ASSESSMENT OF TECHNICAL CONDITION OF PREFABRICATED LARGE-BLOCK BUILDING STRUCTURES LOCATED IN MINING AREA USING THE NAIVE BAYES CLASSIFIER

• Published in: International Multidisciplinary Scientific GeoConference SGEM Vol. 2; pp. 109 - 116
• Main Authors: Rusek, Janusz, Firek, Karol
• Format: Conference Proceeding
• Language: English
• Published: Sofia Surveying Geology & Mining Ecology Management (SGEM) 01.01.2016
• Subjects: Artificial intelligence; Bayesian analysis; Buildings; Classification; Classifiers; Construction; Copper; Damage assessment; Data mining; Data processing; Deformation; Mining; Mining effects; Prefabricated buildings; Probability; Probability theory; Simulation; Statistical analysis; Variables
• ISSN: 1314-2704
• DOI: 10.5593/SGEM2016/B52/S20.015

The paper presents the use of the Naive Bayes Classifier (NBC) to assess the technical condition of prefabricated large-block buildings subjects to mining effects in the Legnica-Głogów Copper District (LGOM). As part of the study, the classifier was created in the form of the Naive Bayes Network, using the data on the intensity of mining impacts and construction factors, collected for 126 analyzed buildings. The paper presents the possibility of using the created model for the standard classification, together with the probabilistic interpretation of the obtained results. The specification of the classification task, which involves the determination of the probability of the predicted category of the technical condition of the buildings, can be used to assess the extent of mining damage.