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

Deep belief network-support vector machine-based software defect prediction method

A deep belief network and software defect prediction technology, applied in software testing/debugging, computing, error detection/correction, etc., can solve problems such as reduced prediction accuracy and data redundancy, and achieve improved training speed, excellent performance, and high accuracy degree of effect

Inactive Publication Date: 2018-11-06
BEIJING INSTITUTE OF TECHNOLOGYGY +1
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a kind of software defect distribution prediction method based on deep belief network algorithm support vector machine (DBN-SVM), adopts novel software defect distribution prediction model---DBN-SVM, solves the prediction of software defect distribution In , the problem of reduced prediction accuracy caused by data redundancy caused by multidimensional measurement

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
  • Deep belief network-support vector machine-based software defect prediction method
  • Deep belief network-support vector machine-based software defect prediction method
  • Deep belief network-support vector machine-based software defect prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0025] In order to predict various defects in software more accurately and improve software quality, it is very necessary to reduce the dimensionality of high-dimensional software measurement data. Manifold learning is an important method for dealing with high-dimensional data, which can discover the real structure hidden in high-dimensional software measurement data. At present, researchers mainly propose methods such as Local Linear Embedding (LLE), Neighborhood Embedding Preservation (NPE) and isometric feature mapping. The measurement data after dimensionality reduction also needs to use machine learning methods to build a predictive model to classify it.

[0026] Inspired by the success of deep learning in image processing, speech recognition, and natural language processing, this application believes that deep learning methods such as deep belief ne...

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 deep belief network-support vector machine (DBN-SVM)-based software defect prediction method. A DBN is adopted to perform dimensionality reduction on a software measurement attribute extracted from to-be-predicted software; and data after the dimensionality reduction enters an SVM for performing classification, thereby obtaining a software defect prediction result. A novel software defect distribution prediction model-DBN-SVM is adopted to solve the problem that the prediction precision is reduced due to data redundancy caused by multi-dimensional measurement in software defect distribution prediction.

Description

technical field [0001] The invention relates to a software defect prediction technology, in particular to a software defect prediction method based on a deep belief network algorithm support vector machine. Background technique [0002] The prediction of software defect distribution plays an important role in the software development process. The timely and accurate prediction of defective software modules will greatly improve the effective allocation of software testing resources. Static analysis can find defects in software before it is released without reducing the efficiency of software operation. [0003] Therefore, in recent years, many researchers have extracted the software measurement attributes of software modules to form training samples, and used machine learning technology to build software defect distribution prediction models, and applied machine learning technology to the field of static prediction of software defects. The traditional defect prediction model...

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): G06F11/36
CPCG06F11/3608
Inventor 单纯熊雯洁位华胡昌振毛俐旻
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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