Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne

Ali Soltani; Betsabeh Tanoori; Christopher J. Pettit

Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne

Ali Soltani
, Betsabeh Tanoori
, Christopher J. Pettit

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

Abstract

This research paper investigates the use of big data to analyse road accidents in the Melbourne metropolitan area. Using the Crash dataset and the Random Forest model, the study sought to determine the relationship between various factors and the proportion of accident victims who were maimed or slain. Results demonstrated that factors such as weekdays, months, and weather conditions can influence the severity of accidents. The study provides policymakers and transportation authorities with valuable insights for devising strategies to enhance road safety and reduce accident risk. Additional research can investigate other potential accident severity factors.

Original language	English
Title of host publication	ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings
Editors	Diona Olaru, Brett Smith, Amanda Eaton
Publisher	ATRF
Number of pages	11
ISBN (Electronic)	9780646890401
Publication status	Published - 2023
Event	Australasian Transport Research Forum Conference 2023, ATRF 2023 - The University of Western Australia, Perth, Australia Duration: 29 Nov 2023 → 1 Dec 2023

Publication series

Name	ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings

Conference

Conference	Australasian Transport Research Forum Conference 2023, ATRF 2023
Country/Territory	Australia
City	Perth
Period	29/11/23 → 1/12/23

Bibliographical note

Publisher Copyright:
© ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings. All rights reserved.

UN SDGs

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

SDG 3 Good Health and Well-being
SDG 11 Sustainable Cities and Communities

Keywords

Big data
Correlation analysis
Machine Learning
Road crashes
Victoria

Access to Document

https://australasiantransportresearchforum.org.au/predicting-crash-injury-risk-using-big-data-the-case-of-metropolitan-melbourne/Licence: In Copyright

Cite this

Soltani, A., Tanoori, B., & Pettit, C. J. (2023). Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne. In D. Olaru, B. Smith, & A. Eaton (Eds.), ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings (ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings). ATRF. https://australasiantransportresearchforum.org.au/predicting-crash-injury-risk-using-big-data-the-case-of-metropolitan-melbourne/

@inproceedings{45a7f0de983b444f8886a0a17962ec53,

title = "Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne",

abstract = "This research paper investigates the use of big data to analyse road accidents in the Melbourne metropolitan area. Using the Crash dataset and the Random Forest model, the study sought to determine the relationship between various factors and the proportion of accident victims who were maimed or slain. Results demonstrated that factors such as weekdays, months, and weather conditions can influence the severity of accidents. The study provides policymakers and transportation authorities with valuable insights for devising strategies to enhance road safety and reduce accident risk. Additional research can investigate other potential accident severity factors.",

keywords = "Big data, Correlation analysis, Machine Learning, Road crashes, Victoria",

author = "Ali Soltani and Betsabeh Tanoori and Pettit, \{Christopher J.\}",

note = "Publisher Copyright: {\textcopyright} ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings. All rights reserved.; Australasian Transport Research Forum Conference 2023, ATRF 2023 ; Conference date: 29-11-2023 Through 01-12-2023",

year = "2023",

language = "English",

series = "ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings",

publisher = "ATRF",

editor = "Diona Olaru and Brett Smith and Amanda Eaton",

booktitle = "ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings",

}

Soltani, A, Tanoori, B & Pettit, CJ 2023, Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne. in D Olaru, B Smith & A Eaton (eds), ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings. ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings, ATRF, Australasian Transport Research Forum Conference 2023, ATRF 2023, Perth, Western Australia, Australia, 29/11/23. <https://australasiantransportresearchforum.org.au/predicting-crash-injury-risk-using-big-data-the-case-of-metropolitan-melbourne/>

Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne. / Soltani, Ali; Tanoori, Betsabeh; Pettit, Christopher J.
ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings. ed. / Diona Olaru; Brett Smith; Amanda Eaton. ATRF, 2023. (ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings).

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

TY - GEN

T1 - Predicting crash injury risk using Big Data

T2 - Australasian Transport Research Forum Conference 2023, ATRF 2023

AU - Soltani, Ali

AU - Tanoori, Betsabeh

AU - Pettit, Christopher J.

PY - 2023

Y1 - 2023

N2 - This research paper investigates the use of big data to analyse road accidents in the Melbourne metropolitan area. Using the Crash dataset and the Random Forest model, the study sought to determine the relationship between various factors and the proportion of accident victims who were maimed or slain. Results demonstrated that factors such as weekdays, months, and weather conditions can influence the severity of accidents. The study provides policymakers and transportation authorities with valuable insights for devising strategies to enhance road safety and reduce accident risk. Additional research can investigate other potential accident severity factors.

AB - This research paper investigates the use of big data to analyse road accidents in the Melbourne metropolitan area. Using the Crash dataset and the Random Forest model, the study sought to determine the relationship between various factors and the proportion of accident victims who were maimed or slain. Results demonstrated that factors such as weekdays, months, and weather conditions can influence the severity of accidents. The study provides policymakers and transportation authorities with valuable insights for devising strategies to enhance road safety and reduce accident risk. Additional research can investigate other potential accident severity factors.

KW - Big data

KW - Correlation analysis

KW - Machine Learning

KW - Road crashes

KW - Victoria

UR - https://www.scopus.com/pages/publications/105026340868

UR - https://catalogue.nla.gov.au/catalog/10015360

M3 - Conference contribution

AN - SCOPUS:105026340868

T3 - ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings

BT - ATRF 2023 - Australasian Transport Research Forum 2023, Proceedings

A2 - Olaru, Diona

A2 - Smith, Brett

A2 - Eaton, Amanda

PB - ATRF

Y2 - 29 November 2023 through 1 December 2023

ER -

Predicting crash injury risk using Big Data: The case of Metropolitan Melbourne

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this