Reliability analysis based on deep learning for fault big data on bug tracking system
Yoshinobu Tamura, Shigeru Yamada · 2016
Many open source software are useful for quick delivery, cost reduction, and standardization in the system development. The bug tracking systems are managed by many open source projects for quality management of open source software. 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 reliability analysis based on the deep learning. In particular, we analyze the reliability growth/regression trends based on the fault big data recorded on bug tracking system. Also, this paper shows several numerical examples of open source software reliability assessment in the actual software projects. 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.