Road network traffic state judgment method based on MFD + spectral clustering + SVM
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of traffic status and discrimination method, applied in the field of neural network, can solve the problem of too idealized classification
Pending Publication Date: 2019-09-06
GUANGDONG COMM POLYTECHNIC
View PDF5 Cites 17 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0007] The road network MFD can judge the traffic status of the roa
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 more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0073] Such as Figures 1 to 8 Shown is a kind of embodiment of the road network traffic status discrimination method based on MFD+spectral clustering+SVM of the present invention, concrete steps are as follows:
[0074] (1) First use the spectral clustering algorithm to classify the traffic status of the road network MFD;
[0075] (2) Then use the divided road network MFD parameters to train the SVM multi-classifier, and give a method for evaluating the accuracy of the model classification results based on the confusion matrix;
[0076] (3) Finally, a vehicle networking simulation platform is built, and the BP neural network classifier is selected as a comparative classifier for empirical analysis.
[0077] Among them, in step (1), the traffic state classification of the road network MFD is carried out by using the spectral clustering algorithm,
[0078] Specific steps are as follows:
[0079] (1) Define sample data set X={x i |i=1,2,…,n}, determine the number of clusters...
specific Embodiment
[0139] Select the core road network intersection group in Tianhe District, Guangzhou City as the experimental area, such as figure 2 shown. According to the road network layout map, actual road lane layout, intersection layout, traffic flow data, intersection signal control scheme, traffic organization mode and other information, build a micro-traffic simulation platform for Internet of Vehicles based on Vissim software.
[0140] Set 100% of the vehicles as connected vehicles, read the relevant data of each connected vehicle every 15 seconds, select the data statistics period as 120s, and the simulation time as 32400s. Import the networked vehicle data file (*.fzp) of the simulation result into the EXCEL file, use VBA macro programming to realize the NCD estimation method, and finally obtain 270 road network weighted traffic flow qNCD, road network weighted traffic density kNCD, and draw the simulated road network MFD, such as image 3 and Figure 4 shown.
[0141] Functi...
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 relates to the field of neural network technical methods, in particular to a road network traffic state judgment method based on MFD + spectral clustering + SVM, and the method comprisesthe following specific steps: (1) firstly, carrying out traffic state grade division on a road network MFD by using a spectral clustering algorithm; (2) training an SVM multi-classifier by using thedivided road network MFD parameters, and giving a model classification result precision evaluation method based on a confusion matrix; and (3) finally constructing an Internet of Vehicles simulation platform, selecting a BP neural network classifier as a comparison classifier, and carrying out truth analysis. In the road network traffic state judgment method based on MFD + spectral clustering + SVM, traffic state grade division is performed on the road network MFD by using a spectral clustering algorithm; then an SVM multi-classifier is trained by using the divided road network MFD parameters,a classification result precision evaluation method is given based on a confusion matrix, finally an Internet of Vehicles simulation platform is built, a BP neural network classifier is selected as acomparison classifier, and truth analysis is carried out.
Description
technical field [0001] The present invention relates to the field of neural network technology and method, and more specifically, relates to a road network traffic state discrimination method based on MFD+spectral clustering+SVM. Background technique [0002] The state of road network traffic objectively reflects the operation of road network traffic, which is the key to improving the efficiency of urban traffic control and management. The road network traffic state discrimination method has always been a research hotspot in the field of intelligent transportation. Generally speaking, it can be divided into two categories: methods based on data mining and methods based on basic traffic flow graphs. [0003] (1) Based on data mining method [0004] Based on the data mining method, it refers to the use of neural network, deep learning, clustering algorithm, support vector machine, Bayesian method and other machine learning algorithms for data mining, so as to automatically de...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more