signalized intersection operation state prediction method and system based on an LSTM model

A technology of operation status and prediction method, applied in the field of intelligent transportation technology management, to achieve high universality, ease urban traffic congestion, and reduce delays

Inactive Publication Date: 2019-05-24
BEIJING JIAOTONG UNIV
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned existing management control methods often lead to control optimization at signalized intersections after a high travel delay.
That is to say, the current control method lacks a method for predicting the operation of signalized intersections, and a corresponding prediction system is urgently needed to make up for the prediction vacancy of the operation status of signalized intersections, so as to predict the operation status of signalized intersections in advance to formulate management and control plans in time

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
  • signalized intersection operation state prediction method and system based on an LSTM model
  • signalized intersection operation state prediction method and system based on an LSTM model
  • signalized intersection operation state prediction method and system based on an LSTM model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] figure 1 It is a flow chart of a method for predicting the operating state of a signalized intersection based on an LSTM model in an embodiment of the present invention, referring to figure 1 , the method includes:

[0060] S1 obtains the floating car data in a certain area through the mobile Internet.

[0061] Obtain mobile Internet floating car data and signal intersection timing data from mobile Internet companies, taxi companies, government and other departments through the mobile Internet, and store the data in the database.

[0062] Construct a signalized intersection operating state prediction model database, and store the collected data in the database. Firstly, the area to be detected is determined, and each intersection in the area is constructed with a data table, in which each intersection has a specific unique ID as a primary key. According to the longitude and latitude information represented by the floating car data, input them into the corresponding s...

Embodiment 2

[0100] This embodiment provides a system applied to the method for predicting the operating state of signalized intersections based on the LSTM model, Figure 4 It is the schematic diagram of the signalized intersection operating state prediction system based on the LSTM model of the present embodiment, referring to Figure 4 , the system includes: a data collection module, a data storage module, a data processing module, a model prediction module and a prediction display module.

[0101] The data collection module is used to obtain the floating car data in a certain area through the mobile Internet;

[0102] A data storage module, used to store the floating car data obtained by the data collection module in a certain area;

[0103] The data processing module is used to extract relevant data matching a signalized intersection within a certain period of time through the data storage module, and filter the data;

[0104] The model prediction module is used for normalizing the ...

Embodiment 3

[0107] This example uses the existing Internet mobile floating car data to predict the state of existing intersections.

[0108] This example uses 15 days of floating car data, the data interval is 3s, and the selected area is: longitude range , latitude range . The specifically selected intersection is the signalized intersection at the intersection of Hepingli West Street and Qingniangou Road in Beijing. Such as Figure 6 As shown, the intersection marked 2 is selected.

[0109] The traffic parameters extracted in this example are: traffic flow, passing time, average speed, number of stops, average delay time, red light duration, green light duration, intersection of secondary trunk roads and branch roads. The target value that needs to be predicted is: intersection signal light delay time. Eliminate bad values ​​and biased values ​​from the collected data.

[0110] Through the prediction module of the model, the parameter data obtained above are trained and predicted, a...

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

No PUM Login to view more

Abstract

The invention provides a signalized intersection operation state prediction method and system based on an LSTM model. The method comprises the steps that floating vehicle data of a certain area are acquired through the mobile internet; extracting related data matched with a certain signalized intersection within a certain period of time according to the floating vehicle data, and screening the data; performing normalization processing on the screened data, dividing the data into a training data set and a test data set, training the data in the training data set through an LSTM model, and testing the trained model through the test data set to obtain a prediction model of the signalized intersection; and predicting the operation state of the signal intersection through newly collected real-time data according to the obtained prediction model of the signal intersection. According to the method, the operation state of the signal intersection is predicted through the mobile internet floating vehicle data, and the traffic operation efficiency of the signal intersection area is improved.

Description

technical field [0001] The invention relates to the field of intelligent transportation technology management, in particular to a method and system for predicting the operating state of a signalized intersection based on an LSTM model. Background technique [0002] With the development of the mobile Internet, it becomes more convenient to collect floating car data based on the smart phone of the owner of the floating car. Based on this, a large amount of floating car data can be obtained for traffic congestion identification, traffic status determination, and formulation of traffic control strategies. [0003] At present, domestic management and control methods for signalized intersections mainly include timing control, induction control and adaptive control. However, the above-mentioned existing management control methods often lead to control optimization at signalized intersections after a relatively high travel delay. That is to say, the current control methods lack the...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q10/04G06Q50/26G08G1/01G06N3/04G06N3/08
Inventor 闫学东陈德启王立威高自友张可
Owner BEIJING JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap