Key Generation of Biomedical Implanted Antennas Through Artificial Neural Networks

Abstract

This paper presents an accurate and efficient optimization-based approach for modelling and sizing implanted antennas automatically. The proposed method employs the long short-term memory (LSTM) artificial neural network (ANN) for predicting the design specifications in not only one frequency but also in a large frequency band. The entire process is performed in an automated environment that is the combination of electronic design automation (EDA) tools and the numerical analyzer. Based on this intelligent method, the difficulty of designing electromagnetic (EM)-based antennas is solved to the most degrees and the design parameters can be achieved in the easiest way. To validate the efficiency of the presented ANN, two implanted antennas are designed; they and realized on a grounded biocompatible substrate and covered by bone, muscle, fat, and skin tissues, respectively. These implanted antennas are optimized in terms of input scattering parameter, E-plane and H-plane radiation pattern (RP) specifications and the suitable design parameters are provided automatically. The modelled implanted antennas are appropriate to be used at the industrial, scientific, and medical (ISM) frequency band between 2.4 GHz and 2.5 GHz.