Published on Sun Apr 26 2020

Pilot Interval Reduction by Deep Learning Based Detectors in Uplink NOMA

Ahmet Emir, Ferdi Kara, Hakan Kaya

Non-Orthogonal Multiple Access has higher spectral efficiency than orthogonal multiple access (OMA) techniques. In uplink communication systems, pilot signals sent from each user in different time intervals have reduced the spectral efficiency of NOMA.

0
0
0
Abstract

Non-Orthogonal Multiple Access (NOMA) has higher spectral efficiency than orthogonal multiple access (OMA) techniques. In uplink communication systems that the channel is not known at the receiver, pilot signals sent from each user in different time intervals have reduced the spectral efficiency of NOMA. In this study, in the uplink communication system, DL-deep learning based detectors which are known to respond to the pilot signals sent from the users at the base station have been researched. It is aimed to maintain the spectral efficiency of NOMA by sending a single pilot from users, thus reducing the time interval in the DL detectors.

Tue Jan 12 2021
Artificial Intelligence
CAnet: Uplink-aided Downlink Channel Acquisition in FDD Massive MIMO using Deep Learning
0
0
0
Sun Jun 21 2020
Machine Learning
Pruning the Pilots: Deep Learning-Based Pilot Design and Channel Estimation for MIMO-OFDM Systems
The overhead due to pilot transmission for channel estimation can be prohibitive in wideband massive MIMO systems. We propose a neural network (NN)-based joint pilot design and downlink channel estimation scheme.
0
0
0
Mon Sep 06 2021
Artificial Intelligence
Learning to Perform Downlink Channel Estimation in Massive MIMO Systems
We propose two novel estimation methods. The first method is model-aided and utilizes asymptotic arguments. The second one is a deep-learning-based approach that uses a neural network. We compare the proposed methods against other benchmarks.
0
0
0
Thu Feb 18 2021
Machine Learning
DeepMuD: Multi-user Detection for Uplink Grant-Free NOMA IoT Networks via Deep Learning
We propose a deep learning-aided multi-user detection (DeepMuD) in uplink non-orthogonal multiple access (NOMA) The proposed DeepMuD improves the error performance of the uplink NOMA significantly.
0
0
0
Sat Jul 27 2019
Machine Learning
Deep Learning for CSI Feedback Based on Superimposed Coding
Massive multiple- input multiple-output (MIMO) with frequency division duplex (FDD) mode is a promising approach to increasing system capacity and link robustness for 5G wireless cellular systems. The premise of these advantages is the accurate downlink channel state information (CSI) that is fed back from user equipment.
0
0
0
Thu Jul 23 2020
Machine Learning
Deep Learning Based Equalizer for MIMO-OFDM Systems with Insufficient Cyclic Prefix
Deep learning-based equalizer is proposed for approximating the maximum likelihood detection. Employing the proposed equalizer, an iterative receiver is also constructed.
0
0
0