 |
International Society of Science and Applied Technologies |
| A Study on the Prediction of Software Faults Using RNN and LSTM | ||||
| Author | Kwang Yoon Song
|
|||
| Co-Author(s) | Youn Su Kim; In Hong Chang
|
|||
| Abstract | Software reliability has been continuously researched to solve the problem because software that plays a big role in various fields can cause big problems if it faults due to small or large problems such as coding or operation errors. Many software reliability models developed are based on NHPP, but since it is developed based on assumptions, it does not show good results for models that do not include assumptions. Therefore, in this study, we proposed a software reliability model using deep learning that does not rely on assumptions but on data. We utilized RNN and LSTM to solve the sequential nature of software reliability model using deep learning. We showed the superiority of software reliability models using deep learning by utilizing four measures using NTDS data. In particular, the software reliability model using LSTM showed excellent results.
|
|||
| Keywords | Software Reliability, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) | |||
| Article #: RQD2024-269 | ||||
Proceedings of 29th ISSAT International Conference on Reliability & Quality in Design |