Machine learning in image reconstruction by multi-sensor electrodes

The article presents a system that uses machine learning to reconstruct the image using multi-sensor electrodes based on electric tomography. It is an innovative approach to testing the properties of test areas, including levees. The measuring system was based on an electric tomography device, which assumes the use of two measuring methods and allows measurements to be made to 32 channels. The device based on electric impedance tomography measures the tested object based on the potential distribution measurements. The system collects measured data from the electrodes. In the process of image reconstruction, the elastic net method was used, where appropriate regularization methods help in choosing the optimal solution.