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

You might also read

Related Articles

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

Sort by

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

Postoperative recurrence and systemic metastasis of large cell neuroendocrine carcinoma of the breast: a case report including T-DXd treatment.

Frontiers in oncology·2026

Same author

Antibacterial mechanism of action of perilla leaf essential oil on Shigella flexneri and its preservation effectiveness in fresh-cut lettuce.

International journal of food microbiology·2026

Same author

Accelerated Carrier Kinetics in Hollow Cubic Mott-Schottky CoFe@carbon Composites for High-Efficiency Broadband Electromagnetic Wave Absorption.

Small (Weinheim an der Bergstrasse, Germany)·2025

Same author

Endothelin-1 Mediates Oxaliplatin Resistance via Activation of YAP Signaling in Colorectal Cancer.

Oncology research·2025

Same journal

Modeling road-segment-level speeding risk of new energy vehicle taxis using a multistage framework with spatial spillover, endogeneity, and nonlinear effects.

Accident; analysis and prevention·2026

Same journal

Role of streetscape feature in pedestrian safety: A modified multi-level multiple membership model.

Accident; analysis and prevention·2026

Same journal

Assessing autonomous driving performance and environmental influencing factors using real-world operational trajectory data.

Accident; analysis and prevention·2026

Same journal

Multi-scale modeling of electric vehicle fatal crash risk: uncovering spatial heterogeneity and infrastructure-land use coupling mechanisms.

Accident; analysis and prevention·2026

Same journal

Differential sensitivity of self-reported driving and collision measures to aspects of shiftwork, sleep, and fatigue.

Accident; analysis and prevention·2026

Same journal

Delving into the visual attention of pedestrians during street crossing under time pressure: An eye-tracking approach.

Accident; analysis and prevention·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Nov 4, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Cost-sensitive learning for semi-supervised hit-and-run analysis.

Siying Zhu¹, Jianwu Wan¹

¹School of Civil and Environmental Engineering, Nanyang Technological University, Singapore.

Accident; Analysis and Prevention

|May 28, 2021

Summary

This summary is machine-generated.

This study introduces a cost-sensitive semi-supervised logistic regression (CS³LR) model to address class imbalance and missing labels in hit-and-run crash analysis. The CS³LR model effectively identifies key contributing factors to these crashes, improving prediction accuracy.

Keywords:

Cost-sensitive Hit-and-run Imbalanced dataset Semi-supervised learning Unlabelled data

More Related Videos

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

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Nov 4, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

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

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Traffic safety research
Machine learning applications in transportation
Data science for accident analysis

Background:

Hit-and-run crashes pose significant societal and logistical challenges, including delayed medical services.
Existing crash analysis methods struggle with class imbalance and missing data, limiting the effective use of unlabelled samples.
Accurate analysis of hit-and-run incidents is crucial for developing effective prevention strategies.

Purpose of the Study:

To propose a novel cost-sensitive semi-supervised logistic regression (CS³LR) model for analyzing hit-and-run crashes.
To address the challenges of class imbalance and missing labels in crash datasets.
To improve the prediction and identification of factors contributing to hit-and-run collisions.

Main Methods:

Development of a cost-sensitive semi-supervised logistic regression (CS³LR) model.
Utilizing a maximum likelihood framework for joint label estimation on both labelled and unlabelled data.
Application to a crash dataset from Victoria, Australia (2013-2019).

Main Results:

The CS³LR model demonstrated superior performance compared to traditional logistic regression and other machine learning methods.
Significant contributing factors to hit-and-run crashes were identified with high consistency using only 10% labelled data.
Analysis revealed the impact of class-weighted ratios and hyper-parameter λ on model performance.

Conclusions:

The CS³LR model offers an effective solution for analyzing imbalanced and incomplete crash data.
The methodology provides reliable insights into hit-and-run crash contributing factors, even with limited labelled data.
Findings can inform policy development for preventing hit-and-run incidents and related crimes.