Enhanced Antenna Design Accuracy Using a Hybrid Deep Learning Model

The increasing growth of the Internet of Things (IoT), coupled with the advancements in 5G technologies, presents significant challenges and opportunities in the realm of antenna design for wireless communications. This work offers a novel hybrid deep learning model that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to enhance microstrip antenna designs, with a specific focus on addressing space and bandwidth constraints significant for IoT and 5G applications. The obtained results show that the proposed model significantly improves predicting accuracy, demonstrated by decreased Root Mean Square Error (RMSE) values and R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> values, surpassing conventional regression models. This methodology therefore signifies a substantial advancement in integrating machine learning techniques into antenna design, offering a significant opportunity to enhance wireless communication infrastructure in alignment with evolving technological demands.