Traffic jam condition prediction method and system based on two-stage spectral clustering
A technology of traffic congestion and forecasting method, applied in forecasting, data processing applications, instruments, etc., can solve problems such as long congestion time, traffic congestion, slow dredging, etc., and achieve strong generalization ability, fast speed, and strong error correction ability Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] like figure 1 and figure 2 As shown, the traffic jam prediction method based on two-stage spectral clustering of the present embodiment includes the following steps:
[0050] Step 1. Obtain street information and meteorological information of various periods in several historical periods of the city;
[0051] The street information includes the street position, the traffic flow of each street in each time period, and the traffic flow direction of each intersection in each time period;
[0052] In the present embodiment, a cycle T is divided into multiple time periods t, and the street traffic flow, street vehicle migration matrix and meteorological information of each period in the past 7 days are obtained, that is, 7 cycles (days), and each day is divided into 4 Three time periods: peak hours (07:00-11:00) on weekdays and weekends, daytime hours (11:00-16:00), evening peak hours (16:00-21:00) and late night hours ( 21:00-24:00; 00:00-09:00);
[0053] The meteorolo...
Embodiment 2
[0095] The present embodiment provides a traffic jam prediction system based on two-stage spectral clustering, including:
[0096] The data acquisition module is used to acquire street information and weather information of the city at various times;
[0097] The clustering module is used for clustering according to the street information of each time period, and obtains the clusters to which the streets belong in each time period;
[0098] The first prediction module is used to predict the street traffic flow in the next cycle using the gradient enhanced regression tree model according to the clusters and meteorological information to which the street belongs in each time period;
[0099]The second prediction module is used to predict the traffic flow of each street in different time periods in the next cycle using a multi-similarity reasoning model according to the clusters and meteorological information to which the streets belong in each period;
[0100] The street conges...
Embodiment 3
[0104] This embodiment provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned method for predicting traffic congestion based on two-level spectral clustering .
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


