Oleksii Panko
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Oleksii Panko has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Svitlana Terenchuk
Київський національний університет будівництва і архітектури
3 shared publications - Natalia Poltorachenko
Kyiv National University of Construction and Architecture
2 shared publications - Roman Pasko
Київський національний університет будівництва і архітектури
2 shared publications - Bohdan Yeremenko
Taras Shevchenko National University of Kyiv
1 shared publication - Pavlo Pasieka
Kyiv National University of Construction and Architecture
1 shared publication - Vitaliy Zaprivoda
Kyiv National University of Construction and Architecture
1 shared publication
Latest Publications
- Open Access
- 30 June 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (3 (141)) , 41-53
Development of an approach to managing transport logistics at a construction site
This study investigates the process that forms a vehicle route in a complex logistics environment. The task addressed relates to the lack of a full-fledged logic in autonomous decision-making regarding operational routing in specialized logistics systems. An analysis of modern transport logistics management systems revealed their limitations in terms of the efficiency and explainability of the logic of autonomous decision-making regarding route replanning. An approach to route formation has been devised that combines the modified A* algorithm, multi-agent reinforcement learning, and spatio-temporal graph convolutional networks (STGCNs). Distinctive features of this approach are the combination of spatial-temporal forecasting, multi-agent decision-making, and modular system architecture, which provides adaptability, scalability, resistance to communication degradation, as well as explainability of transport routing decisions in closed reconfigurable networks. Experimental comparison of the devised approach and analogs based on A* and STGCN, carried out on a simulation model of the logistics environment at a construction site in residential area, showed its statistical superiority in terms of the route travel time criterion. With a threshold of this criterion of 300 s, the proposed approach achieved this indicator in 90% of cases, and the approaches based on STGCN and A* – in 79% and 57% of cases. In this case, the value of the 95th percentile was 310 s, 360 s, and 410 s for the proposed approach, STGCN, and A*. These results are explained by the combination of network state prediction and adaptive route replanning. The findings could be used in the design of intelligent transport logistics management systems at other facilities with dynamic transport infrastructure
- 30 June 2026
- Published by Private Company Technology Center in Eastern-European Journal of Enterprise Technologies
- Vol. 3 (3 (141)) , 41-53
Open AccessDevelopment of an approach to managing transport logistics at a construction site
This study investigates the process that forms a vehicle route in a complex logistics environment. The task addressed relates to the lack of a full-fledged logic in autonomous decision-making regarding operational routing in specialized logistics systems. An analysis of modern transport logistics management systems revealed their limitations in terms of the efficiency and explainability of the logic of autonomous decision-making regarding route replanning. An approach to route formation has been devised that combines the modified A* algorithm, multi-agent reinforcement learning, and spatio-temporal graph convolutional networks (STGCNs). Distinctive features of this approach are the combination of spatial-temporal forecasting, multi-agent decision-making, and modular system architecture, which provides adaptability, scalability, resistance to communication degradation, as well as explainability of transport routing decisions in closed reconfigurable networks. Experimental comparison of the devised approach and analogs based on A* and STGCN, carried out on a simulation model of the logistics environment at a construction site in residential area, showed its statistical superiority in terms of the route travel time criterion. With a threshold of this criterion of 300 s, the proposed approach achieved this indicator in 90% of cases, and the approaches based on STGCN and A* – in 79% and 57% of cases. In this case, the value of the 95th percentile was 310 s, 360 s, and 410 s for the proposed approach, STGCN, and A*. These results are explained by the combination of network state prediction and adaptive route replanning. The findings could be used in the design of intelligent transport logistics management systems at other facilities with dynamic transport infrastructure
- Open Access
- 26 March 2026
- Published by Kyiv National University of Construction and Architecture in Management of Development of Complex Systems
- No. 65,p. 181-187
Formalization of the initial stage of engineering network design
The problem of distributing work volumes at different stages of construction or reconstruction of engineering networks is solved, taking into account the current state of communal utility systems. The problem is formulated considering the conditions of initial information uncertainty and the prospective development of the engineering network. The proposed mathematical model is a Boolean programming problem with variables in the form of interval numbers that characterize the assignment of design territory sections to a particular stage of construction or reconstruction of the engineering network. The problem is solved by Boolean programming methods taking into account the apparatus of interval arithmetic. Two variants of the algorithm for finding a compromise solution are proposed. Initially, numerical characteristics are calculated based on expert conclusions, which are associated with interval coefficients. At the next stage, the reduction task is solved by using two extreme objective functions, which limit the set of feasible compromise solutions. Based on the intermediate results, variables that take the same values are selected. The values of these variables are taken as final and are removed from the objective function of the initial model, which significantly reduces the number of variables in the model. Boolean programming methods are again applied to the new model with a smaller number of Boolean functions and interval coefficients of the objective function, which provides the most probable solution. If the problem has a solution, then it is close to the optimal one. If the problem does not have a solution, then fuzzy preference relation methods are used on a set of alternatives. If at the beginning of the modeling it is allowed to reduce the requirement that the site belongs to the corresponding stage of construction (reconstruction) of the engineering network, then Boolean programming problems are modified to partially discrete linear programming, which allows expanding the criteria for assigning final values to variables and removing them from the objective function of the initial model.
