S. Sinan Gultekin

A comparative study of neural networks for input resistance computation of electrically thin and thick rectangular microstrip antennas

Multilayered-perceptron-based neural models for calculating the input resistance of electrically thin and thick rectangular microstrip antennas are presented. Eleven learning algorithms—Levenberg-Marquardt, conjugate gradient of Fletcher-Reeves, Bayesian regularization, Broyden-Fletcher-Goldfarb-Shanno, conjugate gradient of Polak-Ribiére, conjugate gradient of Powell-Beale, scaled conjugate gradient, one-step secant, resilient backpropagation, backpropagation with momentum, and backpropagation with adaptive learning rate—are used to train the multilayered perceptrons. The input resistance results obtained with the use of neural models are in very good agreement with the experimental results available in the literature. When the performances of neural models are compared with each other, the best result is obtained from the multilayered perceptrons trained by the Levenberg-Marquardt algorithm.

Modeling congestion of vessel on rectangular microstrip antenna and evaluating electromagnetic signals

According to researches, the most common diseases of unexpected death causes are related to heart. The one of basic reasons of heart diseases is congestion of heart vessel. To detect these failures, various solutions are produced and these solutions are continued. With the proposed study, the congestion of heart vessel related to heart disease is modelled on rectangular microstrip patch antenna and evaluations of electromagnetic field values are tried in situations while there is congestion and not congestion. In modelling, permittivity values of heart vessel and fat tissues are used, by selecting 2.45 GHz as operating frequency and FR-4 as substrate, simulations are realized in High Frequency Structural Simulator(HFSS). From obtained results, it has been shown that the congestion of heart vessel can be detected with electromagnetic data.