Abstract
Predicting crash injury severity is a crucial constituent of reducing the consequences of traffic crashes. This study developed machine learning (ML) models to predict crash injury severity using 15 crash-related parameters. Separate ML models for each cluster were obtained using fuzzy c-means, which enhanced the predicting capability. Finally, four ML models were developed: feed-forward neural networks (FNN), support vector machine (SVM), fuzzy C-means clustering based feed-forward neural network (FNN-FCM), and fuzzy c-means based support vector machine (SVM-FCM). Features that were easily identified with little investigation on crash sites were used as an input so that the trauma center can predict the crash severity level based on the initial information provided from the crash site and prepare accordingly for the treatment of the victims. The input parameters mainly include vehicle attributes and road condition attributes. This study used the crash database of Great Britain for the years 2011–2016. A random sample of crashes representing each year was used considering the same share of severe and non-severe crashes. The models were compared based on injury severity prediction accuracy, sensitivity, precision, and harmonic mean of sensitivity and precision (i.e., F1 score). The SVM-FCM model outperformed the other developed models in terms of accuracy and F1 score in predicting the injury severity level of severe and non-severe crashes. This study concluded that the FCM clustering algorithm enhanced the prediction power of FNN and SVM models.
Highlights
The aim of this study is to investigate the role of clustering algorithms in the enhancement of the performance of machine learning models, such as artificial neural networks (ANN) and support vector machine (SVM)
The comparative analysis showed that the SVM-fuzzy c-means clustering (FCM) model performed better than the other developed models based on accuracy and F1 score in predicting severe and non-severe accidents
This study focused on predicting traffic crash severity by employing 15 crash-related parameters in four machine learning models: forward neural networks (FNN), SVM, FCM clustering-based FNN, and FCM-based SVM
Summary
The number of traffic crashes and their victims has been a rising trend globally due to increases in population and motorization. Different statistical techniques have been employed to predict the severity of traffic crashes Among those statistical models, ordered probit (OP) model [1,2,3,4,5], ordered logit (OL) model [6], multinomial logit (ML) model [7,8], and logistic regression (LR) model [9] are all widely used. Public Health 2020, 17, 5497 between explanatory and dependent variables can be untrue and lead to inaccurate inferences [10,11] To overcome these limitations, many ML techniques have been introduced to model crash severity [12]. These models include the Bayesian network (BN) model [13,14], regression tree cart model [15,16], and artificial neural networks (ANN) [10,17]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Environmental Research and Public Health
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
