Highway exit ramp accident severity prediction method based on decision tree model
A technology of severity and prediction method, applied in the field of traffic safety, can solve problems that cannot be used to explore the nonlinear relationship of variables, and achieve high-precision results
Inactive Publication Date: 2019-12-10
南京东控智能交通研究院有限公司
View PDF3 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method cannot be used to explore non-linear relationships between variables
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0053] Such as Figure 1-3 As shown, the present invention discloses a method for predicting the severity of highway exit ramp accidents based on a decision tree model, comprising the following steps:
[0054] 1) Obtain the accident data of the highway off-ramp area; in this example, a total of 5538 accidents are used for analysis, and the data comes from three years of accident statistics in a certain area. The accident statistics area includes a total of 326 expressway sections, and the research area is the deceleration area and the ramp exit area with a length of 762 meters (2500 feet);
[0055] 2) Select several factors as independent variables from the influencing factors of highway exit ramp traffic accidents, integrate and screen the data in step 1) according to the characteristics of the required independent variables, and select complete accident samples that meet the requirements to establish an accident severity prediction database , and the data is randomly divide...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention belongs to the field of traffic safety and particularly relates to a highway exit ramp accident severity prediction method based on a decision tree model. Firstly, accident data of an expressway exit ramp is collected from a traffic management department, independent variables are selected according to the actual situation, then integration and screening are conducted in original data according to the characteristics of the needed independent variables, and a complete accident sample meeting the requirement is selected to establish an accident database. The decision tree is trained by using the training set sample. In the decision-making tree prediction model, sensitivity analysis is introduced to reduce the black box problem of the decision-making tree prediction model, eachinput variable in the network is changed, the change of an output result is observed, and finally the prediction precision of the prediction model is analyzed. The method can improve the prediction precision of the accident severity of the exit ramp area of the expressway, and is of great significance for improving the safety of the exit ramp and the whole expressway.
Description
technical field [0001] The invention belongs to the field of traffic safety, and in particular relates to a method for predicting the severity of highway off-ramp accidents based on a decision tree (Decision Tree) model. Background technique [0002] With the development of my country's transportation industry, the traffic volume of highways has increased rapidly, which has brought great traffic safety hazards. The freeway ramp area is a traffic accident-prone area. According to statistics, the length of the ramp route accounts for less than 5% of the entire expressway length, but the traffic accidents in the ramp area account for about 40% of the entire expressway traffic accidents. Among them, the exit ramp traffic The number of accidents is about twice that of the on-ramp area. In principle, there are ways to reduce the number of people killed or injured in road crashes. Reducing the severity of accidents is one of them. Accident severity refers to the damage to people ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q10/06G06K9/62G08G1/01
CPCG06Q10/04G06Q10/0635G08G1/0133G06F18/24323
Inventor 李志斌
Owner 南京东控智能交通研究院有限公司