified and interpreted significant crash contributing factors using pseudo-elasticity values.

Conclusions:

  • The CSmGAT model offers a superior approach to crash severity analysis by addressing cost-sensitivity and spatio-temporal complexities.
  • The cost-sensitive framework and graph attention mechanism enhance the accuracy and interpretability of crash contributing factor identification.
  • This research advances the application of deep learning in transportation safety by providing a more nuanced understanding of crash severity.