Macroscopic road safety analysis unit selection method based on Laplacian spectrum analysis
A technology of safety analysis and Laplacian matrix, applied in the field of macro road safety analysis unit selection, can solve the problems of large amount of information loss, many iterations of two-way spectrum clustering, etc., and achieve a reasonable effect of the scheme
Active Publication Date: 2018-07-24
JIANGSU ZHITONG TRANSPORTATION TECH
View PDF7 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The commonly used two-way spectral clustering has the defects of many iterations and large amount of information loss
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
[0034] A method for selecting macroscopic road safety analysis units based on Laplacian spectrum analysis, such as figure 1 , including the following steps,
[0035] S1. Establish a road network Laplacian matrix.
[0036] S2. Calculate the smallest k eigenvalues and eigenvectors of the Laplacian matrix except 0, and implement K-means clustering on the eigenmatrix constructed from the eigenvectors.
[0037] S3. Check whether the difference of the weight w(u,v) of each cluster is significant, cut the classes with significant difference into different spatial units, and determine the k value and the cutting scheme D of the spatial unit by iterative method 0 ={r 1 ,r 2 ,...,r k}.
[0038] S4, in plan D 0 On the basis of the above, a spatial unit adjustment link based on the similarity of traffic density in the spatial unit is added; firstly, the outlier points with significant differences in the traffic density in the spatial unit are identified through the box plot; secon...
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 provides a macroscopic road safety analysis unit selection method based on Laplacian spectrum analysis. The method comprises the following steps: establishing a Laplacian matrix of a road network; calculating k minimal characteristic values and characteristic vectors except 0 in the Laplacian matrix, and performing K-means clustering on a characteristic matrix constructed by the characteristic vectors; checking whether differences of various cluster weights w (u, v) are obvious, segmenting clusters with obvious differences as different space units, and determining the value k anda segmentation scheme D0={r1, r2, ..., rk} of the space units by using an iterative method; increasing a space unit adjustment link based on traffic density similarity in the space units on the basisof the scheme D0; and finally, obtaining a selection scheme for macroscopic road safety analysis units with the highest traffic density characteristic similarity in the units and the highest difference among different units. According to the method disclosed by the invention, the selection scheme of the macroscopic road safety analysis units is efficiently and stably obtained according to trafficflow similarity characteristics, the scheme is reasonable, and the requirement on macroscopic road safety analysis can be met.
Description
technical field [0001] The invention relates to a method for selecting macroscopic road safety analysis units based on Laplacian spectrum analysis. Background technique [0002] Traffic safety analysis at the macro level involves the aggregation of traffic safety accidents in various spatial units, while ignoring traffic accidents at specific locations. Different research units will directly affect the analysis results. In order to count the population, social economy and other indicators in the unit, most macroscopic traffic safety analyzes use administrative divisions, traffic analysis districts, streets, etc. as spatial units. [0003] However, this kind of static regional division method ignores the characteristics of traffic operation. Studies have shown that traffic flow operation status is related to traffic safety characteristics, and it is necessary to incorporate traffic flow characteristics into the consideration factors for the selection of spatial units. In ess...
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 IPC IPC(8): G08G1/01G06Q50/30G06K9/62
CPCG08G1/0125G06F18/22G06Q50/40
Inventor 吕伟韬刘林陈凝李攀
Owner JIANGSU ZHITONG TRANSPORTATION TECH