An Improved Scheme for Deep Learning Channel Estimation

Han T., Zhang Y., Lv X., TEMİZ M.

4th International Symposium on Computer Technology and Information Science, ISCTIS 2024, Xian, China, 12 - 14 July 2024, pp.13-17, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/isctis63324.2024.10699086
  • City: Xian
  • Country: China
  • Page Numbers: pp.13-17
  • Keywords: Channel estimation, deep learning, DFT, DNN, OFDM
  • Middle East Technical University Affiliated: Yes

Abstract

For the channel estimation problem in the Orthogonal Frequency Division Multiplexing (OFDM) system, we propose an optimization scheme based on the existing deep neural network (DNN) channel estimation. In this scheme, the Discrete Fourier Transform (DFT) is used to process the input data to eliminate the influence of noise in the Least Squares (LS) method, so as to improve the learning ability of the DNN model. Through simulation experiments, it can be seen that the proposed scheme can effectively improve the performance of DNN channel estimation.