Unlock instant, AI-driven research and patent intelligence for your innovation.

Improved feature filtering method and device based on correlation feature selection

A technology of feature selection and filtering method, applied in the fields of instruments, digital data processing, character and pattern recognition, etc., can solve the problems of poor data quality and low preprocessing efficiency, and achieve the effect of improving data quality

Inactive Publication Date: 2019-08-16
BEIHANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an improved feature filtering method based on correlation feature selection. The present invention aims to solve the problems of poor data quality and low preprocessing efficiency in software defect prediction, and can delete redundant features and not Improving the performance of software defect prediction models while using relevant features

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
  • Improved feature filtering method and device based on correlation feature selection
  • Improved feature filtering method and device based on correlation feature selection
  • Improved feature filtering method and device based on correlation feature selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0066] The invention is an improved feature filtering method based on correlation feature selection. The specific steps of the method are as follows: (the basic feature selection method of the present invention refers to a method combining the CFS method and Greedy Forward Stepwise Search (GS for short)).

[0067] refer to figure 1 mentioned, including:

[0068] S11. Converting the numerical type of the class label in the N data ...

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 improved feature filtering method and device based on correlation feature selection. The method aims at a classification task in software defect prediction, calculates the similarity between the proportions of the features selected by using the CFS method and the proportions of the features in the original data set; the first K features are selected through sorting; theproblem that a filtering method in feature selection is high in efficiency but a prediction model is poor in performance is solved, data preprocessing guidance on a software prediction model is achieved, and the requirements for preprocessing data and improving the data quality under the condition that data is sufficient and irrelevant features or redundant features exist in the data are met; andon the other hand, the method is simple, easy to implement and short in running time, and the constructed software defect prediction model is high in accuracy.

Description

technical field [0001] The invention relates to the technical field of software defect prediction, in particular to an improved feature filtering method and device based on correlation feature selection. Background technique [0002] In recent years, software defect prediction has become an active field in software engineering. It is possible to predict the defects of newly developed software or tested software through historical knowledge of previous versions of the software or related defect knowledge of other software, and it is possible to understand each module of the software in advance (or class, or subsystem, or function) quality status. In this way, certain guidance can be provided for software testers, managers, reliability designers and other relevant personnel, so that they can reasonably allocate relevant manpower and resources, save development costs, and improve software development efficiency. [0003] The most important part of defect prediction is data, an...

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
CPCG06F11/3608G06F18/2113G06F18/22
Inventor 崔灿刘斌李国旗
Owner BEIHANG UNIV