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

A Minority of One: Conformity to Group Norms08:55

A Minority of One: Conformity to Group Norms

18.0K
Source: William Brady & Jay Van Bavel—New York University
It is obvious that we are influenced by those around us, but in the early to mid 1900's, psychologists began to study how potent social influence can be on our thoughts and behaviors. Motivated in part by attempts to explain the behaviors of Nazi soldiers in World War II, one topic of considerable interest at the time in psychology was conformity, the phenomenon in which people match their attitudes, behaviors, or beliefs to...
18.0K
Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers10:41

Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers

8.8K
This study presents an alternative strategy to the conventional toxic analog-based method in identifying amino acid overproducers by using rare-codon-rich markers to achieve accuracy, sensitivity, and high-throughput...
8.8K
Trajectory Data Analyses for Pedestrian Space-time Activity Study16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

14.1K
A suite of spatiotemporal processing methods are presented to analyze human trajectory data, such as that collected using a GPS device, for the purpose of modeling pedestrian space-time...
14.1K
Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior10:52

Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior

9.1K
A protocol is presented for the characterization of the in-field pedestrian behavior and the simulation of the resulting structural response. Field-tests demonstrate that the in situ identified pacing rate and synchronization rate among the participants constitute an essential input for the simulation and verification of the human-induced...
9.1K
Using a Virtual Reality Walking Simulator to Investigate Pedestrian Behavior06:38

Using a Virtual Reality Walking Simulator to Investigate Pedestrian Behavior

5.2K
This protocol describes use of a walking simulator that serves as a safe and ecologically valid method to study pedestrian behavior in the presence of moving...
5.2K
Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease08:51

Application of Unsupervised Multi-Omic Factor Analysis to Uncover Patterns of Variation and Molecular Processes Linked to Cardiovascular Disease

2.1K
We present a flexible, extendible Jupyter-lab-based workflow for the unsupervised analysis of complex multi-omics datasets that combines different pre-processing steps, estimation of the multi-omics factor analysis model, and several downstream...
2.1K

You might also read

Related Articles

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

Sort by
Same author

Joint analysis of two nationwide crash databases to model transit bus stop-related pedestrian crash severity in the United States.

Accident; analysis and prevention·2026
Same author

Shedding light on safety: Comparing the crash likelihood and speed at impact of pedestrian crash avoidance systems across day and night conditions.

Journal of safety research·2026
Same author

Beyond the conventional: Exploring pedestrian safety on interstates with Bayesian and machine learning models.

Journal of safety research·2025
Same author

Nighttime pedestrian safety in different communities: Application of artificial intelligence techniques.

Journal of safety research·2025
Same author

Day and night performance differences in detection and deceleration by pedestrian automatic emergency braking systems.

Accident; analysis and prevention·2025
Same author

Nighttime safety of pedestrians: The role of pedestrian automatic emergency braking systems.

Accident; analysis and prevention·2025

Related Experiment Video

Updated: Jan 20, 2026

Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers
10:41

Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers

Published on: June 24, 2019

8.8K

Beyond the norm: Identifying rare and high-risk pedestrian crash patterns using unsupervised learning.

Zeinab Bayati1, Asad J Khattak1

  • 1Department of Civil and Environmental Engineering, The University of Tennessee, Knoxville, TN, United States.

Accident; Analysis and Prevention
|January 18, 2026
PubMed
Summary

Pedestrian safety requires focusing on high-risk "edge case" crashes. A new framework identifies these rare, severe events, often missed by traditional methods, enabling targeted safety interventions.

Keywords:
Built EnvironmentEdge CasesNorth CarolinaPedestrian SafetyUnsupervised Learning

More Related Videos

Assessing the Power of Conformity on Judgment Making
08:55

Assessing the Power of Conformity on Judgment Making

Published on: April 30, 2023

18.0K
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

14.1K

Related Experiment Videos

Last Updated: Jan 20, 2026

Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers
10:41

Identifying Amino Acid Overproducers Using Rare-Codon-Rich Markers

Published on: June 24, 2019

8.8K
Assessing the Power of Conformity on Judgment Making
08:55

Assessing the Power of Conformity on Judgment Making

Published on: April 30, 2023

18.0K
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

14.1K

Area of Science:

  • Transportation Safety
  • Traffic Accident Analysis
  • Public Health

Background:

  • Pedestrian safety is a critical concern, with rising fatalities despite existing improvements.
  • Conventional and automated vehicle safety advancements necessitate a focus on the most dangerous crash scenarios.

Purpose of the Study:

  • To introduce and validate a composite unsupervised edge case detection framework for identifying high-risk pedestrian crashes.
  • To analyze the characteristics and severity of different crash types, distinguishing common patterns from rare, complex events.

Main Methods:

  • Utilized Uniform Manifold Approximation and Projection (UMAP) for dimensionality reduction and Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN).
  • Developed a composite scoring system based on cluster membership uncertainty and distance from typical crash patterns.
  • Applied the framework to 10,108 police-reported pedestrian crashes from North Carolina using the Pedestrian and Bicycle Crash Analysis Tool (PBCAT).

Main Results:

  • The framework classified crashes into Core, Moderate Edge, and Strong Edge categories.
  • Strong Edge crashes exhibited substantially higher severity, with 36.6% resulting in fatal injuries compared to 8.1% in the Core group.
  • High-risk crashes were frequently associated with rural areas, poor lighting, non-intersection locations, and unusual pedestrian behaviors.

Conclusions:

  • The developed edge case framework effectively detects rare, severe pedestrian crashes that traditional methods may overlook.
  • Crash severity is significantly influenced by the built environment and crash type, highlighting the need for context-specific safety strategies.
  • Targeted safety efforts can be enhanced by identifying and addressing these high-risk edge case scenarios.