Research on software defect prediction system based on deep learning

Wei Wu; Chuyan Feng; Huimin Ren; Xiangyu Han; Xin Tong

doi:10.1117/12.2660800

16 December 2022 Research on software defect prediction system based on deep learning

Wei Wu, Chuyan Feng, Huimin Ren, Xiangyu Han, Xin Tong

Proceedings Volume 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022); 125005W (2022) https://doi.org/10.1117/12.2660800
Event: 5th International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 2022, Chongqing, China

Abstract

Aiming at the high importance of software quality work in aerospace field and the requirement of high reliability of software products, we study the software defect prediction system based on deep learning; introduce the process of prediction model generation in the system from three aspects: metric selection, prediction model and evaluation indicator. The main points of design of the software defect prediction system based on TensorFlow Serving and Docker container technology are introduced from three aspects: system requirements, architecture design and model deployment. The software prediction system can be used to discover potential defects in software, improve software development and testing efficiency, and enhance the quality of aerospace software products.

Citation Download Citation

Wei Wu, Chuyan Feng, Huimin Ren, Xiangyu Han, and Xin Tong "Research on software defect prediction system based on deep learning", Proc. SPIE 12500, Fifth International Conference on Mechatronics and Computer Technology Engineering (MCTE 2022), 125005W (16 December 2022); https://doi.org/10.1117/12.2660800

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