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

Gene selecting method in consideration of gene correlation and device

A gene selection and correlation technology, applied in the field of data processing, can solve the problems of redundant selection results and low precision, and achieve the effects of low redundancy, guaranteed classification accuracy, and high classification accuracy

Active Publication Date: 2019-09-06
HENAN NORMAL UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a gene selection method considering gene correlation, which is used to solve the redundant and low precision of the gene selection results using the prior art At the same time, it also provides a gene selection device that considers the degree of gene correlation. Similarly, it is used to solve the problems of redundancy and low precision in the selection results of genes using existing technologies

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
  • Gene selecting method in consideration of gene correlation and device
  • Gene selecting method in consideration of gene correlation and device
  • Gene selecting method in consideration of gene correlation and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] A gene selection method considering gene correlation in this embodiment is as follows:

[0059] Select at least two neighborhood radii to be compared, use the neighborhood rough set model to reduce the initial gene set at each neighborhood radius, and obtain the initial candidate gene subsets corresponding to each neighborhood radius. Specifically, use the neighborhood rough set model to reduce the initial gene set through the following steps (1) and (2) under each neighborhood radius:

[0060] Given a neighborhood decision information system NDIS=(U,C∪D,V,f), where U is the neighborhood, that is, the domain of discourse, defined as a non-empty finite set of objects, U={x 1 ,x 2 ,...,x n}. C is a set of conditional attributes, which refers to the initial set of genes in a reduction, D is a set of decision attributes, which in this embodiment indicates the category of genetic data, and V is a value range. f:U×(C∪D)→V is an information function, which represents the c...

Embodiment 2

[0093] This embodiment proposes a gene selection method considering gene correlation, such as figure 1 As shown, on the basis of obtaining the primary candidate gene subset by reduction in the method embodiment 1, the primary candidate gene subset is reduced again by using the discrete particle swarm optimization algorithm. Specific steps are as follows:

[0094] (1) Set the initial parameters, including the population size m, the maximum number of iterations max_Iter, the size of the neighborhood δ and the particle dimension, the particle dimension is the number of genes in the gene subset, each dimension of the particle represents a gene, and each One dimension only has two values ​​of 0 or 1. If the value of a certain dimension is 1, the corresponding gene is selected, otherwise the gene is not selected. Therefore, the particles adopt the form of binary code, and the genes corresponding to the value of 1 in all dimensions in each particle are selected by the particles.

...

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 relates to a gene selecting method in consideration of gene correlation and a device, wherein the method and the device belong to the field of data processing technology. Through introducing the correlation between rank correlation coefficient metering genes, an average correlation coefficient between the genes is calculated. By means of the average correlation coefficient, a fitnessfunction for evaluating a neighborhood radius value is improved so that the defined fitness function considers classification precision and the number of genes in result evaluation, and further considers the correlation between the genes. Therefore the gene subset which is selected by the improved fitness function has advantages of low redundancy, low dimension, high precision, etc.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a gene selection method and device considering gene correlation. Background technique [0002] In the existing technology, Peng Xiaoran et al. published "Adaptive Neighborhood Rough Set Neighborhood Size Value Method" in the journal "Computer Application Research" Issue 1 in 2019, and proposed an adaptive neighborhood radius The function, that is, fit(δ)=α length+β ratio, improves the evaluation standard based on human experience only to combine the properties of the actual data set and the classifier, and converts the value of the evaluation neighborhood radius δ into Analyze the reliability of its corresponding reduced set. Among them, the reliability of the reduced set can be intuitively reflected by the data. [0003] The above adaptive function mainly includes two variables length and ratio, length represents the adaptive value of the number of genes in...

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): G16B30/10G16B30/20
CPCG16B30/10G16B30/20
Inventor 孙林宁远翔曹玉洁李晨阳王蓝莹秦小营赵婧殷腾宇王天翔黄金旭
Owner HENAN NORMAL UNIV
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