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: Jul 8, 2025

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

13.5K

Exploring nighttime pedestrian crash patterns at intersection and segments: Findings from the machine learning

Ahmed Hossain1, Xiaoduan Sun1, Mahir Shahrier2

  • 1Department of Civil Engineering, University of Louisiana at Lafayette, Lafayette, LA, 70504, United States.

Journal of Safety Research
|December 11, 2023
PubMed
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

Career anxiety in the age of artificial intelligence: Survey data of university students in Bangladesh.

Data in brief·2026
Same author

Transforming chronic low back pain management in Bangladesh: implications for rehabilitation in low- and middle-income countries.

Annals of medicine and surgery (2012)·2026
Same author

How Health Systems 'Software' Factors Affect Frontline Health Workers' Humanitarian Response Efforts During Infectious Disease Outbreaks in the Rohingya Refugee Camps, Cox's Bazar, Bangladesh.

The International journal of health planning and management·2026
Same author

Global and regional trends in multidrug- or rifampicin-resistant tuberculosis, 2000-2024 with forecasts to 2030: a systematic review and meta-analysis.

BMC infectious diseases·2026
Same author

Protective Effect of "Ark-e-Kasni," a Unani Formulation, in Letrozole and High-Fat Diet-Induced Polycystic Ovarian Syndrome in Rats.

The journal of obstetrics and gynaecology research·2026
Same author

Role of cold shock protein CspA in <i>Aeromonas salmonicida</i> subsp. <i>salmonicida</i> physiology and virulence.

Canadian journal of microbiology·2026
Same journal

School zone speed compliance in the ACT, Australia: Risks, findings and recommendations for improved safety.

Journal of safety research·2026
Same journal

A bibliometric performance and network analysis of red-light camera impact on signalized intersection safety.

Journal of safety research·2026
Same journal

Effects of driver direct visibility in passenger vehicles on the risk of turning crashes with pedestrians.

Journal of safety research·2026
Same journal

The importance of employee-engaged safety audits to reduce LTI and safety-related costs.

Journal of safety research·2026
Same journal

Improving crash data quality by identifying misclassified alcohol-involved crashes using NLP on narrative data.

Journal of safety research·2026
Same journal

The influence of employee health and safety policies on the value of the organization.

Journal of safety research·2026
See all related articles
This summary is machine-generated.

Nighttime pedestrian crashes are linked to specific factors like driver behavior and road conditions, varying by intersection or segment location. Understanding these associations helps develop targeted safety measures to prevent future incidents.

Area of Science:

  • Traffic Safety Engineering
  • Data Mining and Machine Learning
  • Human Factors in Transportation

Background:

  • Nighttime pedestrian safety is a critical traffic concern, with visibility being a major factor but not the sole cause of crashes.
  • Numerous interacting factors including human, vehicle, roadway, and environmental elements contribute to nighttime pedestrian accidents.
  • Crash patterns differ significantly between intersections and road segments, necessitating location-specific analysis.

Purpose of the Study:

  • To identify and analyze the risk factors associated with nighttime pedestrian crashes.
  • To differentiate crash patterns and contributing factors based on whether crashes occur at intersections or road segments.
  • To apply Association Rules Mining (ARM) for uncovering complex relationships in crash data.

Main Methods:

Keywords:
AlcoholDark conditionsFatalHigh-speed intersectionInterstateMachine learning

More Related Videos

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.3K
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

20.4K

Related Experiment Videos

Last Updated: Jul 8, 2025

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

13.5K
Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street
14:55

Evaluating the Effect of Roadside Parking on a Dual-Direction Urban Street

Published on: January 20, 2023

3.3K
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

20.4K
  • Utilized Association Rules Mining (ARM), a machine learning technique, to analyze crash data.
  • Examined a dataset of 2,505 nighttime pedestrian fatal and injury crashes in Louisiana from 2015-2019.
  • Categorized crash data based on location: intersections versus road segments.

Main Results:

  • Intersection crashes linked to specific vehicle movements, older drivers/pedestrians, adverse weather, young pedestrian violations, and alcohol involvement.
  • Segment crashes frequently associated with roadways lacking physical separation, absence of streetlights, driver impairment, and high-speed conditions.
  • Identified critical issues like lack of crosswalks, high driveway density, and risky pedestrian crossing behaviors near intersections.

Conclusions:

  • Findings provide a basis for developing targeted countermeasures tailored to specific crash scenarios (intersection vs. segment).
  • Location-specific risk factor identification is crucial for effective nighttime pedestrian safety strategies.
  • Data-driven insights can inform educational campaigns to reduce nighttime pedestrian crashes.