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

CNN multipoint regression prediction model for traffic flow prediction

A technology of convolutional neural network and traffic flow, which is applied in the field of multi-point regression prediction model, achieves the effect of time complexity and feature selection, and avoids the disappearance of spatial information

Inactive Publication Date: 2018-11-16
ZHANGJIAGANG INST OF IND TECH SOOCHOW UNIV +1
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0024] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art. Compared with the traditional statistical regression model, it has the feature extraction ability of data spatial correlation, and has the advantages of local perceptual field and weight sharing, so that the time complexity and Better balance in feature selection

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
  • CNN multipoint regression prediction model for traffic flow prediction
  • CNN multipoint regression prediction model for traffic flow prediction
  • CNN multipoint regression prediction model for traffic flow prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Such as figure 1 with figure 2 As shown, a convolutional neural network multi-point regression forecasting model for traffic flow forecasting includes the following steps:

[0057] The first perceptual input layer: the input of training data, which usually needs to be converted into matrix form;

[0058] The second convolutional layer: Convolve the input layer data and output it after passing the activation function;

[0059] The third convolutional layer: Convolve the output of the previous layer as input, and output it after passing the activation function; the number of convolutional layers is determined according to the actual effect, and more convolutional layers cannot guarantee the performance of the network model. Improvement. The third layer is the best result after our experiment. For this convolutional layer, it can also include the fourth convolutional layer, the fifth convolutional layer, and other convolutional layers.

[0060] The fourth full link lay...

Embodiment 2

[0091] The implementation steps of traffic state prediction for expressways in Shanghai are as follows:

[0092] 1) Based on the data of the Shanghai expressway ground induction coil, the space-time relationship of the coil is divided into different section types: ordinary section, ramp section, diversion section, weaving section section, and confluence section;

[0093] 2) Calibrate the congestion nodes through the TSI index of Shanghai:

[0094]

[0095] Among them, h represents the actual vehicle speed, f represents the free flow speed; TSI identifies the congested node;

[0096] Table 1 Road traffic status corresponding to different index intervals

[0097]

[0098] 3) Carry out the sensitivity analysis of the feature, take the feature samples with different numbers of nodes upstream and different numbers of nodes downstream of the target point to predict the final target point; enable the multi-point regression prediction model of the six-layer non-pooling convolut...

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 discloses a CNN multipoint regression prediction model for traffic flow prediction. The CNN multipoint regression prediction model comprises the following steps that a first perception input layer; a second convolutional layer that performs convolution on the input layer data and outputs the data by an activation function; a multi-layer convolutional layer that performs convolution on the output of the last layer as an input and outputs data by an activation function; a fourth full-link layer; a fifth discard layer: a random discard layer discards some redundant neurons and retains 40% to 70% of the full-link nodes of the last layer; a sixth output layer that subjects the effective node output of the discard layer to regression calculation, obtains a regression value as the output of the entire network, sets a total of m output nodes, that is, maps the full-link layer to the output layer to achieve weight combination. Compared with a traditional statistical regression model, the CNN multipoint regression prediction model has a feature extraction ability associated with a data space, has the advantages of local receptive field and weight sharing, and makes a better balance in time complexity and feature selection.

Description

technical field [0001] The invention relates to a multi-point regression prediction model of a convolutional neural network, in particular to a multi-point regression prediction model of a convolutional neural network for traffic flow prediction. Background technique [0002] The regression analysis forecasting method is based on the analysis of the correlation between the independent variables and the dependent variables of various phenomena, and establishes the regression equation between the variables, and uses the regression equation as a forecasting model to predict according to the quantitative changes of the independent variables in the forecast period. Most of the dependent variable relationships are correlated. Therefore, the regression analysis prediction method is an important prediction method. When we predict the future development status and level of the phenomenon of the research object, if we can affect the main factors of the prediction object of the research...

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
IPC IPC(8): G06Q10/04G06N3/04
CPCG06Q10/04G06N3/045
Inventor 陶砚蕴沈智威王翔沈智勇
Owner ZHANGJIAGANG INST OF IND TECH SOOCHOW 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