Comparison of road traffic accident prediction effects based on SVR and BP neural network

The Macro-road traffic accident prediction is an important branch of ITS, which could not only make improving direction, but also improve the traffic operation. The paper based on the analyzing the existing macro prediction model, aiming at the existing shortcomings of prediction models with low accuracy and slow convergence speed, introducing the Radial Basis Function, establishing the accident prediction model between Population, Economic situation, cars, road mileage and the index of accident Statistics, and apply Matlab to Simulation to prove the Feasibility and Practicality of the model.

Download Full-text

A Traffic Accident Predictive Model Based on Neural Networks Algorithm and Rough Set Theory

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.97-98.947 ◽

2011 ◽

Vol 97-98 ◽

pp. 947-951 ◽

Cited By ~ 2

Author(s):

Qiao Ru Li ◽

Liang Chen ◽

Chang Guang Cheng ◽

Yue Xiang Pan

Keyword(s):

Neural Network ◽

Set Theory ◽

Rough Set ◽

Bp Neural Network ◽

Traffic Accident ◽

Rough Set Theory ◽

Road Traffic ◽

Black Spot ◽

Black Spots ◽

Neural Network Algorithm

The most important and critical step to improve road traffic safety is prediction and identification of traffic accident black spot. A new prediction model of traffic accident black spots is proposed based on GA-BP neural network algorithm and rough set theory. First of all, the traffic accident statistics of Jinwei Road in Tianjin are analyzed. With consideration of static road conditions, the samples of road accident black spots are obtained by the GA-BP neural network algorithm. Furthermore, an effective road traffic accident black spot prediction model is established by utilizing rough set theory with consideration of the impact of real time dynamic conditions. Finally, a numerical example is illustrated. Experimental results show that the proposed model with the combination of these two theories can reduce the hybrid and burdensome amount of data, lower the false alarm rate and improve the forecasting accuracy of accident black spots.

Download Full-text

COMPARISON OF ROAD TRAFFIC ACCIDENT PREDICTION MODELS FOR TWO-LANE HIGHWAY INTEGRATING TRAFFIC AND PAVEMENT CONDITION PARAMETERS

Journal of Natural Sciences Engineering and Technology ◽

10.51406/jnset.v16i2.1841 ◽

2019 ◽

Vol 16 (2) ◽

pp. 1-10

Author(s):

O. M. POPOOLA ◽

O. S. ABIOLA ◽

S. O. ODUNFA ◽

S. O. ISMAILA

Keyword(s):

Road Traffic Accident ◽

Traffic Accident ◽

Negative Binomial ◽

Prediction Models ◽

Road Traffic ◽

International Roughness Index ◽

Pavement Condition ◽

Accident Prediction ◽

Explanatory Variables ◽

Roughness Index

In Nigeria, literature on the integration of traffic of pavement condition and traffic characteristics in predicting road traffic accident frequency on 2-lane highways are scanty, hence this article to fill the gap. A comparison of road traffic accident frequency prediction models on IIesha-Akure-Owo road based on the data observed between 2012 and 2014 is presented. Negative Binomial (NB), Ordered Logistic (OL) and Zero Inflated Negative Binomial (ZINB) models were used to model the frequency of road traffic accident occurrence using road traffic accident data from the Federal Road Safety Commission (FRSC) and pavement conditions parameters from pavement evaluation unit of the Federal Ministry of Works, Kaduna. The explanatory variables were: annual average daily traffic (aadt), shoulder factor (sf), rut depth (rd), pavement condition index (pci), and international roughness index (iri). The explanatory variables that were statistically significant for the three models are aadt, sf and iri with the estimated coefficients having the expected signs. The number of road traffic accident on the road increases with the traffic volume and the international roughness index while it decreases with shoulder factor. The systematic variation explained by the models amounts to 87.7, 78.1 and 74.4% for NB, ZINB and OL respectively. The research findings suggest the accident prediction models that should be integrated into pavement rehabilitation. Keywords:

Download Full-text