A Highway Accident Frequency Prediction Method Considering Time-varying Characteristics of Risk Factors

Abstract

The invention discloses a road accident frequency prediction method considering the time-varying characteristics of risk factors. The steps are as follows: 1. Collect and process historical traffic accident data and related risk factor data; 2. Establish a Logistic regression model; 3. Use Youden Calculate the classification threshold of the Logistic model by the index method; 4. Calculate the positive predictive value (Positive predictive value) and negative predictive value (Negative predictive value) of the model based on the Logistic model and historical accident data; 5. Use the calculated positive predictive value and The negative predictive value is used to predict the frequency of accidents. The invention can overcome the problem that the traditional accident frequency model cannot reflect the influence of time-varying characteristics of risk factors on accidents, and is beneficial to improving the prediction accuracy of the accident frequency prediction method.

Description

technical field [0001] The invention relates to a method for predicting the frequency of road accidents considering the time-varying characteristics of risk factors, and belongs to the technical field of road traffic safety analysis. Background technique [0002] Constructing the relationship between the frequency of traffic accidents and risk factors such as road geometric characteristics, traffic conditions, and weather, so as to predict the frequency of accidents, is a common method for road safety evaluation. In the traditional accident frequency prediction model, since the dependent variable is the total number of accidents in a long time range (such as one year), for time-varying risk factors such as traffic conditions and weather, only statistical indicators within the corresponding time range can be used ( Such as annual average daily traffic volume, total annual rainfall) as independent variables. However, the time-varying characteristics of the above factors have ...

AI Technical Summary

Problems solved by technology

However, the time-varying characteristics of the above factors have a significant impact on accident risk

Compared with non-peak hours, the road traffic volume during peak hours is large, the occupancy rate is high, and the vehicle speed is low. Reduced visibility for the driver, increased braking distance and increased risk of accidents

To sum up, the traditional accident frequency prediction model cannot accurately describe the influence of time-varying characteristics of factors on accident risk, resulting in inaccurate prediction of road accident frequency.

Images