查看文章

Intelligent reflective surfaces (IRS) are used in wireless communication to direct the electromagnetic wave towards the user. This technique can help to reduce noise in the communication system and improve the user experience. However, the channel estimation technique is very hard due to the number of elements that makes the mathematical model complex. Machine learning approaches are very useful tools to make channel estimation for IRS-based system. In this study, we compare the performance of long short-term memory (LSTM) and BiLSTM for IRS-based wireless communication system. The simulations results show that BiLSTM has better bit error rate performance as compared to LSTM technique.