Deep Learning Approach for Reliability Assessment of Cloud Software  
Author Yoshinobu Tamura

 
Co-Author(s) Shigeru Yamada

 
Abstract Many open source software are used for quick delivery, cost reduction, and standardization. The bug tracking systems are managed by many open source projects. Then, many data sets are recorded on the bug tracking systems by many users and project members. In this paper, we propose a method of open source software reliability assessment based on the deep learning. In particular, the cloud software depend on several browser software of client side. Therefore, we identify the failures of operating system, which are caused by software faults, by using the deep learning. Also, several numerical examples of open source software reliability assessment in the actual software projects are shown in this paper. Moreover, we compare the method based on the deep learning with that based on neural network by using the fault data sets of actual software projects.

 
Keywords Cloud software, Big Data, Reliability, Deep learning
   
    Article #:  22138
 
Proceedings of the 22nd ISSAT International Conference on Reliability and Quality in Design
August 4-6, 2016 - Los Angeles, California, U.S.A.