Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification

Portugal has the sixth highest road fatality rate among European Union members. This is a problem of different dimensions with serious consequences in people’s lives. This study analyses daily data from police and government authorities on road traffic accidents that occurred between 2016 and 2019 in a district of Portugal. This paper looks for the determinants that contribute to the existence of victims in road traffic accidents, as well as the determinants for fatalities and/or serious injuries in accidents with victims. We use logistic regression models, and the results are compared to the machine-learning model results. For the severity model, where the response variable indicates whether only property damage or casualties resulted in the traffic accident, we used a large sample with a small imbalance. For the serious injuries model, where the response variable indicates whether or not there were victims with serious injuries and/or fatalities in the traffic accident with victims, we used a small sample with very imbalanced data. Empirical analysis supports the conclusion that, with a small sample of imbalanced data, machine-learning models generally do not perform better than statistical models; however, they perform similarly when the sample is large and has a small imbalance.

Topics

No keywords indexed for this article. Browse by subject →

References

22

[1]

Belokurov "Determining passenger traffic as important factor in urban public transport system" Transp. Res. Procedia (2020) 10.1016/j.trpro.2020.10.007

[2]

World Health Organization (2022, January 25). Global Status Report on Road Safety 2018. Available online: https://apps.who.int/iris/bitstream/handle/10665/276462/9789241565684-eng.pdf?sequence=1&isAllowed=y.

[3]

Eurostat (2022, January 25). Road Accidents: Number of Fatalities Continues Falling. Available online: https://ec.europa.eu/eurostat/en/web/products-eurostat-news/-/ddn-20210624-1.

[4]

Lusa (2022, January 25). Sinistralidade Rodoviária tem Impacto Económico e Social Negativo de 1.2% do PIB-Governo. Available online: https://www.rtp.pt/noticias/pais/sinistralidade-rodoviaria-tem-impacto-economico-e-social-negativo-de-12-do-pib-governo_n1112193.

[5]

Savolainen "The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives" Accid. Anal. Prev. (2011) 10.1016/j.aap.2011.03.025

[6]

Garrido "Prediction of road accident severity using the ordered probit model" Transp. Res. Procedia (2014) 10.1016/j.trpro.2014.10.107

[7]

Zhang "Comparing prediction performance for crash injury severity among various machine learning and statistical methods" IEEE Access (2018) 10.1109/access.2018.2874979

[8]

Silva "Machine learning applied to road safety modeling: A systematic literature review" J. Traffic Transp. Eng. (Engl. Ed.) (2020)

[9]

Jamal "Injury severity prediction of traffic crashes with ensemble machine learning techniques: A comparative study" Int. J. Inj. Control Saf. Promot. (2021) 10.1080/17457300.2021.1928233

[10]

Iranitalab "Comparison of four statistical and machine learning methods for crash severity prediction" Accid. Anal. Prev. (2017) 10.1016/j.aap.2017.08.008

[11]

Li "Impact of pavement conditions on crash severity" Accid. Anal. Prev. (2013) 10.1016/j.aap.2013.06.028

[12]

Martensen "Comparing single vehicle and multivehicle fatal road crashes: A joint analysis of road conditions, time variables and driver characteristics" Accid. Anal. Prev. (2013) 10.1016/j.aap.2013.03.005

[13]

Hosseinpour "Exploring the effects of roadway characteristics on the frequency and severity of head-on crashes: Case studies from Malaysian Federal Roads" Accid. Anal. Prev. (2014) 10.1016/j.aap.2013.10.001

[14]

Yasmin "A latent segmentation based generalized ordered logit model to examine factors influencing driver injury severity" Anal. Methods Accid. Res. (2014)

[15]

Rezapour "Ordered logistic models of influencing factors on crash injury severity of single and multiple-vehicle downgrade crashes: A case study in Wyoming" J. Saf. Res. (2019) 10.1016/j.jsr.2018.12.006

[16]

ANSR (2022, January 25). Manual de Prenchimento. Boletim Estatístico de Acidente de Viação. Available online: http://www.ansr.pt/Estatisticas/BEAV/Documents/MANUALPREENCHIMENTOBEAV.pdf.

[17]

Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, John Wiley & Sons. 10.1002/9781118548387

[18]

Quinlan, J.R. (1993). C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers.

[19]

Research, R. (2022, January 25). Is See5/C5.0 Better Than C4.5?. Available online: https://rulequest.com/see5-comparison.html.

[20]

Learning from Imbalanced Data

Haibo He, E.A. Garcia

IEEE Transactions on Knowledge and Data Engineerin... 2009 10.1109/tkde.2008.239

[21]

R Core Team (2021). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing.

[22]

Fiorentini, N., and Losa, M. (2020). Handling Imbalanced Data in Road Crash Severity Prediction by Machine Learning Algorithms. Infrastructures, 5. 10.3390/infrastructures5070061

Cited By

41

Comparison of Cluster-Based Sampling Approaches for Imbalanced Data of Crashes Involving Large Trucks

Syed As-Sadeq Tahfim, Yan Chen · 2024

Information

Metrics

41

Citations

22

References

Details

Published: May 16, 2022
Vol/Issue: 11(5)
Pages: 80
License: View

Authors

P

Paulo Infante

CIMA, IIFA, University of Évora, 7000-671 Évora, Portugal; Department of Matematics, ECT, University of Évora, 7000-671 Évora, Portugal

G

Gonçalo Jacinto

CIMA, IIFA, University of Évora, 7000-671 Évora, Portugal; Department of Matematics, ECT, University of Évora, 7000-671 Évora, Portugal

A

Anabela Afonso

CIMA, IIFA, University of Évora, 7000-671 Évora, Portugal; Department of Matematics, ECT, University of Évora, 7000-671 Évora, Portugal

L

Leonor Rego

Department of Matematics, ECT, University of Évora, 7000-671 Évora, Portugal

V

Vitor Nogueira

Algoritmi Research Centre, University of Évora, 7000-671 Évora, Portugal; Department of Informatics, ECT, University of Évora, 7000-671 Évora, Portugal

P

Paulo Quaresma

Algoritmi Research Centre, University of Évora, 7000-671 Évora, Portugal; Department of Informatics, ECT, University of Évora, 7000-671 Évora, Portugal

J

José Saias

Algoritmi Research Centre, University of Évora, 7000-671 Évora, Portugal; Department of Informatics, ECT, University of Évora, 7000-671 Évora, Portugal

D

Daniel Santos

Department of Informatics, ECT, University of Évora, 7000-671 Évora, Portugal

P

Pedro Nogueira

ICT, IIFA, University of Évora, 7000-671 Évora, Portugal; Department of Geosciences, University of Évora, 7000-671 Évora, Portugal

M

Marcelo Silva

ICT, IIFA, University of Évora, 7000-671 Évora, Portugal; Department of Geosciences, University of Évora, 7000-671 Évora, Portugal

R

Rosalina Pisco Costa

CICS.NOVA.UEVORA, IIFA, University of Évora, 7000-208 Évora, Portugal; Department of Sociology, ECS, University of Évora, 7000-803 Évora, Portugal

P

Patrícia Gois

Department of Visual Arts and Design, EA, University of Évora, 7000-208 Évora, Portugal

P

Paulo Rebelo Manuel

CIMA, IIFA, University of Évora, 7000-671 Évora, Portugal

Cite This Article

Paulo Infante, Gonçalo Jacinto, Anabela Afonso, et al. (2022). Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification. Computers, 11(5), 80. https://doi.org/10.3390/computers11050080

Comparison of Statistical and Machine-Learning Models on Road Traffic Accident Severity Classification

You May Also Like