Newly established crossing traffic flow prediction method based on generating type deep belief network

A deep-confidence network and traffic flow technology, applied in the field of traffic flow prediction at new intersections, can solve the problems of less data and low prediction accuracy, and achieve the effect of improving model accuracy and achieving reliability.

Active Publication Date: 2015-11-25
NANJING POWER HORIZON INFORMATION TECH CO LTD
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem of less data and low prediction accuracy in traffic flow forecasting for new

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
  • Newly established crossing traffic flow prediction method based on generating type deep belief network
  • Newly established crossing traffic flow prediction method based on generating type deep belief network
  • Newly established crossing traffic flow prediction method based on generating type deep belief network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific implementation mode one: the following combination Figure 1 to Figure 3 Illustrate this embodiment, the new intersection traffic flow prediction method based on generation type deep belief network described in this embodiment, it comprises the following steps:

[0027] Step 1: Based on deep learning theory and restricted Boltzmann machine, build a generative deep belief network regression model with 144 input and 144 output structures;

[0028] Step 2: using the mature intersection data of the city to which the new intersection belongs to pre-train the deep belief network regression model to obtain the deep belief network regression pre-training model; the mature intersection is an intersection formed by the accumulation of traffic flow data;

[0029] Step 3: Use the pre-stored actual traffic flow data of the new intersection to continue fine-tuning the deep belief network regression pre-training model, and learn the mapping relationship between the sequences ...

specific Embodiment approach 2

[0032] Specific implementation mode two: the following combination Figure 1 to Figure 3 Describe this embodiment, this embodiment will further explain Embodiment 1, the establishment method of the generative deep belief network regression model in step 1 is:

[0033] Construct a deep belief network regression model with 144 input and 144 output structures through the stacking of restricted Boltzmann machines; the deep belief network regression model is an l-layer neural network, with vector x=h 0 represents the original input, with h 1 ,..., h l-1 Indicates the input of the corresponding hidden layer, h l represents the input of the output layer;

[0034] Among them, the l-1th hidden layer uses a sigmoid function and is composed of a restricted Boltzmann machine, and the top activation function uses a pure linear function;

[0035] For the original input x, the joint probability distribution of l-1 hidden layer and output layer p(x,h 1 ,...,h l )for:

[0036] ...

specific Embodiment approach 3

[0079] Specific implementation mode three: the following combination figure 2 and image 3 Describe this implementation mode. This implementation mode will further explain the implementation mode 2. The specific method for obtaining the final deep belief network regression model in step 3 is:

[0080] Step 31: Use the layer-by-layer greedy method to layer the deep belief network regression pre-training model obtained in step 2, from bottom to top, and then use the pre-stored actual traffic flow data of the new intersection to unsupervised the layer that inputs x training;

[0081] Step 32: After the unsupervised training is over, use supervised learning to fine-tune the deep belief network regression pre-training model;

[0082] Step 33: In addition to the hidden layer of the original input x, use the output of the deep belief network regression pre-training model as a supervisory signal, construct a loss function, and use the gradient descent method to return the deep beli...

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

A newly established crossing traffic flow prediction method based on a generating type deep belief network belongs to the technical field of short-period traffic flow prediction. The newly established crossing traffic flow prediction method settles the problems of small amount of data and low prediction precision in traffic flow prediction for a newly established crossing. The newly established crossing traffic flow prediction method comprises the steps of establishing a generating type deep belief network regression model with a 144 input structure and a 144 output structure based on a deep learning theory and a restricted Boltzmann machine; performing pre-training on the deep belief network regression model through mature crossing data of a city to which the newly established crossing is affiliated, and obtaining a deep belief network regression pre-training model; performing fine adjustment on the deep belief network regression pre-training model by means of prestored actual traffic flow data of the newly established crossing, and obtaining a final deep belief network regression model; and acquiring the current actual traffic flow data of the newly established crossing, and performing online prediction on the traffic flow by means of the final deep belief network regression model. The newly established crossing traffic flow prediction method is used for predicting the traffic flow of the newly established crossing.

Description

technical field [0001] The invention relates to a new intersection traffic flow forecasting method based on a generative deep belief network, and belongs to the technical field of short-term traffic flow forecasting. Background technique [0002] With the improvement of the level of urbanization and the rapid development of the economy, the demand for transportation increases rapidly, and the problem of traffic congestion is becoming more and more serious around the world. Traffic congestion directly affects the travel time and cost of travelers. More seriously, the increase in travel time due to delays leads to increased economic losses and environmental pollution, resulting in a decline in urban vitality. Traffic congestion directly causes extra energy consumption and economic loss, and the extension of car travel time leads to extra fuel consumption, thereby increasing vehicle exhaust emissions. Therefore, traffic congestion is also one of the factors leading to increasi...

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): G08G1/065G08G1/01
Inventor 刘辉万杰刘鑫任国瑞黄建华刘智李美兰于乘
Owner NANJING POWER HORIZON INFORMATION TECH CO LTD
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