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: Jun 6, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Analyzing angle crashes at unsignalized intersections using machine learning techniques.

Mohamed Abdel-Aty1, Kirolos Haleem

  • 1Department of Civil, Environmental & Construction Engineering, University of Central Florida, Orlando, FL 32816-2450, United States. mabdel@mail.ucf.edu

Accident; Analysis and Prevention
|November 25, 2010
PubMed
Summary

Multivariate adaptive regression splines (MARS) effectively predict angle crashes at unsignalized intersections, outperforming traditional Negative Binomial models. MARS offers a powerful and interpretable tool for traffic safety analysis.

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

Comparative safety evaluation of ADAS-Equipped electric and gasoline vehicles using real-world crash data.

Accident; analysis and prevention·2026
Same author

Modeling crash frequencies at highway-railroad grade crossings in Kentucky in the United States.

Accident; analysis and prevention·2026
Same author

When does visual distraction become dangerous in car-following? Evidence from naturalistic driving study data with causal inference on time-to-collision and braking intensity.

Accident; analysis and prevention·2026
Same author

Determinants influencing risks in e-bike cyclists under mix traffic condition: a partially constrained random parameters approach using experimental study data.

Accident; analysis and prevention·2025
Same author

Segment level safety analysis using lane-changing behavior and driving volatility features from connected vehicle trajectories.

Scientific reports·2025
Same author

Assessing the safety effectiveness of advanced driver assistance systems.

Journal of safety research·2025

Area of Science:

  • Transportation Engineering
  • Machine Learning Applications
  • Traffic Safety Analysis

Background:

  • Angle crashes at unsignalized intersections pose significant safety risks.
  • Traditional models like Negative Binomial (NB) have limitations in predicting crash frequency.
  • Machine learning offers advanced predictive capabilities for complex traffic phenomena.

Purpose of the Study:

  • To introduce and evaluate multivariate adaptive regression splines (MARS) for predicting angle crash frequency at unsignalized intersections.
  • To compare the predictive performance of MARS against Negative Binomial (NB) models.
  • To explore variations of MARS, including treating crash frequency as a continuous variable and combining it with random forest.

Main Methods:

  • Fitting and comparing MARS and NB models using extensive crash data from Florida unsignalized intersections.

More Related Videos

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
11:41

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

Related Experiment Videos

Last Updated: Jun 6, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation
11:41

Evaluation of an Exclusive Spur Dike U-Turn Design with Radar-Collected Data and Simulation

Published on: February 1, 2020

  • Estimating models for both discrete and continuous (log-transformed) crash frequency.
  • Utilizing random forest for covariate screening to enhance MARS model performance.

    • Main Results:

    • MARS models demonstrated superior prediction power over NB models based on mean square prediction error (MSPE).
    • Predicting crash frequency as a continuous variable using MARS yielded better results than predicting discrete frequency.
    • Significant factors influencing angle crashes included traffic volume, intersection proximity, median type, truck percentage, and location.

    Conclusions:

    • MARS is a highly recommended and efficient technique for predicting angle crashes at unsignalized intersections.
    • The interpretability and predictive accuracy of MARS make it a valuable tool for traffic safety researchers and practitioners.
    • Combining MARS with random forest further improved prediction accuracy by effectively screening relevant variables.