A Bayesian Network for the Analysis of Traffic Accidents in Peru

Willy Ugarte; Manuel Alcantara-Zapata; Leibnihtz Ayamamani-Choque; Renzo Bances-Morales; Cristian Cabrera-Sanchez

doi:10.5220/0011045900003191

A Bayesian Network for the Analysis of Traffic Accidents in Peru

Willy Ugarte
, Manuel Alcantara-Zapata
, Leibnihtz Ayamamani-Choque
, Renzo Bances-Morales
, Cristian Cabrera-Sanchez

Universidad Peruana de Ciencias Aplicadas

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Traffic accidents are a problem that affects the State and society, because they cause material damage, injuries and even the death of a person. This has led countries such as China, Switzerland and Australia to carry out studies using Bayesian networks to determine the main causes and, based on them, propose measures to reduce the number of traffic accidents. Following this trend, we, without having any expert knowledge on the subject, decided to analyze the data of traffic accidents on the Pan-American Highway in Lima, Peru. This analysis was done by means of directed graph learning with the Hill Climbing Search, Chow-Liu, K2, BIC and BDEU. In addition, we used a Bayesian estimator to calculate the conditional probability distribution for our dataset. This dataset contains observations from the years 2017 to 2019 and approximately 16 km of this highway. Our results show that it is possible to identify the possible causes of excess accidents in specific areas of the Pan-American Highway in certain shifts i.e., 32% of fatal accidents occur between 12 am and 7 pm in the Rimac district and of these 20% are due to pedestrians on the highway.

Original language	English
Title of host publication	Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022
Editors	Jeroen Ploeg, Jeroen Ploeg, Markus Helfert, Karsten Berns, Oleg Gusikhin
Publisher	Science and Technology Publications, Lda
Pages	308-315
Number of pages	8
ISBN (Electronic)	9789897585739
DOIs	https://doi.org/10.5220/0011045900003191
State	Published - 2022
Event	8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022 - Virtual, Online Duration: 27 Apr 2022 → 29 Apr 2022

Publication series

Name	International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings
ISSN (Electronic)	2184-495X

Conference

Conference	8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022
City	Virtual, Online
Period	27/04/22 → 29/04/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Accidents
Bayesian Network
Graph Learning
Probabilistic Graphical Model
Traffic

Access to Document

10.5220/0011045900003191

Cite this

Ugarte, W., Alcantara-Zapata, M., Ayamamani-Choque, L., Bances-Morales, R., & Cabrera-Sanchez, C. (2022). A Bayesian Network for the Analysis of Traffic Accidents in Peru. In J. Ploeg, J. Ploeg, M. Helfert, K. Berns, & O. Gusikhin (Eds.), Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022 (pp. 308-315). (International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings). Science and Technology Publications, Lda. https://doi.org/10.5220/0011045900003191

Ugarte, Willy ; Alcantara-Zapata, Manuel ; Ayamamani-Choque, Leibnihtz et al. / A Bayesian Network for the Analysis of Traffic Accidents in Peru. Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022. editor / Jeroen Ploeg ; Jeroen Ploeg ; Markus Helfert ; Karsten Berns ; Oleg Gusikhin. Science and Technology Publications, Lda, 2022. pp. 308-315 (International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings).

@inproceedings{282ec78ecf494b3eac85ff4044aa386b,

title = "A Bayesian Network for the Analysis of Traffic Accidents in Peru",

abstract = "Traffic accidents are a problem that affects the State and society, because they cause material damage, injuries and even the death of a person. This has led countries such as China, Switzerland and Australia to carry out studies using Bayesian networks to determine the main causes and, based on them, propose measures to reduce the number of traffic accidents. Following this trend, we, without having any expert knowledge on the subject, decided to analyze the data of traffic accidents on the Pan-American Highway in Lima, Peru. This analysis was done by means of directed graph learning with the Hill Climbing Search, Chow-Liu, K2, BIC and BDEU. In addition, we used a Bayesian estimator to calculate the conditional probability distribution for our dataset. This dataset contains observations from the years 2017 to 2019 and approximately 16 km of this highway. Our results show that it is possible to identify the possible causes of excess accidents in specific areas of the Pan-American Highway in certain shifts i.e., 32\% of fatal accidents occur between 12 am and 7 pm in the Rimac district and of these 20\% are due to pedestrians on the highway.",

keywords = "Accidents, Bayesian Network, Graph Learning, Probabilistic Graphical Model, Traffic",

author = "Willy Ugarte and Manuel Alcantara-Zapata and Leibnihtz Ayamamani-Choque and Renzo Bances-Morales and Cristian Cabrera-Sanchez",

note = "Publisher Copyright: Copyright {\textcopyright} 2022 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.; 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022 ; Conference date: 27-04-2022 Through 29-04-2022",

