Using of Artificial Neural Networks in Support System of Forensic Building-Technical Expertise
Petro Kulikov1, Roman Pasko2, Svitlana Terenchuk3, Vitalii Ploskyi4, Bohdan Yeremenko5
1Petro Kulikov, Rector of Kyiv National University of Construction and Architecture, Kyiv, Ukraine.
2PRoman Pasko, Laboratory of Engineering and Technical Research, Kyiv Scientific Research Institute of Forensic Expertise of the Ministry of Justice of Ukraine, Kiev, Ukraine.
3Svitlana Terenchuk, Department of Information Technology Design and Applied Mathematics, Kyiv National University of Construction and Architecture, Kyiv, Ukraine.
4Vitalii Ploskyi, department of Architectural Structures, Kyiv National University of Construction and Architecture, Kyiv, Ukraine.
5Yeremenko Bohdan*, Department of Information Technology Design and Applied Mathematics, Kyiv National University of Construction and Architecture, Kyiv, Ukraine.
Manuscript received on January 13, 2020. | Revised Manuscript received on January 21, 2020. | Manuscript published on February 10, 2020. | PP: 3162-3168 | Volume-9 Issue-4, February 2020. | Retrieval Number: D2050029420/2020©BEIESP | DOI: 10.35940/ijitee.D2050.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The article contains an analysis of the order of forensic building-technical expertise and expert research to determine the reasons for the deterioration of the technical condition of the structural elements of buildings. The conditions for forming expert conclusions about the possible correlation between the appearance of negative changes in the technical condition of the structural elements that have become the subject of forensic building-technical expertise and the various factors of influence of the environment are investigated. In doing so, the focus is on the impact factors associated with carrying out renovation work in adjacent premises. In addition, issues related to the fuzzy uncertainty of the different nature of the expert researches are highlighted. Some of these problems are proposed to be solved by the using of artificial neural networks in the fuzzy subsystem of the system of support of forensic building-technical expertise. It is shown that a considerable part of the materials of forensic building-technical expertise and expert research is represented by photographs of injuries. Fixation of damaged structures is reflected in the plans of premises and schemes of placement of structures in the buildings. The graphic information of the research materials is accompanied by textual information, the processing of which requires the use of models and methods of fuzzy mathematics. The fragment of the knowledge base is provided, which contains information on the geometric parameters of damage to building structures and an example of a fuzzy rule that reflects an expert conclusion. The expediency of using fuzzy neural networks of adaptive resonance theory of the Cascade ARTMAP category is substantiated. Cascade ARTMAP memory card schematic is shown.
Keywords: Building Construction, Expert Conclusion, Fuzzy Uncertainty, Fuzzy rule, Geometric Damage Parameters.
Scope of the Article: Energy Efficient Building Technology