Related Experiment Video
Updated: Nov 7, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.1K
Radiation Pattern Prediction for Metasurfaces: A Neural Network-Based Approach
Hamidreza Taghvaee1, Akshay Jain1, Xavier Timoneda1
1NaNoNetworking Center in Catalonia (N3Cat), Universitat Politècnica de Catalunya, 08034 Barcelona, Spain.
Sensors (Basel, Switzerland)
|April 30, 2021
Summary
Researchers developed a neural network approach for reconfigurable intelligent surfaces (RIS) in 6G networks. This method accurately predicts radiation patterns, matching full-wave simulations at analytical model speeds.
Area of Science:
- Wireless communication
- Metamaterials
- Artificial intelligence
Background:
- 5G network standardization is nearing completion, with research focusing on 6G technologies.
- Reconfigurable intelligent surfaces (RIS) are a key technology for 6G, offering channel control.
- Accurate characterization of RIS metasurface response is crucial for their deployment.
Purpose of the Study:
- To propose a novel neural network-based approach for fast and accurate characterization of RIS metasurface response.
- To overcome the limitations of analytical models (inaccuracy) and full-wave simulations (computational complexity).
Main Methods:
- Development and application of a neural network model.
- Analysis of multiple operational scenarios for RIS.
- Prediction of parameters governing the reflected wave radiation pattern.
Main Results:
- The neural network approach achieved prediction accuracy comparable to full-wave simulations (98.8-99.8%).
- The method demonstrated computational efficiency, matching the speed of analytical models.
- The model successfully learned and predicted the metasurface response across various scenarios.
Conclusions:
- The proposed neural network methodology offers a fast and accurate solution for RIS characterization.
- This approach is vital for the design, fault tolerance, and maintenance of RIS in future 6G networks.
- The study highlights the potential of AI in optimizing wireless communication systems.
