Motor vehicle pollution discharge monitoring node deployment method based on active space-time diagram convolution

A technology for monitoring nodes and space-time diagrams, applied in prediction, complex mathematical operations, biological neural network models, etc., can solve the problems of limited quantity, high installation and maintenance costs of monitoring nodes, and achieve the effect of improving accuracy

Active Publication Date: 2019-08-23
HANGZHOU DIANZI UNIV
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the high installation and maintenance costs of the monitoring nodes deployed in the urban traffic network, the number is limited by the e

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
  • Motor vehicle pollution discharge monitoring node deployment method based on active space-time diagram convolution
  • Motor vehicle pollution discharge monitoring node deployment method based on active space-time diagram convolution
  • Motor vehicle pollution discharge monitoring node deployment method based on active space-time diagram convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The following is attached figure 1 To further illustrate the present invention, the method of the present invention includes the following steps:

[0049] Step 1: Feature extraction for structural sequence data

[0050] Use the idea of ​​attention mechanism for reference to process the adjacency matrix to obtain the adaptive adjacency matrix:

[0051]

[0052] Among them, A is the adjacency matrix, I N Is the identity matrix, W embed Is a learnable embedding matrix, o is element-wise multiplication, and ReLU is a linear rectification function.

[0053] Send the adaptive adjacency matrix to the graph convolutional network to obtain the adaptive graph convolutional network, which is

[0054]

[0055] Where H (l) For l th Layer nonlinear transformation output, σ(·) is the activation function, H (0) =X is the feature input.

[0056] Adaptive graph convolution can adaptively adjust the weight of edges according to the graph structure and the characteristics of each node, can lear...

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 motor vehicle pollution discharge monitoring node deployment method based on active space-time diagram convolution. The deployed node monitoring data, urban traffic network characteristics, traffic flow data and the like are utilized to predict global motor vehicle exhaust concentration space-time distribution and uncertainty indexes thereof in an urban range; and then anew place is jointly optimized and selected to establish the motor vehicle exhaust emission monitoring node according to the prediction uncertainty index and the inherent characteristic difference between each non-point-arrangement road section and the arranged node road section. Under the condition that the monitoring nodes are deployed, the most appropriate position can be found to arrange themonitoring nodes, so that the accuracy of exhaust emission distribution prediction is improved to the maximum extent, and the method is suitable for multi-stage construction scenes.

Description

Technical field [0001] The invention relates to a method for deploying a motor vehicle emission monitoring node based on active spatiotemporal graph convolution, which belongs to the technical field of deployment of motor vehicle exhaust emission monitoring nodes, and aims to improve the prediction reliability of the temporal and spatial distribution of exhaust emissions in urban road networks. Convolutional neural network and active learning related theories are modeled and solved, and then the problem of location and placement of vehicle exhaust emission monitoring nodes in urban traffic network is studied. Background technique [0002] In recent years, the number of motor vehicles in my country has increased sharply. A large number of harmful gases such as NOx, CO, HC, PMx, etc. emitted by motor vehicles have aggravated urban air pollution, resulting in declining air quality and increasingly frequent smog. In addition, these pollutants also increase the risk of causing urban r...

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): G06Q10/04G06N3/04G06F17/16
CPCG06Q10/043G06F17/16G06N3/045
Inventor 蒋鹏俞程佘青山
Owner HANGZHOU DIANZI 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