Method of parameter estimation for a multi-input multi-output system
US11489560B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 11, 2020 |
| Grant date | Nov 1, 2022 |
| Priority date | — |
| Expiry date | May 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.