Skip to main content
Signal Processing

You are not logged in. Your edit will be placed in a queue until it is peer reviewed.

We welcome edits that make the post easier to understand and more valuable for readers. Because community members review edits, please try to make the post substantially better than how you found it, for example, by fixing grammar or adding additional resources and hyperlinks.

6
  • $\begingroup$ Thank you for your reply. Sorry for the long post. Is my understanding below correct? Assuming downlink communication, there are 612 subcarriers and 14 time slots are transmitted. Assume that one resource block is allocated to each user. The user who receives the signal performs a Fourier transform on the allocated 12 frequencies. As a result, each user receives a signal of 12 subcarriers x 14 time slots. After that, channel estimation and equalization are performed. $\endgroup$ Commented Oct 15, 2023 at 21:54
  • $\begingroup$ However, in the research, it was as if one user were receiving the received data of 612 subcarriers x 14 time slots. Then, the 612 x 14 data was input to machine learning (CNN) to perform channel estimation. Is it possible to receive 612 subcarriers in a real scenario? $\endgroup$ Commented Oct 15, 2023 at 21:55
  • $\begingroup$ No, that understanding is not correct. The FFT will be over the full bandwidth, usually, exactly because otherwise it's hard to get channel state information. Of course it is possible to receive all subcarriers at once. Have you looked at at 4G/5G time/frequency frame diagram? There's phases where there's synchronization and pilot symbols everywhere, and of course in a scenario where one user gets all the availalable spectrum, they will have to receive all of it. $\endgroup$ Commented Oct 15, 2023 at 22:01
  • $\begingroup$ You might really want to take a step back and look at OFDM theory. An OFDM receiver will not do a sub-band FFT, that makes no sense, it loses the ability to time- and frequency synchronize. I think you're already thinking about optimizing a system with machine learning which you haven't fully understood the very basis of! $\endgroup$ Commented Oct 15, 2023 at 22:03
  • $\begingroup$ Thank you very much! I will study this ieeexplore.ieee.org/ielx7/6287639/8948470/… $\endgroup$ Commented Oct 15, 2023 at 23:43