1 Ocak 2022 Konferans bildirisi Açık Erişim

Nayir, Hasan; Karakoca, Erhan; Gorcin, Ali; Qaraqe, Khalid

Citation Style Language JSON

{
  "DOI": "10.1109/VTC2022-Fall57202.2022.10013010", 
  "abstract": "Frequency scarcity implies the utilization of higher frequencies for wireless communications; however, spreading loss becomes a dominating issue as the frequency increases to the level of and beyond millimeter waves. To this end, massive multiple-input multiple-output structures introduce mitigation alternatives. However, to make these solutions possible, the channel estimation approach strives to be modified: since Rayleigh distance is very short for conventional systems, the only far-field channel is examined in that context. On the other hand, the implementation of massive antenna arrays in high frequencies increases Rayleigh distance; thus, both near-field and far-field analyses become necessary. Instead of a dual estimation process, it would be effective and efficient to develop hybrid-field channel estimation techniques. Therefore, in this study, a new channel estimation method which is based on convolutional autoencoder (CAE) and orthogonal matching pursuit (OMP) approach, is proposed for hybrid channel estimation. The results indicate that the proposed OMP-CAE method has much better error performance when compared to the conventional OMP algorithm, especially at low signal-to-noise ratio regimes.", 
  "author": [
    {
      "family": "Nayir", 
      "given": " Hasan"
    }, 
    {
      "family": "Karakoca", 
      "given": " Erhan"
    }, 
    {
      "family": "Gorcin", 
      "given": " Ali"
    }, 
    {
      "family": "Qaraqe", 
      "given": " Khalid"
    }
  ], 
  "id": "252745", 
  "issued": {
    "date-parts": [
      [
        2022, 
        1, 
        1
      ]
    ]
  }, 
  "title": "Hybrid-Field Channel Estimation for Massive MIMO Systems based on OMP Cascaded Convolutional Autoencoder", 
  "type": "paper-conference"
}