Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-factor short-term traffic flow prediction method based on neural network LSTM

A technology of neural network and forecasting method, applied in the field of multi-factor short-term traffic flow forecasting based on neural network LSTM, can solve the problems of poor forecasting effect of LSTM forecasting model, achieve accurate and effective forecasting, improve forecasting accuracy, and improve forecasting accuracy Effect

Active Publication Date: 2019-09-10
CHANGAN UNIV
View PDF7 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is to provide a kind of method based on neural network LSTM model multi-factor traffic flow forecasting, in order to solve the problem that the LSTM forecasting model in the prior art predicts poor effect

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
  • Multi-factor short-term traffic flow prediction method based on neural network LSTM
  • Multi-factor short-term traffic flow prediction method based on neural network LSTM
  • Multi-factor short-term traffic flow prediction method based on neural network LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] In this example, the data required for the example are provided by the toll station in Xi’an. Xi’an belongs to the temperate zone semi-humid continental monsoon climate, with four distinct seasons, mild climate and moderate rainfall. Most of the rainy seasons are concentrated in spring and summer, so in the example The data in June 2018 is counted every 15 minutes. Observing the data, from June 16th to June 18th, the light rain turned cloudy for three consecutive days. At this time, the data from June 1st to 18th is used as the training set, and June 19th is used as the test set to predict the traffic flow on June 19th. According to the previous weather data, it is known that June 19th is also cloudy , the weather conditions are different from the previous three days, and the test results are shown in Figure 2. Then delete the data from June 16th to June 18th to exclude the case of three consecutive days of light rain turning cloudy, and then use the data after excludi...

example 2

[0081] In this example, in order to consider the impact of holidays on traffic flow forecasting, the data in February of the Spring Festival in 2018 is selected as the training set, because according to the local climate conditions, winter is cold and less rainy and snowy, which minimizes the impact of weather factors. Because the Spring Festival in February is the most important day of the year, and about 15 days before and after the Spring Festival is the peak period of Spring Festival travel, the selection of data for the Spring Festival in February fully illustrates the impact of holidays on traffic flow. Use the data in February as the training set to train in the LSTM model, and use the data on March 1st as the test set to make predictions. The results are shown in Figure 4(a) and Figure 4(b). The mse and rmse are relatively large. And the R square is less than 0.92. According to the neural network LSTM model, the prediction effect of this model is better, and the R squar...

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 belongs to the field of traffic engineering, and discloses a multi-factor short-term traffic flow prediction method based on neural network LSTM. The multi-factor short-term traffic flowprediction method based on the neural network LSTM comprises the following steps: step 1, obtaining traffic flow data of a period of time, and preprocessing the traffic flow data to obtain short-termtraffic flow data; step 2, screening the short-term traffic flow data according to weather records and holiday records, and dividing data sets; step 3, performing data cleaning, data reconstruction,and normalization; and step 4, establishing an LSTM neural network model, selecting the data set according to the weather conditions and holiday conditions of the date to be predicted, using the selected data set to train the LSTM neural network model and adjust the LSTM parameters, and obtaining the traffic flow of the date to be predicted based on the established LSTM neural network model. The invention provides a more detailed idea, excludes influences of other factors on the traffic flow, such as weather factors and holiday factors, and relatively improves the prediction accuracy, so thatthe traffic flow prediction of a certain period in the future is more accurate and effective.

Description

technical field [0001] The invention belongs to the field of traffic engineering, in particular to a multi-factor short-term traffic flow prediction method based on neural network LSTM. Background technique [0002] Traffic management and intelligent traffic control and other upper-level applications are based on traffic flow. Research on short-term traffic flow prediction models based on time series has always been a research hotspot for scholars at home and abroad. Therefore, traffic control and guidance systems are hot topics in ITS research. Main course. The key to realizing traffic guidance is to accurately predict traffic flow, that is, to use the real-time and historical traffic flow data of existing lanes to predict the traffic flow situation in the next period by establishing a suitable model. Traffic flow forecasting can be divided into long-term forecasting, medium-term forecasting and short-term forecasting, which can serve different research fields. The short-...

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): G08G1/01G08G1/065G06K9/62G06N3/04
CPCG08G1/0125G08G1/065G06N3/044G06N3/045G06F18/214G06F18/24
Inventor 赵祥模程鑫王钰周洲赵怀鑫周经美张立成郝茹茹尚旭明韩睿之陈宇轩常惠
Owner CHANGAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com