Analysis and Comparison of Traffic Accident Regression Prediction Model

Weihong Ma, Zhenzhou Yuan

Abstract

The purpose of this paper is to analyse the relationship between the number of road traffic accidents and road length, traffic conditions and other factors. Taking the number of road traffic accidents subject to Poisson regression, negative binomial (NB) regression and Zero Inflated Negative Binomial (NINB) regression as response variables, we construct a generalized linear model by introducing a joint function. We construct the Traffic Accident Prediction Model Based on Random Forest (RF) Regression. The defect models are compared, and based on the predictive model, selecting the significant factors and determining the degree of influence factors of road traffic accidents, reducing the number of traffic accidents and improve the overall security of the road.

Download


Paper Citation


in Harvard Style

Ma W. and Yuan Z. (2018). Analysis and Comparison of Traffic Accident Regression Prediction Model.In 3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT, ISBN 978-989-758-312-4, pages 364-369. DOI: 10.5220/0006970803640369


in Bibtex Style

@conference{icectt18,
author={Weihong Ma and Zhenzhou Yuan},
title={Analysis and Comparison of Traffic Accident Regression Prediction Model},
booktitle={3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT,},
year={2018},
pages={364-369},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006970803640369},
isbn={978-989-758-312-4},
}


in EndNote Style

TY - CONF

JO - 3rd International Conference on Electromechanical Control Technology and Transportation - Volume 1: ICECTT,
TI - Analysis and Comparison of Traffic Accident Regression Prediction Model
SN - 978-989-758-312-4
AU - Ma W.
AU - Yuan Z.
PY - 2018
SP - 364
EP - 369
DO - 10.5220/0006970803640369