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

Related Concept Videos

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

You might also read

Related Articles

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

Sort by

Same author

Case report: A case series report: recurrent urolithiasis as a risk factor for upper tract urothelial carcinoma.

Frontiers in oncology·2026

Same author

Multi-phase fate and removal mechanism of acetamiprid in a planted coastal wetland mesocosm system: A 'dual-engine' perspective.

Journal of hazardous materials·2026

Same author

Recent advances in antiviral drugs for Chikungunya virus (CHIKV): Targets, mechanisms, and development strategies.

Acta pharmaceutica Sinica. B·2026

Same author

Microbial photoelectrotrophic denitrification: Development, mechanisms, and applications in wastewater treatment.

Bioresource technology·2026

Same author

Kinetic Regulation of Anionic Redox Reaction Voltage by Metastable Over-Lithiated Surface Shells Formation for High-Energy-Density Batteries.

Angewandte Chemie (International ed. in English)·2026

Same author

BiOBr/g-C<sub>3</sub>N<sub>4</sub> Planar Heterostructures toward Enhanced Tetracycline Hydrochloride Removal.

Langmuir : the ACS journal of surfaces and colloids·2026

Search research articles

Related Experiment Video

Updated: Apr 4, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Driving risk assessment using near-crash database through data mining of tree-based model.

Jianqiang Wang¹, Yang Zheng¹, Xiaofei Li¹

¹State Key Laboratory of Automotive Safety and Energy, Tsinghua University, Beijing 10084, China.

Accident; Analysis and Prevention

|August 31, 2015

Summary

This study clusters driving risk levels from near-crash data. Key factors influencing risk include braking velocity, triggering events, object type, and crash type, offering insights for road safety.

Keywords:

Classification and regression tree (CART)Driving risk K-mean cluster Naturalistic driving study Near-crash

More Related Videos

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Related Experiment Videos

Last Updated: Apr 4, 2026

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Collecting and Processing Drone-based Remotely Sensed Data for Use in Forest Recovery Monitoring

Published on: October 24, 2025

An R-Based Landscape Validation of a Competing Risk Model

An R-Based Landscape Validation of a Competing Risk Model

Published on: September 16, 2022

Area of Science:

Traffic Safety
Transportation Engineering
Human Factors in Driving

Background:

Naturalistic driving studies are crucial for understanding real-world driving behavior.
Near-crash scenarios provide valuable data for accident prevention research.
Existing databases often lack detailed information on the nuances of near-crash events.

Purpose of the Study:

To cluster and categorize different levels of driving risk observed in near-crash incidents.
To identify and analyze the critical factors influencing driving risk during near-crash events.
To develop a quantitative method for assessing driving risk in complex traffic scenarios.

Main Methods:

Collected comprehensive naturalistic driving data on Chinese roads, including vehicle dynamics, environmental conditions, and driver actions.
Constructed a near-crash database encompassing vehicle status, potential crash objects, road types, weather, and driver behavior.
Developed a novel risk quantification method by clustering braking characteristics (deceleration, kinetic energy reduction).
Utilized Classification and Regression Trees (CART) to model the relationships between driving risk and influencing factors.

Main Results:

Successfully clustered distinct driving-risk levels within near-crash scenarios.
Identified key factors significantly impacting driving risk: velocity at braking, triggering event type, potential object type, and potential crash type.
Established a quantitative link between braking behavior and overall driving risk.

Conclusions:

The study provides a robust framework for understanding and quantifying driving risk in near-crash situations.
The identified influencing factors offer targeted insights for developing advanced driver-assistance systems and improving road safety strategies.
This research contributes to a deeper understanding of the complex interplay between driver behavior, vehicle dynamics, and the driving environment.