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

A method for estimating air particulate pollution degree based on shallow convolution neural network

A convolutional neural network and air particulate matter technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as high algorithm complexity, low detection accuracy, and slow training speed, so as to improve estimation accuracy, Improve training speed and prevent overfitting effect

Active Publication Date: 2019-03-26
NORTHWEST UNIV(CN)
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of high algorithm complexity, slow training speed, prone to overfitting and low detection accuracy in the detection of air particle pollution degree, and propose a kind of air particle pollution based on shallow convolutional neural network. degree estimation method

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
  • A method for estimating air particulate pollution degree based on shallow convolution neural network
  • A method for estimating air particulate pollution degree based on shallow convolution neural network
  • A method for estimating air particulate pollution degree based on shallow convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In this scheme, a shallow convolutional neural network is selected to process the image. The specific idea is: the shallow convolutional neural network can extract local features such as texture and shape of the image, avoiding complicated steps such as feature extraction and feature optimization; Select part of the test set images to generate the corresponding heat map (Heatmap), such as Figure 4 As shown in the third column, by comparing with the original image, it can be found that the focus of image feature extraction is whether the image edge and texture are clear; the existing deep convolutional neural network model is suitable for object recognition tasks, while the shallow convolutional neural network is It can extract local features such as texture and shape of the image, so it is proposed to construct a shallow convolutional neural network model to estimate the PM2.5 index value of the image.

[0055] Such as Figure 1 to Figure 8 As shown, the present inven...

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 method for estimating air particulate pollution degree based on shallow convolution neural network. The basic steps of the method include: 1. Constructing a shallow convolution neural network (PMIE) model with a layer enhancement function; 2. Combining the output of PMIE model with four kinds of weather eigenvalues to construct regression model; 3. Trainning PMIE model and regression model; 4. The PM2.5 index of the test set image is estimated by using the trained PMIE model and regression model. The invention provides a shallow convolution neural network model with layer enhancement function, Combining the output results with four kinds of weather features to estimate the degree of air particulate pollution in the image, the problem caused by feature extraction and feature optimization is effectively avoided, and the specific PM2.5 index value is obtained, which improves the training convergence speed and algorithm robustness, and has better performance.

Description

technical field [0001] The invention relates to the technical field of air pollution degree detection, in particular to a method for estimating air particle pollution degree based on a shallow convolutional neural network. Background technique [0002] Atmospheric particulate matter, smaller than 2.5 microns in diameter (PM2.5), is one of the most harmful air pollutants because it can carry dangerous chemicals deep into the lungs and bloodstream, causing serious health problems. Reliable, easy-to-use and low-cost PM2.5 monitoring systems can greatly improve public awareness of PM2.5 and reduce the health hazards of air pollution. [0003] At present, the detection of PM2.5 index in the air mainly relies on monitoring stations, but because the establishment of monitoring stations requires high setup and maintenance costs, the number of stations is limited, and only local air quality can be detected. With the popularization of camcorders and smart phones, direct estimation of...

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): G06N3/04G06N3/08G06K9/62G06F17/18
CPCG06F17/18G06N3/084G06N3/045G06F18/214
Inventor 冯筠杨雯雯卜起荣王晓宇
Owner NORTHWEST UNIV(CN)
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