US 12,231,269 B2
Active user detection and channel estimation method and device, using deep neural network
Byonghyo Shim, Seoul (KR); and Yongjun Ahn, Seoul (KR)
Assigned to Seoul National University R&DB Foundation, Seoul (KR)
Appl. No. 18/038,357
Filed by SEOUL NATIONAL UNIVERSITY R&DB FOUNDATION, Seoul (KR)
PCT Filed Nov. 1, 2021, PCT No. PCT/KR2021/015558
§ 371(c)(1), (2) Date May 23, 2023,
PCT Pub. No. WO2022/114561, PCT Pub. Date Jun. 2, 2022.
Claims priority of application No. 10-2020-0162482 (KR), filed on Nov. 27, 2020.
Prior Publication US 2023/0412429 A1, Dec. 21, 2023
Int. Cl. H04L 25/02 (2006.01)
CPC H04L 25/0254 (2013.01) 8 Claims
OG exemplary drawing
 
1. An active terminal detection and channel estimation method of a base station in a wireless communication system based on grant-free uplink transmission, the method comprising:
receiving superimposed signals (custom character) from k active terminals;
calculating, using a first artificial neural network and using the received signals (custom character) as input, an estimated probability (Ω) that each of all terminals in a cell of the base station is an active terminal; and
estimating channels of the active terminals using a second artificial neural network with the received signals (custom character) and an active terminal detection result value as input,
wherein the first artificial neural network and the second artificial neural network are each an artificial neural network based on long short-term memory (LSTM) networks, and
wherein the first artificial neural network is established by learning a direct mapping according to Equation 5, and the second artificial neural network is established by learning a direct mapping according to Equation 8:
Ω=gand(custom character:θA)  [Equation 5]
wherein θA is a parameter of the first artificial neural network used for the active user detection,
ĥΩ=gce(custom character,Ω;θC)  [Equation 8]
wherein θC is a parameter of the second artificial neural network used for the channel estimations.