Patent · US Active

Method of parameter estimation for a multi-input multi-output system

US11489560B2 · kind B2 · utility

0Cited by
0References
36Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 11, 2020
Grant dateNov 1, 2022
Priority date
Expiry dateMay 15, 2041

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04W76/10
  • WIPO fieldTelecommunications
  • WIPO sectorElectrical engineering

Abstract

A method of parameter estimation for a multi-input multi-output system based on deep learning is executed. The method includes creating a connection between the base station and a user device entering a coverage of the base station, transmitting real-time channel information from the user device to the base station through the connection, optimizing a parameter for the user device based on the real-time channel information through a deep learning algorithm, transmitting the optimized parameter to the user device, and applying the optimized parameter in a signal detection for the multi-input multi-output system at the user device. The real-time channel information is a channel status of the user device upon the creation of the connection between the base station and the user device. Another method of parameter estimation for a multi-input multi-output system having a base station and a plurality of user devices is also disclosed.

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