Determination of Electrical Values of Tissue Equivalent Liquids Prepared for 900 MHz Frequency by Using Soft Computing Methods

In this paper, an application of artificial neural network (ANN) for the prediction of electrical parameters in a human brain equivalent liquid (BEL), resulting from mixing different chemicals is presented. In the first phase of the study, different chemicals are used to produce the best BEL that meets the electrical values of IEEE 1528. 17 different chemicals are used by trying different combinations. After the experimental phase of study, electrical values of the BELs are measured for 900 MHz that was used in GSM communications. It is possible to prepare thousands of different tissue-like liquids with the 17 different chemicals used in this study. However, it is practically impossible to prepare thousands of tissue-like fluids and is not suitable in terms of scientific working principles. Therefore, the use of ANN is found to be very useful in terms of the prediction of electrical values of the BELs. This study is the first in the literature in which ANN is used to determine the electrical properties of chemicals. Moreover, the success of ANN in this study proved that the electrical values of all liquids with a determined stoichiometry can be determined by using soft computing methods.