@article{M3DD7083A,
title = "Channel Estimation for OFDM Systems Using an Improved SRGAN Architecture",
journal = "The Journal of Korean Institute of Communications and Information Sciences",
year = "2025",
issn = "1226-4717",
doi = "10.7840/kics.2025.50.1.78",
author = "Eunwoo Jo, Nayoung Lee, Hosung Park",
keywords = "Channel estimation, Deep learning, Neural network, SRGAN",
abstract = "It is important to accurately estimate channel values in orthogonal frequency division multiplexing systems.
In the channel estimation (CE), the channel values in the positions of pilot signals can be regarded as low-resolution images, therefore deep learning (DL)-based super-resolution (SR) algorithms can be applied to estimate all the channel values. The existing DL-based CE algorithm with the SR generative adversarial network (SRGAN) achieves good performance and we further improved the neural network architecture, enhancing the CE accuracy with lower complexity."
}