Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Performance prediction of a circularly polarized graphene-dielectric resonator-based antenna for THz frequency application using machine learning algorithms

Open Access Open Access

Abstract

In this article, a graphene-dielectric resonator-based antenna is designed in the THz frequency regime. Circular polarization is achieved by feeding the cylindrical-shaped ceramic using a perturbed square-shaped aperture. Graphene loading over the alumina ceramic provides the frequency reconfigurable feature. In order to overcome the difficulty of simulating the THz antenna (i.e., very large simulation time), machine learning algorithms such as the artificial neural network (ANN) and random forest are used to effectively predict the performance of the designed antenna. The proposed antenna works effectively in between 5.0 and 5.5 THz with a 3 dB axial ratio frequency range from 5.1 to 5.35 THz. There is good correlation found between the predicted, measured, and simulated reflection coefficient and axial ratio. Due to stable radiation properties and good diversity performance within the operating frequency band, the proposed antenna can be employable for different wireless applications in the THz frequency regime.

© 2023 Optica Publishing Group

Full Article  |  PDF Article
More Like This
Efficient graphene-based circularly polarized MIMO antenna for THz applications

ChunchulaSai Vamsi, Ajay Kumar Dwivedi, Gagandeep Bharti, Vandna Rani Verma, and Anand Sharma
Appl. Opt. 61(28) 8155-8161 (2022)

Terahertz antenna with tunable filtering

Mohd Farman Ali, Zaid Jawed, Vinamra Raj, and Gaurav Varshney
Appl. Opt. 62(2) 284-290 (2023)

Large angle beam steering THz antenna using active frequency selective surface based on hybrid graphene-gold structure

Bian Wu, Yue Hu, Yu Tong Zhao, Wei Bing Lu, and Wei Zhang
Opt. Express 26(12) 15353-15361 (2018)

Data availability

Data underlying the results presented in this paper may be obtained from the authors upon reasonable request.

Cited By

Optica participates in Crossref's Cited-By Linking service. Citing articles from Optica Publishing Group journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (13)

Fig. 1.
Fig. 1. Designed layout of ceramic-based THz antenna. (a) Excitation mechanism; (b) panoramic view.
Fig. 2.
Fig. 2. $|{\rm S11|}$ variation of designed antenna in the presence/absence of cylindrical ceramic.
Fig. 3.
Fig. 3. E-field variation on cylindrical ceramic at 5.15 THz. (a) Top view; (b) side view.
Fig. 4.
Fig. 4. $|{\rm S11|}$ variation of with different changes in the square-shaped slot.
Fig. 5.
Fig. 5. Axial ratio variation of with different changes in the square-shaped slot.
Fig. 6.
Fig. 6. $|{\rm S11|}$ variation with change in chemical potential (uc) of graphene.
Fig. 7.
Fig. 7. Axial ratio variation with change in chemical potential (uc) of graphene.
Fig. 8.
Fig. 8. Comparison between actual and predicted $|{\rm S11|}$. (a) ANN; (b) random forest.
Fig. 9.
Fig. 9. Comparison between actual and predicted axial ratio. (a) ANN; (b) random forest.
Fig. 10.
Fig. 10. $|{\rm S11|}$ variation with HFSS/CST-MWS/ANN/Random Forest.
Fig. 11.
Fig. 11. Axial ratio $|{\rm S11|}$ variation with HFSS/CST-MWS/ANN/Random Forest.
Fig. 12.
Fig. 12. Gain variation of designed antenna w.r.t. frequency.
Fig. 13.
Fig. 13. 2D RHCP/LHCP radiation pattern of designed antenna in XZ plane at 5.25 THz.

Tables (4)

Tables Icon

Table 1. Optimized Dimension of Various Parameters of Structured THz Antenna

Tables Icon

Table 2. Performance Comparison of ANN and Random Forest Based on MAE, MSE, and R-Square Value for | S 11 | Prediction

Tables Icon

Table 3. Performance Comparison of ANN and Random Forest Based on MAE, MSE, and R-Square Value for Axial Ratio Prediction

Tables Icon

Table 4. Performance Assessment of Designed THz Antenna with Other Published Ceramic-Based THz Radiators

Equations (5)

Equations on this page are rendered with MathJax. Learn more.

ε A S = ε a i r [ ε r f p 2 { f + i f c l } ] .
f r , H E M 11 δ = 6.324 c 2 π D ε S i + 2 { 0.27 + 0.36 ( D H ) + 0.02 ( d H ) 2 } .
M S E = ( 1 / n ) Σ ( a c t u a l f o r e c a s t ) 2 ,
M A E = ( T r u e v a l u e s P r e d i c t e d v a l u e s ) .
R - s q u a r e = 1 ( S u m o f s q u a r e s o f r e s i d u a l s / T o t a l s u m o f s q u a r e s ) .
Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.