Implementing Machine Learning for Design and Evaluation of Antenna Parameters

Predictions in the field of machine learning (ML), also known as artificial intelligence (AI), are used for forecasting a model that has been tested on an ancient database. The system then produces probable values for every entry based on the incoming information's unidentified variables. Nowadays, ML is receiving a lot of attention in discovering ideal solutions in a range of fields due to the development and diversity of data available, improved computing, and accessible data storage. The contemporary research focus on ML approaches, which are expected to play a crucial role in modern methods. This study describes and explores the use of various ML techniques like linear regression, decision tree, and random forest mechanism for designing an eyebolt-shaped antenna and evaluating its parameters. A thorough analysis of ML's application in antenna design is offered. It was predicted that ML might expedite the antenna design procedure while keeping high accuracy standards, minimizing error, and saving time, as well as perhaps predicting antenna behavior, improving computation time, and minimizing the number of simulations required. This work also includes the results of different types of ML algorithms in antenna design.