2022
DOI: 10.1109/tap.2022.3140891
|View full text |Cite
|
Sign up to set email alerts
|

Intelligent Beamforming via Physics-Inspired Neural Networks on Programmable Metasurface

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
16
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 27 publications
(16 citation statements)
references
References 27 publications
0
16
0
Order By: Relevance
“…Reproduced with permission. [265] Copyright 2022, IEEE. e) Transmissive programmable metasurface for high-efficiency OAM generation.…”
Section: Reflective Metasurfacesmentioning
confidence: 99%
See 2 more Smart Citations
“…Reproduced with permission. [265] Copyright 2022, IEEE. e) Transmissive programmable metasurface for high-efficiency OAM generation.…”
Section: Reflective Metasurfacesmentioning
confidence: 99%
“…Furthermore, an intelligent beamforming scheme based on a physics-inspired neural network (PINN) and deep neural network (DNN) has been proposed, which can predict the code for desired patterns with more than 98.4% efficiency (Figure 7d). [265]…”
Section: Radiative Metasurfacesmentioning
confidence: 99%
See 1 more Smart Citation
“…Unlike traditional communication systems, which demand many computing resources and result in unacceptable latency, deep-learning-based approaches take advantage of natural channel sparsity to efficiently precode and modulate data into several streams and send it to the distributed system [ 191 , 201 , 202 , 203 ]. Moreover, a physics-inspired neural network is used in [ 204 ] to design a reconfigurable coded metasurface for dynamic beam steering. Such type of ML-based reconfigurable antennas possess huge potential for Industry 4.0 and beyond applications, where the smart antennas system is required to reconfigure its radiation pattern in real-time based on blockage, jamming, and NLOS scenarios.…”
Section: Research Opportunities and Future Directionsmentioning
confidence: 99%
“…In designs of antennas [5], arrays [6]- [8], and artificial electromagnetic media (e.g., metamaterials, metasurfaces, electromagnetic bandgap structures, and frequency selective surfaces [9]), ML offers a wealth of techniques to discover optimum structures and geometric patterns from high-dimensional stochastic data. ML tools are expected to become the cornerstone of antenna designs in the near future.…”
Section: Introductionmentioning
confidence: 99%