1 Non-destructive System Based on Electrical 2 Tomography and Machine Learning to Analyze 3 Moisture of Buildings 4

The article presents the results of research on a new method of spatial analysis of walls 11 and buildings moisture. Due to the fact that destructive methods are not suitable for historical 12 buildings of great architectural significance, a non-destructive method based on electrical 13 tomography has been adopted. A hybrid tomograph with special sensors was developed for the 14 measurements. This device enables the acquisition of data, which are then reconstructed by 15 appropriately developed methods enabling spatial analysis of wet buildings. Special electrodes that 16 ensure good contact with the surface of porous building materials such as bricks and cement were 17 introduced. During the research, a group of algorithms enabling supervised machine learning was 18 analyzed. They have been used in the process of converting input electrical values into conductance 19 depicted by the output image pixels. The conductance values of individual pixels of the output 20 vector made it possible to obtain images of the interior of building walls, both flat intersections (2D) 21 and spatial (3D) images. The presented group of algorithms has a high application value. The main 22 advantages of the new methods are: high accuracy of imaging, low costs, high processing speed, 23 ease of application to walls of various thickness and irregular surface. By comparing the results of 24 tomographic reconstructions, the most efficient algorithms were identified. 25