Ihor Bodnarchuk
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ihor Bodnarchuk has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Kharchenko
National Aviation University, Kosmonavta Komarova ave. 1, Kyiv, 03058, UKRAINE
5 shared publications - Ihor Raichev
Computer Informational Technologies Department, National Aviation University, Kyiv, Ukraine
2 shared publications Irina Halay
Computer Informational Technologies Department, National Aviation University, Kyiv, Ukraine
2 shared publicationsNatalia Zagorodna
Cyber Security Department, Ternopil Ivan Puluj National Technical University, Ternopil, Ukraine
2 shared publications- Nataliia Kunanets
Lviv Polytechnic National University
2 shared publications - Oleksandr Matsiuk
Ternopil Ivan Puluj National Technical University
2 shared publications
Latest Publications
- 28 October 2026
- Published by Society for Structural Integrity and Life "Prof. dr Stojan Sedmak" in Structural Integrity and Life
- Vol. 26 (Special A) , S31-S37
An optimised stacking ensemble machine learning model for predicting the hysteresis behaviour of shape memory alloys
The study investigates the possibility of predicting the hysteresis behaviour of a NiTi shape memory alloy (SMA) under cyclic loading using machine learning methods. Based on experimental test data obtained from SMA wire specimens, an ensemble model of the Stacking Regressor type is developed, combining the Random Forest, Gradient Boosting, Extremely Randomised Trees, k-Nearest Neighbours, Support Vector Regression, and Multi-Layer Perceptron algorithms. The ElasticNet algorithm is employed as the meta-model. The ensemble structure and model hyperparameters are optimised using the GridSearchCV procedure with group cross-validation. The results demonstrate high accuracy in strain prediction across different cyclic loading frequencies. The coefficient of determination R² for the test data exceeds 0.996. The proposed model also exhibits strong generalisation when predicting material behaviour beyond the training range and accurately reproduces the shape of hysteresis loops in the stress-strain diagram.
- 28 October 2026
- Published by Society for Structural Integrity and Life "Prof. dr Stojan Sedmak" in Structural Integrity and Life
- Vol. 26 (Special A) , S31-S37
An optimised stacking ensemble machine learning model for predicting the hysteresis behaviour of shape memory alloys
The study investigates the possibility of predicting the hysteresis behaviour of a NiTi shape memory alloy (SMA) under cyclic loading using machine learning methods. Based on experimental test data obtained from SMA wire specimens, an ensemble model of the Stacking Regressor type is developed, combining the Random Forest, Gradient Boosting, Extremely Randomised Trees, k-Nearest Neighbours, Support Vector Regression, and Multi-Layer Perceptron algorithms. The ElasticNet algorithm is employed as the meta-model. The ensemble structure and model hyperparameters are optimised using the GridSearchCV procedure with group cross-validation. The results demonstrate high accuracy in strain prediction across different cyclic loading frequencies. The coefficient of determination R² for the test data exceeds 0.996. The proposed model also exhibits strong generalisation when predicting material behaviour beyond the training range and accurately reproduces the shape of hysteresis loops in the stress-strain diagram.
- 8 November 2020
- Published by Academy of Cognitive and Natural Sciences
Choice Method of Analytical Platform for Smart Cities
The smart cities development results in the expansion of the list of information technologies used for this purpose. These technologies are given below in the form of matrix and formal description. The proposed list of information technologies includes: Internet of Things, Fog Computing, Cloud Computing, Information Models, Intelligent Data Processing and Decision Support Systems, Mobile Technology, Geoinformation Technologies, GRID technology, Confidential Communication and Data Protection Technologies. While implementing the procedures for information technology support of the processes in smart cities, it is a common practice to use the models of analytical platforms which are on the open market. At present, their list is quite extensive. This fact creates uncertainty in the analytical platform selection. In order to select the analytical platform, the technique based on the hierarchy analysis method on the ground of procedure of pairwise comparisons of variants is pro- posed in this paper. The analysis was carried out among such alternative characteristics as computing resources and cloud infrastructure, availability and reliability, ana-lytics, safety and security, cost, application programming interface, support. The obtained results show the highest efficiency of the method of the IBM Bigdata Analytics platform. It should be noted that the proposed method is to be implemented taking into account the probable need for the expansion of the set of analytical platforms characteristics and parameters.
- 8 November 2020
- Published by Academy of Cognitive and Natural Sciences
Choice Method of Analytical Platform for Smart Cities
The smart cities development results in the expansion of the list of information technologies used for this purpose. These technologies are given below in the form of matrix and formal description. The proposed list of information technologies includes: Internet of Things, Fog Computing, Cloud Computing, Information Models, Intelligent Data Processing and Decision Support Systems, Mobile Technology, Geoinformation Technologies, GRID technology, Confidential Communication and Data Protection Technologies. While implementing the procedures for information technology support of the processes in smart cities, it is a common practice to use the models of analytical platforms which are on the open market. At present, their list is quite extensive. This fact creates uncertainty in the analytical platform selection. In order to select the analytical platform, the technique based on the hierarchy analysis method on the ground of procedure of pairwise comparisons of variants is pro- posed in this paper. The analysis was carried out among such alternative characteristics as computing resources and cloud infrastructure, availability and reliability, ana-lytics, safety and security, cost, application programming interface, support. The obtained results show the highest efficiency of the method of the IBM Bigdata Analytics platform. It should be noted that the proposed method is to be implemented taking into account the probable need for the expansion of the set of analytical platforms characteristics and parameters.
