ANN for Fast and Accurate Determination of Resonant Frequency and Quality Factor for CSSRR

Artificial Neural Network (ANN) has been employed for determination of resonant frequency and quality factor for complementary split ring resonator (CSSRR). It has been observed that as the number of training samples increases, the testing error decreases. The error in testing also decreases with the increase in the number of neurons in the hidden layer of the three layer multi-layer perceptron (MLP) network. The computational efficiency for this approach is very high in comparison to electromagnetic (EM) techniques, which takes more time. Usually it takes less than a second for training and testing the 60 samples using ANN whereas the EM simulator takes few hours to generate a single data, which is a huge gain in terms of computational efficiency. The accuracy of this approach is also very close to the EM simulation technique within 1%-2% errors.