Software defect prediction method based on feature extraction and Stacking ensemble learning

A software defect prediction and feature extraction technology, applied in software testing/debugging, computer parts, character and pattern recognition, etc., to achieve good results

Active Publication Date: 2021-12-24
SOUTHWEST UNIVERSITY FOR NATIONALITIES
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the shortcomings of existing defect prediction methods, the present invention proposes a software defect prediction method based on feature extraction and Stacking integrated learning, thereby solving the aforementioned problems in the prior art

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
  • Software defect prediction method based on feature extraction and Stacking ensemble learning
  • Software defect prediction method based on feature extraction and Stacking ensemble learning
  • Software defect prediction method based on feature extraction and Stacking ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will now be further described in conjunction with the embodiments and accompanying drawings:

[0020] The invention proposes a software defect prediction method (KSSDP) based on feature extraction and stacking integrated learning. The flow chart of the KSSDP integrated prediction model is shown in figure 1 , the technical solutions adopted to solve its technical problems include the following:

[0021] 1. Feature extraction on the original dataset

[0022] The original data points in the low-dimensional feature space are mapped to the high-dimensional feature space by using the nonlinear mapping kernel function, and then the representative features are extracted and the complex defect data structure is characterized. Its core principles are as follows:

[0023] Suppose x is mapped into u by the corresponding function ρ, which is defined as follows:

[0024] u=ρ(x) (1)

[0025] The kernel function maps the data to the corresponding N-dimensional...

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 software defect prediction method based on feature extraction and Stacking ensemble learning. The method comprises the following steps: (1) carrying out the feature extraction of an original data set through kernel principal component analysis, and collecting a defect data set DS'after dimension reduction; (2) recommending an applicable sampling method for the new software defect data by using a collaborative filtering algorithm provided by the invention, and performing unbalance processing on the defect data set DS'by using the recommended sampling algorithm to obtain a defect data set DS ''after unbalance processing; (3) clustering the defect data set DS ''by using a K-Means algorithm, and removing abnormal values deviating from a mainstream category to obtain a defect data set DS'' '; (4) constructing a software defect prediction model based on Stacking ensemble learning, selecting proper classifiers for the base learner of the first layer and the meta learner of the second layer, and constructing a software defect prediction model with good performance; and (5) comparing the integrated model with the base model and the mainstream integrated model on the processed defect data set DS ''', thereby verifying the performance of the integrated prediction model provided by the invention. Research results show that the KSSDP integrated prediction model provided by the invention has better performance than a base model and a mainstream integrated model.

Description

technical field [0001] The invention relates to the field of software defects, in particular to a software defect prediction method based on feature extraction and stacking integrated learning. Background technique [0002] Open source software is one of the main trends in the future development of the software industry, and how to ensure its quality has always been a concern and crucial issue in the industry. The openness and community-based sharing of open source software makes the source code often contain many loopholes, resulting in a substantial increase in the cost of defect processing and hindering the application and promotion of open source software. Therefore, identifying and controlling the introduction factors of defects in the early stage of software development is of great practical significance for formulating effective defect prevention measures, reducing the defect introduction rate and ensuring software quality. The current mainstream defect prediction te...

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): G06K9/62G06F11/36
CPCG06F11/3672G06F18/22G06F18/23213G06F18/2135G06F18/24Y02P90/30
Inventor 崔梦天吴克奇李卫榜王琳姜玥罗洪
Owner SOUTHWEST UNIVERSITY FOR NATIONALITIES
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