year = "2022",

doi = "10.5220/0011045900003191",

language = "Ingl{\'e}s",

series = "International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings",

publisher = "Science and Technology Publications, Lda",

pages = "308--315",

editor = "Jeroen Ploeg and Jeroen Ploeg and Markus Helfert and Karsten Berns and Oleg Gusikhin",

booktitle = "Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022",

}

Ugarte, W, Alcantara-Zapata, M, Ayamamani-Choque, L, Bances-Morales, R & Cabrera-Sanchez, C 2022, A Bayesian Network for the Analysis of Traffic Accidents in Peru. in J Ploeg, J Ploeg, M Helfert, K Berns & O Gusikhin (eds), Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022. International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings, Science and Technology Publications, Lda, pp. 308-315, 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022, Virtual, Online, 27/04/22. https://doi.org/10.5220/0011045900003191

A Bayesian Network for the Analysis of Traffic Accidents in Peru. / Ugarte, Willy; Alcantara-Zapata, Manuel; Ayamamani-Choque, Leibnihtz et al.
Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022. ed. / Jeroen Ploeg; Jeroen Ploeg; Markus Helfert; Karsten Berns; Oleg Gusikhin. Science and Technology Publications, Lda, 2022. p. 308-315 (International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Bayesian Network for the Analysis of Traffic Accidents in Peru

AU - Ugarte, Willy

AU - Alcantara-Zapata, Manuel

AU - Ayamamani-Choque, Leibnihtz

AU - Bances-Morales, Renzo

AU - Cabrera-Sanchez, Cristian

PY - 2022

Y1 - 2022

N2 - Traffic accidents are a problem that affects the State and society, because they cause material damage, injuries and even the death of a person. This has led countries such as China, Switzerland and Australia to carry out studies using Bayesian networks to determine the main causes and, based on them, propose measures to reduce the number of traffic accidents. Following this trend, we, without having any expert knowledge on the subject, decided to analyze the data of traffic accidents on the Pan-American Highway in Lima, Peru. This analysis was done by means of directed graph learning with the Hill Climbing Search, Chow-Liu, K2, BIC and BDEU. In addition, we used a Bayesian estimator to calculate the conditional probability distribution for our dataset. This dataset contains observations from the years 2017 to 2019 and approximately 16 km of this highway. Our results show that it is possible to identify the possible causes of excess accidents in specific areas of the Pan-American Highway in certain shifts i.e., 32% of fatal accidents occur between 12 am and 7 pm in the Rimac district and of these 20% are due to pedestrians on the highway.

AB - Traffic accidents are a problem that affects the State and society, because they cause material damage, injuries and even the death of a person. This has led countries such as China, Switzerland and Australia to carry out studies using Bayesian networks to determine the main causes and, based on them, propose measures to reduce the number of traffic accidents. Following this trend, we, without having any expert knowledge on the subject, decided to analyze the data of traffic accidents on the Pan-American Highway in Lima, Peru. This analysis was done by means of directed graph learning with the Hill Climbing Search, Chow-Liu, K2, BIC and BDEU. In addition, we used a Bayesian estimator to calculate the conditional probability distribution for our dataset. This dataset contains observations from the years 2017 to 2019 and approximately 16 km of this highway. Our results show that it is possible to identify the possible causes of excess accidents in specific areas of the Pan-American Highway in certain shifts i.e., 32% of fatal accidents occur between 12 am and 7 pm in the Rimac district and of these 20% are due to pedestrians on the highway.

KW - Accidents

KW - Bayesian Network

KW - Graph Learning

KW - Probabilistic Graphical Model

KW - Traffic

UR - https://www.scopus.com/pages/publications/85140982982

U2 - 10.5220/0011045900003191

DO - 10.5220/0011045900003191

M3 - Contribución a la conferencia

AN - SCOPUS:85140982982

T3 - International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings

SP - 308

EP - 315

BT - Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022

A2 - Ploeg, Jeroen

A2 - Helfert, Markus

A2 - Berns, Karsten

A2 - Gusikhin, Oleg

PB - Science and Technology Publications, Lda

T2 - 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022

Y2 - 27 April 2022 through 29 April 2022

ER -

Ugarte W, Alcantara-Zapata M, Ayamamani-Choque L, Bances-Morales R, Cabrera-Sanchez C. A Bayesian Network for the Analysis of Traffic Accidents in Peru. In Ploeg J, Ploeg J, Helfert M, Berns K, Gusikhin O, editors, Proceedings of the 8th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2022. Science and Technology Publications, Lda. 2022. p. 308-315. (International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS - Proceedings). doi: 10.5220/0011045900003191

A Bayesian Network for the Analysis of Traffic Accidents in Peru

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this