Feature selection method based on multi-core robust fuzzy rough set model

A feature selection method and fuzzy rough set technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as information loss, and achieve the effect of strong performance and robust performance

Inactive Publication Date: 2019-11-05
SOUTHWEST JIAOTONG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of the problem that the existing robust feature selection method will cause information loss when processing data containing noise samples, the purpose of the present invention is to provide a multi-core robust feature selection method (MMRFRS) that can retain the inherent information of the data, so that it has Better classification 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
  • Feature selection method based on multi-core robust fuzzy rough set model
  • Feature selection method based on multi-core robust fuzzy rough set model
  • Feature selection method based on multi-core robust fuzzy rough set model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0057] In order to verify the effectiveness of the present invention, the present invention was compared with two recently proposed algorithms, NRFS and AVDP, on a total of 10 real data sets from the UCI machine learning knowledge base. The original data set will be randomly divided into ten parts, nine of which will be used as the training set and the remaining one will be used as the test set. Feature selection is performed on the training set, and then the reduced training and test sets are sent to the classifier to obtain classification accuracy. After 10 epochs, the mean and variance of classification accuracy are calculated as the final performance. The details of the dataset are shown in Table 1.

[0058] Table 1 Details of the dataset

[0059]

[0060] There are two methods for calculating the lower approximation in the present invention, which are R S and R θ , there are also two multi-core operators used to calculate the similarity between samples, namely K ...

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 feature selection method based on a multi-core robust fuzzy rough set model, and the method comprises the following steps: firstly, respectively finding neighbor samples of each sample in all types of samples; secondly, calculating a fuzzy decision that each sample belongs to each category by utilizing the neighbor samples; replacing an original decision of a sample witha fuzzy decision, and giving a multi-core robust fuzzy rough set model in combination with a k-nearest neighbor thought; then, combining a greedy forward algorithm with a positive domain calculation mode of the proposed model to select a preliminary feature subset; and finally, iteratively selecting an optimal subset of the feature subsets selected in the last step by using a classifier. Accordingto the method, the feature selection problem of the high-dimensional data containing noise is effectively solved, so that the result of data preprocessing is more reliable, and more favorable data support is provided for subsequent tasks such as classification.

Description

technical field [0001] The invention relates to the field of data preprocessing of machine learning, in particular to a feature selection method based on a multi-core robust fuzzy rough set model. Background technique [0002] Rough set theory is an effective mathematical tool for dealing with uncertain, inaccurate and fuzzy data, and has been widely used in the fields of machine learning and pattern recognition. Fuzzy information granulation and approximate reasoning are two basic modules of human cognition and reasoning. Based on this, the classical rough set model is extended to fuzzy rough set to deal with the existing information uncertainty. [0003] A typical application of fuzzy rough sets is feature selection. With the development of computer and database technology, a large number of attributes can be acquired and stored in the database for several practical applications. For classification learning, some attributes may be irrelevant or redundant, and they may g...

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): G06K9/62
CPCG06F18/211G06F18/22G06F18/241
Inventor 陈红梅王生武樊鑫李天瑞封云飞袁钟
Owner SOUTHWEST JIAOTONG 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