- 26 March 2026
- Published by Kyiv National University of Construction and Architecture in Management of Development of Complex Systems
- No. 65,p. 181-187
Open AccessFormalization of the initial stage of engineering network design
The problem of distributing work volumes at different stages of construction or reconstruction of engineering networks is solved, taking into account the current state of communal utility systems. The problem is formulated considering the conditions of initial information uncertainty and the prospective development of the engineering network. The proposed mathematical model is a Boolean programming problem with variables in the form of interval numbers that characterize the assignment of design territory sections to a particular stage of construction or reconstruction of the engineering network. The problem is solved by Boolean programming methods taking into account the apparatus of interval arithmetic. Two variants of the algorithm for finding a compromise solution are proposed. Initially, numerical characteristics are calculated based on expert conclusions, which are associated with interval coefficients. At the next stage, the reduction task is solved by using two extreme objective functions, which limit the set of feasible compromise solutions. Based on the intermediate results, variables that take the same values are selected. The values of these variables are taken as final and are removed from the objective function of the initial model, which significantly reduces the number of variables in the model. Boolean programming methods are again applied to the new model with a smaller number of Boolean functions and interval coefficients of the objective function, which provides the most probable solution. If the problem has a solution, then it is close to the optimal one. If the problem does not have a solution, then fuzzy preference relation methods are used on a set of alternatives. If at the beginning of the modeling it is allowed to reduce the requirement that the site belongs to the corresponding stage of construction (reconstruction) of the engineering network, then Boolean programming problems are modified to partially discrete linear programming, which allows expanding the criteria for assigning final values to variables and removing them from the objective function of the initial model.
- Open Access
- 11 April 2022
- Published by Kyiv National University of Construction and Architecture in Management of Development of Complex Systems
- No. 49,p. 74-80
DIGITAL TECHNOLOGIES INTO PROCESS INSPECTION OF BUILDINGS, PROPERTY AND INFRASTRUCTURE OBJECTS INTRODUCING
The paper examines the RebuildUA project, which aims to digitize, analyze and disseminate information on the destruction of buildings, property and infrastructure objects of settlements in Ukraine as a result of the Russian invasion. Providing such information to communities, public authorities and specialized funds for the reconstruction of Ukraine for further damage assessment is dictated by the urgent need for rapid territories’ reconstruction where hostilities have ended. The availability of digitized information will also simplify the process of obtaining reparations and attracting resources for reconstruction. Possibilities of modern unmanned aerial vehicles and satellite surveillance systems are shown in performing such tasks as photo and video shooting, data transmission in detecting destroyed and damaged objects, creating maps of bombing level, level of destruction, destroyed buildings and infrastructure objects, assessment of buildings damage and infrastructure objects. Photo-fixation examples of damaged objects and fragments of orthophotoplans of Kyiv region's settlements region before and after hostilities are given. It has been found that the use of modern digital technology allows to collect the necessary data on the destruction, giving experts the opportunity to obtain photos and videos of objects from different angles. This greatly facilitates and accelerates the identification of damage, assessment of the objects' technical condition and the determination of losses suffered by property owners as a result of destruction. However, the number of destroyed and damaged objects is so large, and the deadlines are so critical that the process of forming expert opinions requires automation. This will be the subject of further work.
