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

Smart city traffic signal control recommendation method, system and device

A signal control and traffic signal technology, applied in the field of smart city traffic signal control recommendation, can solve the problems of low efficiency and low reliability

Active Publication Date: 2019-06-14
ENJOYOR COMPANY LIMITED
View PDF7 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This control method has the disadvantages of non-reproducibility, low efficiency and low reliability, and new technologies are urgently needed as auxiliary means to alleviate such problems

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
  • Smart city traffic signal control recommendation method, system and device
  • Smart city traffic signal control recommendation method, system and device
  • Smart city traffic signal control recommendation method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0046] A kind of implementation mode 1, refer to image 3 , LSTM can solve the problem of long-term and short-term dependence. LSTM includes three gate designs, namely: input gate, forget gate and output gate. The input gate processes the input information at the current moment and is responsible for passing instant information to the memory. The cell; the forget gate processes the long-term state and is responsible for continuing to store long-term information; the output gate processes the current cell state and is responsible for controlling the long-term state as the output of the current LSTM. The data of each period is processed in turn, and the model parameters are updated by using the backpropagation of the error, and then the information of the specified period in the future is estimated. The formula of the gate is as follows, where σ is the activation function, W is the change matrix, and X t is the input parameter, b is the bias function:

[0047] g(X)=σ(WX t +b)...

Embodiment approach 2

[0052] A kind of implementation mode 2, refer to Figure 4 , RNN algorithm process: x t Indicates the information input at time t, s t Represents the hidden state of the model at sequence index t. the s t by x t and s t-1 jointly decide; o t Represents the output of the model at sequence index t. o t Only determined by the model's current hidden state st. The two matrices U and W are respectively x in the RNN network t and s t Linear relationship parameter, V is s t The parameters of the output layer. It is shared across the entire RNN network. The RNN loop processes the data of each cycle, backpropagates the error to update the parameter value, and estimates the information of the future cycle. The algorithm formula is as follows, where W represents the weight from the hidden layer to the hidden layer, and U represents the weight from the input layer to the hidden layer. The weight of the hidden layer, V represents the weight from the hidden layer to the output l...

Embodiment approach 3

[0061] A kind of embodiment 3, deep learning algorithm model selection process, deep learning algorithm N, refer to embodiment 1, embodiment 2, training obtains N deep learning algorithm models, compares model performance, selects and satisfies according to preset model performance requirements A deep learning algorithm model for model performance requirements. Model performance includes but is not limited to: the target value at the end of model training, the time required for model training, the output performance of the model applied to a new data set, etc.

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 smart city traffic signal control recommendation method, system and device. Control scheme data and detector data are learned based on a deep learning algorithm, new knowledge is obtained, the knowledge is updated, a knowledge structure is recombined, signal control recommendation parameter value output is realized, a closed-loop self-learning mechanism is formed, and update and iteration of a model can be continuously carried out according to feedback. A deep learning algorithm model meeting the performance requirement of the model is selected through an algorithm selector; a network structure meeting the searching requirement of the deep learning algorithm is selected through a neural framework generator; data related to a control scheme operator is extracted astraining data of the model, and a signal control scheme of model recommendation is more accurate and more targeted; and a regulation and control triggering mechanism is arranged, and a signal controlrecommendation is timely and effectively given.

Description

technical field [0001] The invention belongs to the field of traffic control, and relates to a smart city traffic signal control recommendation method, system and device. Background technique [0002] With the sustained and rapid development of my country's national economy, the continuous acceleration of urbanization and the continuous improvement of vehicle motorization, urban traffic problems have become a bottleneck restricting the sustainable development of urban economy and society to a certain extent. Advanced urban traffic control system is one of the important ways to improve the efficiency of urban traffic operation and an important symbol of urban modernization, especially in first-tier cities. At this stage, how to maximize the effectiveness of the established signal system and signal control equipment is the most urgent task. [0003] In order to give full play to the role of urban traffic control systems, traffic signal optimization services are receiving more...

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): G08G1/01G08G1/07
Inventor 金峻臣周浩敏李瑶郭海锋温晓岳赵天灏
Owner ENJOYOR COMPANY LIMITED
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