Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches

This study investigates the effectiveness of unsignalized crossings to enhance pedestrian safety through a robust data-driven approach utilizing multiple machine learning models, including the statistical classifier Logistic Regression, Decision Tree, Random Forest, and Neural Network Multi-Layer Pe...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengqi Liu, Harry Evdorides
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:IATSS Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0386111225000226
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319602195005440
author Shengqi Liu
Harry Evdorides
author_facet Shengqi Liu
Harry Evdorides
author_sort Shengqi Liu
collection DOAJ
description This study investigates the effectiveness of unsignalized crossings to enhance pedestrian safety through a robust data-driven approach utilizing multiple machine learning models, including the statistical classifier Logistic Regression, Decision Tree, Random Forest, and Neural Network Multi-Layer Perceptron (MLP). While numerous studies have applied predictive models to traffic crash data, few have systematically analysed pedestrian crash severity at unsignalized crossings using multiple machine learning algorithms. By leveraging historical crash data from the UK's STATS19 database, key factors influencing pedestrian safety at unsignalized crossings were identified and analysed. The research highlights the superior predictive performance of Random Forest and MLP models, with accuracies of 84 % and 86 %, respectively, underscoring their capability to handle complex, nonlinear relationships in crash data. Feature importance analysis revealed critical determinants of crash severity. The findings emphasize the need for targeted interventions to mitigate crash severity of crash outcomes. Despite challenges like underreporting and data imputation biases, this study provides valuable insights into the role of infrastructure in pedestrian safety, offering a foundation for policy recommendations and future research on improving unsignalized crossing designs.
format Article
id doaj-art-33523db7faa946fb8aba0a723e69266e
institution Kabale University
issn 0386-1112
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series IATSS Research
spelling doaj-art-33523db7faa946fb8aba0a723e69266e2025-08-20T03:50:22ZengElsevierIATSS Research0386-11122025-07-0149227127910.1016/j.iatssr.2025.06.002Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approachesShengqi Liu0Harry Evdorides1Corresponding author.; Department of Civil Engineering, School of Engineering, College of Engineering and Physical Sciences, The University of Birmingham, Birmingham B15 2TT, UKDepartment of Civil Engineering, School of Engineering, College of Engineering and Physical Sciences, The University of Birmingham, Birmingham B15 2TT, UKThis study investigates the effectiveness of unsignalized crossings to enhance pedestrian safety through a robust data-driven approach utilizing multiple machine learning models, including the statistical classifier Logistic Regression, Decision Tree, Random Forest, and Neural Network Multi-Layer Perceptron (MLP). While numerous studies have applied predictive models to traffic crash data, few have systematically analysed pedestrian crash severity at unsignalized crossings using multiple machine learning algorithms. By leveraging historical crash data from the UK's STATS19 database, key factors influencing pedestrian safety at unsignalized crossings were identified and analysed. The research highlights the superior predictive performance of Random Forest and MLP models, with accuracies of 84 % and 86 %, respectively, underscoring their capability to handle complex, nonlinear relationships in crash data. Feature importance analysis revealed critical determinants of crash severity. The findings emphasize the need for targeted interventions to mitigate crash severity of crash outcomes. Despite challenges like underreporting and data imputation biases, this study provides valuable insights into the role of infrastructure in pedestrian safety, offering a foundation for policy recommendations and future research on improving unsignalized crossing designs.http://www.sciencedirect.com/science/article/pii/S0386111225000226Pedestrian safetyUnsignalized crossingsNeural networksMachine learning
spellingShingle Shengqi Liu
Harry Evdorides
Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
IATSS Research
Pedestrian safety
Unsignalized crossings
Neural networks
Machine learning
title Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
title_full Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
title_fullStr Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
title_full_unstemmed Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
title_short Analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data-driven approaches
title_sort analysing the effectiveness of unsignalized crossing infrastructure in improving pedestrian safety using multiple data driven approaches
topic Pedestrian safety
Unsignalized crossings
Neural networks
Machine learning
url http://www.sciencedirect.com/science/article/pii/S0386111225000226
work_keys_str_mv AT shengqiliu analysingtheeffectivenessofunsignalizedcrossinginfrastructureinimprovingpedestriansafetyusingmultipledatadrivenapproaches
AT harryevdorides analysingtheeffectivenessofunsignalizedcrossinginfrastructureinimprovingpedestriansafetyusingmultipledatadrivenapproaches