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

Air quality prediction method based on multi-step recursive prediction

A technology of air quality and prediction method, which is applied in the direction of prediction, neural learning method, biological neural network model, etc., can solve the problem of slow training speed of Seq2Seq model, achieve the effect of maintaining prediction accuracy, reducing error accumulation, and improving prediction accuracy

Inactive Publication Date: 2019-07-30
BEIJING UNIV OF TECH
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of slow Seq2Seq model training speed, and reduce error accumulation to improve prediction accuracy

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
  • Air quality prediction method based on multi-step recursive prediction
  • Air quality prediction method based on multi-step recursive prediction
  • Air quality prediction method based on multi-step recursive prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Taking air quality prediction as an example, the following is a detailed description of the present invention in combination with examples and accompanying drawings.

[0020] The present invention uses a PC and requires a GPU with sufficient computing power to accelerate training. like figure 1 As shown, the concrete steps of a kind of air quality prediction method based on extreme learning machine provided by the present invention are as follows:

[0021] Step 1. Acquire data and preprocess, construct input and output;

[0022] The acquired data generally includes air quality data and weather data, which need to be processed into an input sequence and an output sequence. Generally, the input sequence includes pollutant data and weather data for a period of time in the past. Let D={X, Y} be the processed data set. Where X is the input sequence, that is, historical data, including pollutant data and weather data. For each input sequence x∈R S×Q , whose length is S, ...

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 an air quality prediction method based on multi-step recursive prediction, and the method comprises the following steps: obtaining and preprocessing air quality data and weather data, and constructing input data and output data, wherein the input data of the encoder comprises pollutant data and historical meteorological data, the input data of the decoder comprises the output result of the encoder, the weather forecast data and the pollutant data at the previous moment; dividing the data into training data and test data; using the training data to train the Seq2Seq model; and using the test data to test the prediction result. According to the method, the air quality is predicted by using the Seq2Seq model. An RNN of an encoder is replaced by using a full connectionlayer, and a time sequence relation of an input sequence is reserved by using position coding, so that the effect of accelerating training while maintaining the prediction precision is achieved, erroraccumulation can be effectively reduced, and the prediction precision is improved.

Description

technical field [0001] The invention belongs to the technical field of data mining and is mainly used for establishing an air quality prediction model. Background technique [0002] At present, air pollution in developing countries such as China and India is very serious due to rapid industrialization. Air pollution poses a threat to people's health, especially the respiratory system, and can even cause death. Therefore, the prediction of air quality is particularly important, because if we can know when the pollution will appear, then people can take measures to protect themselves in advance. At present, many scholars are conducting research on air quality prediction, most of which use ANN (Artificial Neural Network, artificial neural network), because it has a very powerful nonlinear fitting ability compared to other machine learning algorithms. Since there is a very complex nonlinear relationship between air pollutants and their impact factors, it is often impossible to...

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): G06Q10/04G06Q10/06G06N3/08G06K9/62
CPCG06Q10/04G06Q10/06395G06N3/08G06F18/214
Inventor 刘博闫硕
Owner BEIJING UNIV OF TECH
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