Multinomial logistic regression for prediction of vulnerable road users risk injuries based on spatial and temporal assessment

Abstract

Urban area’s rapid growth often leads to adverse effects such as traffic congestion and increasing accident risks due to the expansion in transportation systems. In the frame of smart cities, active modes are expected to be promoted to improve living conditions. To achieve this goal, it is necessary to reduce the number of vulnerable road users (VRUs) injuries. Considering injury severity levels from crashes involving VRUs, this article seeks spatial and temporal patterns between cities and presents a model to predict the likelihood of VRUs to be involved in a crash. Kernel Density Estimation was applied to identify blackspots based on injury severity levels. A Multinomial Logistic Regression model was developed to identify statistically significant variables to predict the occurrence of these crashes. Results show that target spatial and temporal variables influence the number and severity of crashes involving VRUs. This approach can help to enhance road safety policies.

Keywords:

• Road crashes
• injury severity
• kernel density estimation
• multinomial logistic regression
• vulnerable road users

Acknowledgments

The authors acknowledge ANSR for providing crashes data. Finally, the authors acknowledge the collaboration of the students Laura Laranjo and Bárbara Romeira for the collaboration in data georeferencing.

Additional information

Funding

The authors acknowledge the support of TEMA – CENTRO 01-0145-FEDER-022083; Strategical Project UID/EMS/00481/2019-FCT - Fundação para a Ciencia e Tecnologia; @CRUiSE project (PTDC/EMS-TRA/0383/2014), funded within Project 9471—Reforçar a Investigação, o Desenvolvimento Tecnológico e a Inovação and supported by European Community Fund FEDER; MobiWise (P2020 SAICTPAC/0011/2015), co-funded by COMPETE2020, Portugal2020—Operational Program for Competitiveness and Internationalization (POCI), European Union’s ERDF (European Regional Development Fund) and FCT; and CISMOB (PGI01611, funded by Interreg Europe Programme). This work was also financially supported by the projects POCI-01-0145-FEDER-029463 (DICA-VE) and POCI-01-0145-FEDER-029679 (InFLOWence) funded by FEDER through COMPETE2020- Programa Operacional Competitividade e Internacionalização (POCI), and by national funds (OE), through FCT/MCTES.