Impact of the Radial Basis Function Spread Factor onto Image Reconstruction in Electrical Impedance Tomography∗

The major problem of the Electrical impedance tomography (EIT) is to get the resistivity distribution image of a given cross-sectional area. There are many methods solving this non-linear problem, mostly requiring certain simplifications and assumptions. Most of the methods are also computationally demanding and not easy to implement. The usage of the neural networks appears to be a solution of the mentioned problems. In this article we continued with our previous study and used Radial basis function (RBF) neural network for image reconstruction in electrical impedance tomography and we focused on examining how the change of the spread parameter of the RBF influences the result of the image reconstruction with the RBF neural network.