Historical Buildings Dampness Analysis Using Electrical Tomography and Machine Learning Algorithms

The article deals with the problem of detecting moisture in walls historical buildings. As part presented research, following four methods based on mathematical modeling and machine learning were compared: total variation, least-angle regression, elastic net, artificial neural networks. Based simulation data, systems for reconstruction “pixel by pixel” tomographic images trained. In order to test reconstructive algorithms obtained during generated real measurements cases. method comparison was performed basis three indicators: mean square error, relative image correlation coefficient. above indicators applied selected variants that corresponded various parts walls. differed dimensions tested wall sections, number electrodes used, resolution 3D meshes. all analyzed variants, best results using net algorithm. addition, better reconstructions than classic Total Variation method.