Patent · US Active

Learning approximate estimation networks for communication channel state information

US11334807B1 · kind B1 · utility

217Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 25, 2018
Grant dateMay 17, 2022
Priority date
Expiry dateMar 18, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04B17/3912
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training and deploying machine-learning estimation networks in a communications system. One of the methods includes: processing first information with ground truth information to generate a first RF signal by altering the first information by channel impairment having at least one channel effect, using a receiver to process the first RF signal to generate second information, training a machine-learning estimation network based on a network architecture, the second information, and the ground truth information, receiving by the receiver a second RF signal transmitted through a communication channel including the at least one channel effect, inferring by the trained estimation network the receiver to estimate an offset of the second RF signal caused by the at least one channel effect, and correcting the offset of the RF signal with the estimated offset to obtain a recovered RF signal.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.