Professor Thammer Mohammed Jamil in the Department of Communications Engineering published two research papers at the IEEE conference DeSE2023

 The first entitled:  Performance Evaluation of SISO-OFDM Channel Equalization Utilizing Deep Learning

 :The research was published in
16th International Conference on Developments in eSystems Engineering (DeSE), Istanbul, Turkiye, 2023
The aim of the research involves the use of the channel formula based on deep learning The primary objective of this research is to assess the performance of the channel equivalent based on deep learning in order to address the shortcomings of the ZF and MMSE equations in terms of modification order and the number of pilots (CP).
Simulation results show that the DL-dependent channel equivalent can outperform the MMSE equivalent when increasing the number of pilots, with or without CP, for both low-frequency and high-frequency selective channel models, respectively. The results also show how deep learning of CNN structures is used in the SISO OFDM system to enhance channel equation.
Finally, numerical evidence showed that deep learning significantly reduced channel equivalent errors compared to traditional methods.

:The second has entitled 

Efficient FBMC-OQAM Channel Equalization Through Pruned DFT

and research was published in
16th International Conference on Developments in eSystems Engineering (DeSE), Istanbul, Turkiye, 2023
This work aims to leverage the unique characteristics of FBMC-OQAM and the power of manicured DFT technology - an effective algorithm for DFT account - to improve system performance. Next, enhance the equation performance of the proposed scheme using many sophisticated equation algorithms.
The main findings include:
First: Improve the FBMC-OQAM system by integrating Pruned-DFT technology into its structure.
Second, the range of proposed equation techniques outperforms the traditional single-tab tie tool in highly variable channels over time and in the High Signal-to-Noise Ratio (SNR) system.