Predicting Beam Switching Directions in Ultra Wideband Spiral Antennas Using Machine Learning Algorithms

This paper presents the application of machine learning techniques to predict beam switching directions based on slot positions and the turn number of the ring in wideband spiral antennas operating at a frequency of 2.6 GHz for 5 G communication. A dataset of 200 samples was generated through simulations on CST Studio, varying the slot angle positions and the turn number of the ring while keeping other parameters constant. This dataset was used to evaluate the performance of three machine learning algorithms: decision trees, random forests, and K-nearest neighbors (KNN). The results indicate that decision tree and random forest models were the most effective in accurately predicting beam-switching positions.