Testing The Performance of Random Forest and Support Vector Machine Algorithms for Predicting Cyclist Casualty Severity

Abstract

Traditional statistical regression models for predicting casualty severity have fundamental limitations. Machine learning algorithms for classifications have started to be applied in severity analysis in order to relax the assumptions and provide better accuracy in the models. However, the performances of highly advised classification algorithms for predicting cyclist casualty severity, which particularly occurred at roundabouts, have not been investigated comprehensively. Therefore, the study in this paper developed classification models for cyclist casualty severity prediction by applying the highest two advised algorithms in the literature namely Random Forest and Support Vector Machine. The dataset included 439 cyclist casualties which were recorded at give-way roundabouts in the North East of England. The predictive variables were sociodemographic information about cyclists, weather conditions, behavior-related contributory factors, speed limit, and roundabout geometrical parameters. 70% of the records were randomly selected for the training stage and 30% were used for the testing in both Random Forest and Support Vector Machine algorithms. After training the algorithm, the testing results showed that the Random Forest algorithm predicted the outcomes with 88.6% classification accuracy. On the other hand, Support Vector Machine algorithm predicted the testing values with 84.73% classification accuracy. The algorithms misestimated 18 and 20 of the casualties in Random Forest and Support Vector Machine, respectively. The outcomes suggested that both Random Forest and Support Vector Machine algorithms were applicable for cyclist casualty severity prediction models with high performance.

Authors and Affiliations

Nurten AKGÜN

Keywords

Related Articles

Investigation of some thermophysical properties of Asphodelus aestivus reinforced polyester composite

In this research, both environmentally friendly and economical composites have been produced by using biomass wastes in unsaturated polyester. The use of renewable biomass wastes as a filler in unsaturated polyester is r...

Modeling of a solar air collector heat transfer coefficient with regression algorithms

Solar air collectors (SAC) are thermodynamic systems that convert solar energy into useful fluid energy. SACs are very common in heating, cooling, food drying, and many other low-temperature applications. In this study,...

Comparison of equivalent earthquake load method for TEC-2007 and TBEC-2018: Adıyaman province example

In this study, in terms of their approach to the equivalent earthquake load method, a comparison of the Turkish building earthquake codes published in 2007 and 2018 was made. For the study a reinforced concrete residenti...

Determination of water sensitivity of nanosilica added hot mix asphalt

In this study, the effects of nanosilica (NS) additive on the water sensitivity of hot mix asphalt (HMA) pavements were investigated. For this, NS-modified asphalts were prepared by adding NS at rates of 1%, 3%, 5% and...

A novel design for concrete culverts absorbing explosive energy from homemade explosives

With the increasing number of terrorist attacks for the last 40 years, terrorist organizations have devised various attack tactics. One of these tactics is to attack by placing homemade explosives inside culverts that ar...

Download PDF file
  • EP ID EP727929
  • DOI 10.5505/fujece.2023.57966
  • Views 56
  • Downloads 0

How To Cite

Nurten AKGÜN (2023). Testing The Performance of Random Forest and Support Vector Machine Algorithms for Predicting Cyclist Casualty Severity. Firat University Journal of Experimental and Computational Engineering, 2(3), -. https://europub.co.uk/articles/-A-727929