- 29 March 2019
- Published by Springer Nature
- p. 419-427
Multicriteria Choice of Software Architecture Using Dynamic Correction of Quality Attributes
- 29 March 2019
- Published by Springer Nature
- p. 419-427
Multicriteria Choice of Software Architecture Using Dynamic Correction of Quality Attributes
- 1 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1245-1248
Optimization of software architecture selection for the system under design and reengineering
The problem of optimization of software system architecture choice is considered taking into account changes of requirements in iterative technologies of design and reengineering. The solution is offered on the base of correction of alternatives' characteristics which were accounted on previous iteration or modification of existing software system during reengineering. This method prevents recalculations for evaluation and selection process. The method of pairwise substitution is applied for alternatives' characteristics correction. Its concept lies in compensation on supremacy of criterion change. Multicriteria optimization of substitution is carried out using nonlinear scalar convolution what improves validity of selected decision.
- 1 February 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1245-1248
Optimization of software architecture selection for the system under design and reengineering
The problem of optimization of software system architecture choice is considered taking into account changes of requirements in iterative technologies of design and reengineering. The solution is offered on the base of correction of alternatives' characteristics which were accounted on previous iteration or modification of existing software system during reengineering. This method prevents recalculations for evaluation and selection process. The method of pairwise substitution is applied for alternatives' characteristics correction. Its concept lies in compensation on supremacy of criterion change. Multicriteria optimization of substitution is carried out using nonlinear scalar convolution what improves validity of selected decision.
- 13 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4-8
Multicriteria architecture choice of software system under design and reengineering
The problems of multi-criteria choice of software system architecture are discussed, connected with definition of criterial function structure and formalization of trade-offs definition procedure for decision making. Universal scalar convolution is offered for taking into account requirements of subject area and criteria values limitations. The criterion weight in this convolution depends on its value proximity to the limitation. Optimization model “replacement-compensation” is used for software system reengineering problems or for directed choice of software architecture.
- 13 October 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4-8
Multicriteria architecture choice of software system under design and reengineering
The problems of multi-criteria choice of software system architecture are discussed, connected with definition of criterial function structure and formalization of trade-offs definition procedure for decision making. Universal scalar convolution is offered for taking into account requirements of subject area and criteria values limitations. The criterion weight in this convolution depends on its value proximity to the limitation. Optimization model “replacement-compensation” is used for software system reengineering problems or for directed choice of software architecture.
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 132-136
Trade-off optimization in the problem of software system architecture choice
The problems of multi-criteria choice of software system architecture are discussed, connected with definition of criterion function. For this the universal scalar convolution is offered to apply, where the priority of quality criteria depends on its proximity to the limitation. Optimization model application for problem of reengineering or directed choice of software architecture is discussed too.
- 1 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 132-136
Trade-off optimization in the problem of software system architecture choice
The problems of multi-criteria choice of software system architecture are discussed, connected with definition of criterion function. For this the universal scalar convolution is offered to apply, where the priority of quality criteria depends on its proximity to the limitation. Optimization model application for problem of reengineering or directed choice of software architecture is discussed too.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 198-205
Trade-off optimal decision of the problem of software system architecture choice
The methods of software architectures examination are discussed in the paper. It is shown that this is multicriteria hierarchical problem. For its solution, modified Analytic Hierarchy Process (AHP) is applied. Nevertheless, general result of software architectures assessment hides influence of each quality criterion on the final value and correlations between criteria too. Therefore, it is proposed to investigate this problem via examination of criteria comparability by replacement and examine sensitivity the result of alternative architectures assessment as well, and optimization of trade-offs between quality criteria.
- 1 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 198-205
Trade-off optimal decision of the problem of software system architecture choice
The methods of software architectures examination are discussed in the paper. It is shown that this is multicriteria hierarchical problem. For its solution, modified Analytic Hierarchy Process (AHP) is applied. Nevertheless, general result of software architectures assessment hides influence of each quality criterion on the final value and correlations between criteria too. Therefore, it is proposed to investigate this problem via examination of criteria comparability by replacement and examine sensitivity the result of alternative architectures assessment as well, and optimization of trade-offs between quality criteria.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 01, 265-269
Decision support system of software architect
Represented system is for supplying of architect with data, knowledge and methods needed to make decisions in the process of software systems (SS) design. It includes two subsystems: first one is subsystem of requirements specification and communication to SS, and second is architecture design subsystem. For requirements specification and communication formalism of basic protocols method and technic of expert pairwise comparisons are used. The selection of architecture decisions is represented as model of multi criteria hierarchic optimization, where modified Analytic Hierarchic Process (AHP) was applied. Main units of the system is implemented as formalized models or software units.
- 1 September 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 01, 265-269
Decision support system of software architect
Represented system is for supplying of architect with data, knowledge and methods needed to make decisions in the process of software systems (SS) design. It includes two subsystems: first one is subsystem of requirements specification and communication to SS, and second is architecture design subsystem. For requirements specification and communication formalism of basic protocols method and technic of expert pairwise comparisons are used. The selection of architecture decisions is represented as model of multi criteria hierarchic optimization, where modified Analytic Hierarchic Process (AHP) was applied. Main units of the system is implemented as formalized models or software units.