Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Eigenbased Multi-Antenna Spectrum Sensing: Experimental Validation on a Software-Defined Radio Testbed.

Sensors (Basel, Switzerland)·2026

Same author

Quadratic Forms in Random Matrices with Applications in Spectrum Sensing.

Entropy (Basel, Switzerland)·2025

Same author

Performance Analysis of Uplink Code Division Multiplexing for LEO Satellite Constellations Under Nonlinear Power Amplifiers.

Sensors (Basel, Switzerland)·2024

Same author

Software-Defined Radio Implementation of a LoRa Transceiver.

Sensors (Basel, Switzerland)·2024

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Aug 13, 2025

Experimental Investigation of the Hierarchical Control in DC Microgrids Using a Real-time Simulator

Experimental Investigation of the Hierarchical Control in DC Microgrids Using a Real-time Simulator

Published on: February 14, 2025

Implementation of Deep-Learning-Based CSI Feedback Reporting on 5G NR-Compliant Link-Level Simulator.

Daniel Gaetano Riviello¹, Riccardo Tuninato², Elisa Zimaglia³

¹Department of Electrical, Electronic, and Information Engineering, University of Bologna, 40136 Bologna, Italy.

Sensors (Basel, Switzerland)

|January 21, 2023

Summary

Deep learning, using NR-CsiNet, enhances channel state information feedback in 5G networks. This approach improves block error rate and throughput for 5G data channels.

Keywords:

5G CSI reporting New Radio convolutional neural network deep learning

More Related Videos

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

Related Experiment Videos

Last Updated: Aug 13, 2025

Experimental Investigation of the Hierarchical Control in DC Microgrids Using a Real-time Simulator

Experimental Investigation of the Hierarchical Control in DC Microgrids Using a Real-time Simulator

Published on: February 14, 2025

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Tactile Vibrating Toolkit and Driving Simulation Platform for Driving-Related Research

Published on: December 18, 2020

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Integration of 5G Experimentation Infrastructures into a Multi-Site NFV Ecosystem

Published on: February 3, 2021

Area of Science:

Telecommunications Engineering
Machine Learning Applications
Wireless Communication Systems

Background:

Deep learning offers solutions for complex problems lacking rigorous mathematical models.
Accurate channel state information (CSI) feedback is vital for optimizing Multiple-Input Multiple-Output (MIMO) systems in 5G networks, especially in Frequency Division Duplexing (FDD).

Purpose of the Study:

To develop and evaluate a deep learning framework (NR-CsiNet) for efficient CSI feedback reporting in 5G FDD networks.
To compress and reconstruct the channel matrix using a convolutional neural network compliant with 5G New Radio standards.

Main Methods:

Designed NR-CsiNet, a 5G New Radio convolutional neural network framework.
Utilized a 5G New Radio compliant simulator with a 3GPP 3-D channel model.
Incorporated realistic 5G scenarios, including multi-antenna schemes and noisy channel estimation.

Main Results:

The NR-CsiNet framework demonstrated promising performance in simulations.
Evaluated performance against current feedback reporting schemes.
Observed improvements in block error rate and throughput for the 5G data channel.

Conclusions:

Deep learning, specifically NR-CsiNet, presents an effective approach for CSI feedback reporting in 5G FDD systems.
The framework's compliance with 5G standards and realistic scenario testing validate its potential.
This method offers significant advantages for enhancing 5G data channel performance.