Metallic Pattern Prediction For Surface Wave Antennas Using Bidirectional Gated Recurrent Unit Neural Network
- Resource Type
- Conference
- Authors
- Yang, Jiashu; Tong, Kin-Fai
- Source
- 2021 IEEE-APS Topical Conference on Antennas and Propagation in Wireless Communications (APWC) Antennas and Propagation in Wireless Communications (APWC), 2021 IEEE-APS Topical Conference on. :082-086 Aug, 2021
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Photonics and Electrooptics
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Wireless communication
Training
Surface waves
Neural networks
Predictive models
Logic gates
Data models
Surface wave antennas
holographic antennas
electric field (E-field) prediction
recurrent neural network (RNN)
bidirectional gated recurrent unit (Bi-GRU)
- Language
This work presents a surface wave antenna metallic pattern prediction from electric field in near-field by applying Bidirectional Gated Recurrent Unit neural network prediction model. The metallic pattern of the proposed antenna has been predicted by using Bi-GRU neural network model with prediction accuracy 100% at 34.5GHz. Different uniform mark-space-ratios (MSR) of the metallic pattern do not affect the metallic pattern prediction accuracy.