Code for Design and Comparative Analysis of THz Antenna through Machine Learning for 6G Connectivity
Resources and extra documentation for the manuscript "Design and Comparative Analysis of THz Antenna through Machine Learning for 6G Connectivity" published in IEEE Latin America Transactions.
Instruction for running the simulation
-
Use HFSS to design an antenna and generate the dataset.
a) Script file to create an antenna.
-
Machine Learning Algorithms Codes:
a) Decision Tree
b) Random Forest
c) XG- Boost
d) KNN
-
Requirements: Google Colab/ Python for the execution of codes
-
Graphical Abstract for proper understanding
The rise of sixth-generation (6G) technology has become increasingly necessary to meet the growing demand for high-speed internet and the continuous advancements in technology. The development of an optimal antenna design is crucial to attain the required performance and capabilities. Traditional electromagnetic modeling approaches for antenna design are, however, time-consuming and computationally intensive requiring long simulation time and high-end computing systems. Therefore, Machine Learning (ML) technology can be utilized to deal with these limitations in the context of Terahertz (THz) antenna design, which has not been done before. The main objective of this work is to develop an antenna that operates in the THz Band, which is the essential 6G band for the future infrastructure revolution, and to predict and optimize the antenna's return loss using ML models like K-Nearest Neighbour (KNN), Extreme Gradient Boosting (XG-Boost), Decision Tree, and Random Forest and Mean Squared Error (MSE) of 3.816. The findings show that all of these models perform accurately, particularly Random Forest having the highest accuracy of 82% in predicting the return loss. ML offers novel possibilities for the development of optimized and efficient 6G antennas for high-speed communication.