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

A Filling Method for Missing Data Based on Correlation Between Data

A technology of correlation and data, applied in the design field of missing data filling method, can solve the problem of inaccurate filling of missing data, etc., and achieve the effect of good neural network model

Active Publication Date: 2017-09-26
UESTC COMSYS INFORMATION
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the inaccurate problem of filling missing data in data preprocessing in the prior art, and propose a method for filling missing data based on the correlation between data

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 Filling Method for Missing Data Based on Correlation Between Data
  • A Filling Method for Missing Data Based on Correlation Between Data
  • A Filling Method for Missing Data Based on Correlation Between Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] Embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0036] Big data is generally expressed in the form of a matrix, such as figure 1 shown. There may be data omissions, such as figure 2 As shown, the place where X is drawn in the figure indicates that this value is missing. These missing data may contain a lot of information and knowledge, which will have a great negative impact on data mining and knowledge discovery. Therefore, these missing data need to be filled.

[0037] The present invention provides a method for filling missing data based on the correlation between data, such as image 3 shown, including the following steps:

[0038] S1. Analyze the association relationship between the data to obtain the association law between the data;

[0039] The data here is the information description of the real society. There are always various correlation phenomena in the real society, so there are mor...

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 filling missing data based on the correlation between data, which comprises the following steps: S1, analyzing the correlation between data, and obtaining the correlation law between the data; S2, finding the best correlation between the data Strong association law; S3, grouping data according to the strongest association law obtained in step S2; S4, pre-filling the missing data in the data; S5, carrying out the design of BP neural network; S6, cyclic application in step S5 The obtained BP neural network is filled with data until all the data is filled. The invention solves the problem of filling missing data by utilizing the correlation between data and designing a BP neural network, provides high-quality data for later data analysis, and has the advantages of simplicity, high efficiency, and accuracy.

Description

technical field [0001] The invention belongs to the technical field of data preprocessing, and in particular relates to the design of a missing data filling method based on an association relationship between data. Background technique [0002] At present, as computer management information systems are widely used in all walks of life, the amount of accumulated data is increasing day by day. In order to make these data play their due role, provide strong support for management decisions in related industries, and improve economic and social benefits , which gave birth to data mining and knowledge discovery, and its methods and technologies emphasize application-oriented. Therefore, its application effect is becoming more and more obvious, and it has attracted more and more attention and attention from people in the industry. [0003] The quality of data involved in data mining and knowledge discovery is the prerequisite for accurate and practical knowledge to be mined. It is...

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 Patents(China)
IPC IPC(8): G06F17/30G06N3/02
Inventor 王淋铱文有庆刘聪
Owner UESTC COMSYS INFORMATION
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