The Performance of Accident Severity Multiclass Classification

One way to monitor accidents on highway is to analyze the accident characteristic to predict the accident severity. This study applied multinomial logistic regression model to predict accident severity. Predicted accident severities are compared with actual accident severities to evaluate the pre...

Full description

Bibliographic Details
Main Authors: Sudesh Nair, Baskara, Haryati, Yaacob, Sitti Asmah, Hassan, Mohd Rosli, Hainin
Format: Article
Language:English
English
Published: INTI International University 2022
Subjects:
Online Access:http://eprints.intimal.edu.my/1578/
http://eprints.intimal.edu.my/1578/1/joit2022_06r.pdf
http://eprints.intimal.edu.my/1578/2/291
_version_ 1848766776816435200
author Sudesh Nair, Baskara
Haryati, Yaacob
Sitti Asmah, Hassan
Mohd Rosli, Hainin
author_facet Sudesh Nair, Baskara
Haryati, Yaacob
Sitti Asmah, Hassan
Mohd Rosli, Hainin
author_sort Sudesh Nair, Baskara
building INTI Institutional Repository
collection Online Access
description One way to monitor accidents on highway is to analyze the accident characteristic to predict the accident severity. This study applied multinomial logistic regression model to predict accident severity. Predicted accident severities are compared with actual accident severities to evaluate the prediction performances of the model. The aim of this study is to determine the performance of accident severity classifications by multinomial logistic regression model. The predicted accident severities could be used to estimate potential effect of changes in factors contributing to accidents. Data was obtained from the Malaysian Highway Authority for the year 2013 and 2014. The accident severity was grouped into four categories of death, serious injury, minor injury and damage. Based on the results, the model correctly classified accident severities by 63.52% using training data and 61.45% using validation data. The Hosmer- Lemeshow test indicated the model has a good fit between the actual accident severities and predicted accident severities and the ROC results indicted the model able to distinguish between the classifications. The classifier of the model inclined more toward the damages compared to other accident severities resulted in classifying accident severity classes with more samples better and remains weak on the accident severity classes with lesser samples.
first_indexed 2025-11-14T11:56:32Z
format Article
id intimal-1578
institution INTI International University
institution_category Local University
language English
English
last_indexed 2025-11-14T11:56:32Z
publishDate 2022
publisher INTI International University
recordtype eprints
repository_type Digital Repository
spelling intimal-15782025-07-23T03:04:59Z http://eprints.intimal.edu.my/1578/ The Performance of Accident Severity Multiclass Classification Sudesh Nair, Baskara Haryati, Yaacob Sitti Asmah, Hassan Mohd Rosli, Hainin TA Engineering (General). Civil engineering (General) TK Electrical engineering. Electronics Nuclear engineering One way to monitor accidents on highway is to analyze the accident characteristic to predict the accident severity. This study applied multinomial logistic regression model to predict accident severity. Predicted accident severities are compared with actual accident severities to evaluate the prediction performances of the model. The aim of this study is to determine the performance of accident severity classifications by multinomial logistic regression model. The predicted accident severities could be used to estimate potential effect of changes in factors contributing to accidents. Data was obtained from the Malaysian Highway Authority for the year 2013 and 2014. The accident severity was grouped into four categories of death, serious injury, minor injury and damage. Based on the results, the model correctly classified accident severities by 63.52% using training data and 61.45% using validation data. The Hosmer- Lemeshow test indicated the model has a good fit between the actual accident severities and predicted accident severities and the ROC results indicted the model able to distinguish between the classifications. The classifier of the model inclined more toward the damages compared to other accident severities resulted in classifying accident severity classes with more samples better and remains weak on the accident severity classes with lesser samples. INTI International University 2022-01 Article PeerReviewed text en cc_by_4 http://eprints.intimal.edu.my/1578/1/joit2022_06r.pdf text en cc_by_4 http://eprints.intimal.edu.my/1578/2/291 Sudesh Nair, Baskara and Haryati, Yaacob and Sitti Asmah, Hassan and Mohd Rosli, Hainin (2022) The Performance of Accident Severity Multiclass Classification. Journal of Innovation and Technology, 2022 (06). pp. 1-6. ISSN 2805-5179 https://ipublishing.intimal.edu.my/joint.html
spellingShingle TA Engineering (General). Civil engineering (General)
TK Electrical engineering. Electronics Nuclear engineering
Sudesh Nair, Baskara
Haryati, Yaacob
Sitti Asmah, Hassan
Mohd Rosli, Hainin
The Performance of Accident Severity Multiclass Classification
title The Performance of Accident Severity Multiclass Classification
title_full The Performance of Accident Severity Multiclass Classification
title_fullStr The Performance of Accident Severity Multiclass Classification
title_full_unstemmed The Performance of Accident Severity Multiclass Classification
title_short The Performance of Accident Severity Multiclass Classification
title_sort performance of accident severity multiclass classification
topic TA Engineering (General). Civil engineering (General)
TK Electrical engineering. Electronics Nuclear engineering
url http://eprints.intimal.edu.my/1578/
http://eprints.intimal.edu.my/1578/
http://eprints.intimal.edu.my/1578/1/joit2022_06r.pdf
http://eprints.intimal.edu.my/1578/2/291