Study on software defects prediction model based on machine learning

Wenqing Ren

doi:10.1117/12.2670396

1 June 2023 Study on software defects prediction model based on machine learning

Wenqing Ren

Proceedings Volume 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022); 126250P (2023) https://doi.org/10.1117/12.2670396
Event: International Conference on Mathematics, Modeling and Computer Science (MMCS2022),, 2022, Wuhan, China

Abstract

In the rapid development of network science and technology, the software, as the basic part of the network system operation, the practical application quality directly determines the realization of the function, so the users put forward higher requirements for the software quality. According to the application situation of network system software in recent years, software defects are the main factor affecting the application quality, and the relevant detection technology is the only way before the formal promotion of software. Therefore, researchers have put forward a defect prediction scheme based on the software code, which can not only reduce the cost, but also improve the practical efficiency. This paper focuses on the understanding of the machine learning algorithm and constructing automatic and comprehensive learning models according to the software defect prediction technology, thus discovering the defects in the software. The final experimental results prove that different algorithms have different advantages in different evaluation indicators. By using these advantages and the stacking integrated learning methods in machine learning, building a prediction model with combined machine learning algorithms as the core can find defects more accurately and perfectly.

Citation Download Citation

Wenqing Ren "Study on software defects prediction model based on machine learning", Proc. SPIE 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022), 126250P (1 June 2023); https://doi.org/10.1117/12.2670396

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available