- 11 April 2022
- Published by Kyiv National University of Construction and Architecture in Management of Development of Complex Systems
- No. 49,p. 74-80
Open AccessDIGITAL TECHNOLOGIES INTO PROCESS INSPECTION OF BUILDINGS, PROPERTY AND INFRASTRUCTURE OBJECTS INTRODUCING
The paper examines the RebuildUA project, which aims to digitize, analyze and disseminate information on the destruction of buildings, property and infrastructure objects of settlements in Ukraine as a result of the Russian invasion. Providing such information to communities, public authorities and specialized funds for the reconstruction of Ukraine for further damage assessment is dictated by the urgent need for rapid territories’ reconstruction where hostilities have ended. The availability of digitized information will also simplify the process of obtaining reparations and attracting resources for reconstruction. Possibilities of modern unmanned aerial vehicles and satellite surveillance systems are shown in performing such tasks as photo and video shooting, data transmission in detecting destroyed and damaged objects, creating maps of bombing level, level of destruction, destroyed buildings and infrastructure objects, assessment of buildings damage and infrastructure objects. Photo-fixation examples of damaged objects and fragments of orthophotoplans of Kyiv region's settlements region before and after hostilities are given. It has been found that the use of modern digital technology allows to collect the necessary data on the destruction, giving experts the opportunity to obtain photos and videos of objects from different angles. This greatly facilitates and accelerates the identification of damage, assessment of the objects' technical condition and the determination of losses suffered by property owners as a result of destruction. However, the number of destroyed and damaged objects is so large, and the deadlines are so critical that the process of forming expert opinions requires automation. This will be the subject of further work.
- 30 June 2021
- Published by Astana IT University in Scientific Journal of Astana IT University
- No. 6,p. 76-87
MODELS, METHODS, AND MEANS OF REPRODUCTION OF EXPERT KNOWLEDGE IN INTELLIGENT SUPPORT SYSTEM BUILDING-TECHNICAL EXPERTISE
The paper is devoted to solving such a scientific and practical problem as the creation of computerized infocommunication systems for support building-technical expertise to determine the causes of destruction and deformation of buildings and structures. The analysis of the current state of expert activity within the framework of building-technical expertise is carried out. Perspective directions of the introduction of intelligent infocommunication systems in the course of performance of building-technical expertise and expert researches are outlined. The architecture of Intelligent Support System Building-Technical Expertise and the communication scheme of experts with the system are shown. To mapping expert knowledge formalized in the form of fuzzy associative rules to the memory card of the Cascade ARTMAP category fuzzy artificial neural network, it is proposed to use a fuzzy Mamdani-type inference system. The main input data, on the basis of which a fuzzy conclusion is realized to establish the degree of influence of various environmental factors on the technical condition of buildings and structures, are systematized and presented in a form acceptable for processing by computerized systems. At the same time, the main focus is on the study of facilities that are built and operated on subsidence loess soils. The process of formalization of heuristics, which is based on the formation of associations related to information on the position of signs of deterioration of the technical condition of the objects of expertise and the position of the changed soil, is described. Examples of interpretation and fuzzification of input information on soil properties, characteristics of the soil base of the object of building-technical expertise, and the surrounding area are given. The described approach provides an opportunity to reduce the risks of making wrong decisions by using the system as an intelligent database. The use of an artificial fuzzy neural network of the Cascade ARTMAP category gives the system the ability to form an expert conclusion on the degree of influence of various environmental factors on the technical condition of objects in the fuzzy conditions of a partially observed environment.
- 30 June 2021
- Published by Astana IT University in Scientific Journal of Astana IT University
- No. 6,p. 76-87
MODELS, METHODS, AND MEANS OF REPRODUCTION OF EXPERT KNOWLEDGE IN INTELLIGENT SUPPORT SYSTEM BUILDING-TECHNICAL EXPERTISE
The paper is devoted to solving such a scientific and practical problem as the creation of computerized infocommunication systems for support building-technical expertise to determine the causes of destruction and deformation of buildings and structures. The analysis of the current state of expert activity within the framework of building-technical expertise is carried out. Perspective directions of the introduction of intelligent infocommunication systems in the course of performance of building-technical expertise and expert researches are outlined. The architecture of Intelligent Support System Building-Technical Expertise and the communication scheme of experts with the system are shown. To mapping expert knowledge formalized in the form of fuzzy associative rules to the memory card of the Cascade ARTMAP category fuzzy artificial neural network, it is proposed to use a fuzzy Mamdani-type inference system. The main input data, on the basis of which a fuzzy conclusion is realized to establish the degree of influence of various environmental factors on the technical condition of buildings and structures, are systematized and presented in a form acceptable for processing by computerized systems. At the same time, the main focus is on the study of facilities that are built and operated on subsidence loess soils. The process of formalization of heuristics, which is based on the formation of associations related to information on the position of signs of deterioration of the technical condition of the objects of expertise and the position of the changed soil, is described. Examples of interpretation and fuzzification of input information on soil properties, characteristics of the soil base of the object of building-technical expertise, and the surrounding area are given. The described approach provides an opportunity to reduce the risks of making wrong decisions by using the system as an intelligent database. The use of an artificial fuzzy neural network of the Cascade ARTMAP category gives the system the ability to form an expert conclusion on the degree of influence of various environmental factors on the technical condition of objects in the fuzzy conditions of a partially observed environment.