| dc.description.abstract | Communication network technology continues to evolve rapidly, especially with the arrival of 5G technology, which represents the latest generation with specifications that are significantly better than those of previous generations. One important component in the implementation of 5G is the antenna, particularly the microstrip antenna, which is known for its high gain and directivity used in various applications including satellite navigation and telecommunications. In an effort to enhance the performance of microstrip antennas for 5G applications at frequencies of 2.6 GHz and 3.4 GHz, this research proposes the use of a Machine Learning (ML) algorithm based on Decision Trees to optimize the design of rectangular patch microstrip antennas for 5G applications. Based on the comparison of parameter results between machine learning simulations with the Decision Tree algorithm, the simulation using CST Studio Suite yielded a return loss of 24,408 dB, VSWR of 1,1281, bandwidth of 3,93 MHz, and gain of 3,838 dBi at a frequency of 2.6 GHz. Meanwhile, at a frequency of 3.4 GHz, the return loss value was -31,2561 dB, VSWR of ,.05627, bandwidth of 5,894 MHz, and gain of 3,58 dBi. The predictions from Machine Learning showed differences, with the frequency of 2.6 GHz yielding a return loss of -25,6573 dB, VSWR of 1,1157, bandwidth of 4,057 MHz, and gain of 3,984 dBi. At a frequency of 3.4 GHz, the return loss value was -33,3262 dB, VSWR of 1,02513, bandwidth of 7,362 MHz, and Gain of 3,895 dBi | en_US |
