| ITI əməkdaşlarının elmi işləri - məqalə |
| Biblioqrafik təsvir | |
| Bayramova , T.A. Predicting the reliability of software systems using recurrent neural networks: LSTM model / T.A. Bayramova // Problems of Information Technology. - 2024. - N: 1, vol.15. - P. 52-61. | |
| Annotasiya | |
| The dynamics and complexity of processes occurring in complex software systems, as well as the emergence of new types of malicious threats, further complicate the issues of ensuring software reliability. Despite the development of hundreds of models for increasing the reliability of software systems, this issue still remains relevant. Research shows that the use of neural networks in predicting the reliability of software systems allows one to obtain more accurate results. In this paper, to predict reliability, we used a neural network model with long short-term memory, which is a type of recurrent neural networks. Seven real-world software crash datasets were used to test the models performance. The experiments were carried out in Python. Both parametric and nonparametric models were taken for comparison. The experimental results showed the practical significance of using the proposed model in predicting the reliability of software systems. | |
| Elektron variant | |
| Elektron variant |
________
© ict.az http://ict.az/az