Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 19;17(20):7598.
doi: 10.3390/ijerph17207598.

Traffic Crash Severity Prediction-A Synergy by Hybrid Principal Component Analysis and Machine Learning Models

Khaled Assi  1
Affiliations

Traffic Crash Severity Prediction-A Synergy by Hybrid Principal Component Analysis and Machine Learning Models

Khaled Assi. Int J Environ Res Public Health. .

Abstract

The accurate prediction of road traffic crash (RTC) severity contributes to generating crucial information, which can be used to adopt appropriate measures to reduce the aftermath of crashes. This study aims to develop a hybrid system using principal component analysis (PCA) with multilayer perceptron neural networks (MLP-NN) and support vector machines (SVM) in predicting RTC severity. PCA shows that the first nine components have an eigenvalue greater than one. The cumulative variance percentage explained by these principal components was found to be 67%. The prediction accuracies of the models developed using the original attributes were compared with those of the models developed using principal components. It was found that the testing accuracies of MLP-NN and SVM increased from 64.50% and 62.70% to 82.70% and 80.70%, respectively, after using principal components. The proposed models would be beneficial to trauma centers in predicting crash severity with high accuracy so that they would be able to prepare for appropriate and prompt medical treatment.

Keywords: emergency management; neural networks (NN); principal component analysis (PCA); support vector machine (SVM); traffic crash severity; vehicle crashes.

PubMed Disclaimer

Conflict of interest statement

The author declares no conflict of interest.

Figures

Figure 1
Figure 1
Simplified structure of MLP-NN.
Figure 2
Figure 2
Data separation by hyperplanes.
Figure 3
Figure 3
Eigenvalues for all components considered (scree plot).
Figure 4
Figure 4
Cumulative variance plot.
Figure 5
Figure 5
Confusion matrices for the MLP-NN model using original crash attributes (training and testing data).
Figure 6
Figure 6
Confusion matrices for the SVM model using original crash attributes (training and testing data).
Figure 7
Figure 7
Confusion matrices for the MLP-NN model using principal components (training and testing data).
Figure 8
Figure 8
Confusion matrices for the SVM model using principal components (training and testing data).
Figure 9
Figure 9
Testing classification accuracies for the developed models.
Figure 10
Figure 10
F1 scores for the developed models (serious/fatal injury and slight injury).
See this image and copyright information in PMC

References

    1. Peden M., Scurfield R., Sleet D., Hyder A.A., Mathers C., Jarawan E., Hyder A.A., Mohan D., Jarawan E. World Report on Road Traffic Injury Prevention. World Health Organizatio; Geneva, Switzerland: 2004.
    1. World Health Organization . Global Status Report on Road Safety. World Health Organizatio; Geneva, Switzerland: 2018.
    1. Andersson R., Menckel E. On the prevention of accidents and injuries: A comparative analysis of conceptual frameworks. Accid. Anal. Prev. 1995;27:757–768. doi: 10.1016/0001-4575(95)00031-3. - DOI - PubMed
    1. Mujalli R.O., de Oña J. Injury severity models for motor vehicle accidents: A review. Proc. Inst. Civ. Eng. Transp. 2013;166:255–270. doi: 10.1680/tran.11.00026. - DOI
    1. Sanguansat P. Principal Component Analysis: Engineering Applications. BoD–Books on Demand, Intech; Rijeka, Croatia: 2012.

Publication types

LinkOut - more resources