Oleksandr
Verified @ukr.net
Scopus Publications
- DEVELOPMENT OF A METHOD FOR CORRECTING THE PLACEMENT OF THE REGION OF INTEREST
Oleksandr Laktionov, Oleksandr Shefer, Svitlana Kyslytsia, Alla Bolotnikova
Advanced Information Systems, 2026
Objective. The process of developing a method for correcting the placement of the region of interest for a tracker has been investigated. The method is based on a nonlinear variable combination methodology that accounts for horizontal and vertical gradients. The justification for selecting the optimal method was carried out considering the number of operations per pixel and the computational complexity of the studied area. The accuracy criterion for region of interest placement correction was variance. To demonstrate the advantages of the proposed method, multiple video streams with varying frame counts were input into the tracker. A comparison was made with the well-known Channel and Spatial Reliability Tracker combined with a Kalman filter featuring different configurations. Results. A method for correcting region of interest placement using a nonlinear methodology requiring 8 operations per pixel has been developed. This method operates in conjunction with the tracker. In experimental videos, the variance decreased by an average of 10.25%, whereas existing methods showed deterioration ranging from -3.61% to -47.63%. The obtained results confirmed compliance with Technology Readiness Level 4. Scientific Novelty. The developed method for correcting the placement of the examined area in the object tracking task differs from existing ones by using combinations of nonlinear variables that take gradient analysis into account. This allows determining the displacement point of the region of interest based on horizontal and vertical gradients. Practical Significance. The proposed method can be used as an additional tool for real-time object tracking. - IMPROVING SAFETY AND EFFICIENCY FOR FIXED-WING UAVS BY UTILIZING AN UNMANNED GROUND PLATFORM
Nazar Pedchenko, Alina Yanko, Oleksandr Laktionov, Bohdan Boriak
Technology Audit and Production Reserves, 2025
The object of this research was the launch process of fixed-wing unmanned aerial vehicles. Military unmanned aerial vehicle systems are rapidly improving and becoming increasingly effective on the battlefield and in the enemy's rear. However, the complex and dynamic environment of modern warfare significantly impacts the preparation and launch of UAVs. Therefore, ensuring the maximum safety of these operations is one of the key factors influencing the overall effectiveness of these systems. At the same time, the launch operation requires personnel to be in an open area, making it a critical task to find solutions to protect UAV crews from enemy attacks. A possible solution is the remote control of the UAV launch. This article proposes using unmanned ground platforms for the remote launch of fixed-wing UAVs to reduce the probability of enemy strikes against crews and equipment. The research included modeling and comparing the launch of a fixed-wing UAV from a runway and with the help of an unmanned ground platform. The modeling results showed that launching from the platform reduces the takeoff distance by 39.1% (from 273.6 m to 166.7 m) and the operation time by more than half (from ~23 s to 9.2 s). This overall reduction will decrease the probability of the unmanned equipment being struck by the enemy. An additional advantage of this method is reduced fuel consumption. It also allows for the use of a propeller that is more efficient for flight, which is not possible with a traditional runway takeoff. Reducing the strength requirements for the drone's airframe allows for a decrease in its mass, which, in turn, increases the mass of the warhead or reconnaissance equipment. - DEVELOPMENT OF A COMPREHENSIVE INDICATOR FOR DIAGNOSING MASSIVE MISSILE STRIKES
Oleksandr Laktionov, Oleksandr Shefer, Serhii Fryz, Viktors Gopejenko, Viktor Kosenko
Advanced Information Systems, 2025
Objective. Enhancing the efficiency of diagnosing the threat level of massive missile strikes by developing a comprehensive indicator. Methodology. The study examines the process of developing a comprehensive indicator based on a dataset of massive missile strikes. This involves preliminary data processing, the development of a comprehensive indicator model, and the integration of individual indicators. One of the integrated indicators is assigned a weight coefficient, which is determined using artificial intelligence methods and constrained by a sigmoid activation function. A comparative analysis of the proposed comprehensive indicator against existing indicators was conducted based on the standard deviation criterion. The assessments obtained using the comprehensive indicator are employed to determine the threat level of massive missile strikes. Results. Based on an existing dataset of massive missile strikes on Ukraine, a comprehensive indicator has been developed, consolidating attack characteristics into a unified assessment. The comprehensive indicator's evaluations regarding massive missile strikes are utilized to determine the threat level (Cluster 1 – low threat level, Cluster 2 – high threat level). Scientific novelty. The proposed comprehensive indicator model differs from existing approaches in that its integrated indicators account for mean values and variations in assessments, serving as a prototype of the regularization concept. As a result, the standard deviation is reduced to 0.0925, whereas the existing approach demonstrates a deviation of 0.447 on a single experimental set of assessments. Practical significance. The proposed comprehensive indicator of massive missile strikes serves as an additional measure for determining the state's threat level or may be considered an element of a decision-making system. - DEVELOPMENT OF A CLUSTERING ALGORITHM FOR PARAMETERS OF EXPLOSIVE OBJECTS BASED ON A COMPREHENSIVE INDICATOR
O Laktionov, A Yanko, N Pedchenko
Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, 2025
Purpose. To enhance the efficiency of clustering parameters of explosive objects through the development of hybrid clustering elements. Methodology. A classifier for explosive objects based on a comprehensive indicator, serving as the main principle for classifier improvement, was developed using mathematical modeling. Data processing was carried out using the Python programming language and scikit-learn libraries. The research methodology involves grouping explosive objects into two clusters with the aim of improving the existing algorithms for detecting explosive objects. Findings. The proposed comprehensive indicator demonstrates a standard deviation 8.2 % less than the existing one. The improved clustering algorithm exhibits Davis-Bouldin index values of 0.517 and 0.525, while the existing ones show 0.572 and 0.572, respectively. This indicates that the output estimations of the new algorithm are less susceptible to noise, which enhances clustering quality and reduces the number of errors during practical application. Originality. A parameter clusterer for explosive objects is proposed which, unlike the existing ones, incorporates complex estimates built on the basis of a linear model with combined parameters as input data. Practical value. The practical significance of the proposed solution lies in the fact that improving existing algorithms for detecting explosive objects will increase the efficiency of computer vision in solving reconnaissance and demining tasks. The proposed solutions can be used as an addition to existing approaches for monitoring and managing national security to prevent emergencies. - Modeling of a Neural Network-Based Motor Position Controller in a System for Tracking Objects of Complex Shapes
Ceur Workshop Proceedings, 2025 - PREDICTING ROBOTIC PLATFORM MISSIONS USING A KERNEL ACTIVATION NETWORK WITH AN ASYMMETRIC KERNEL
Oleksandr Laktionov, Alina Yanko, Bohdan Boriak, Oleksii Mykhailichenko
Eastern European Journal of Enterprise Technologies, 2025
This study considers those processes predicting the functional efficiency of robotic platforms that affect the optimization of their mission planning. Given the growing demand for autonomous mobile systems, a critical task is to ensure high efficiency of their dynamics under different loads, terrains, and speeds, which requires reliable tools for decision-making even before physical launch. To solve the task, a method based on a customized Kernel Activation Network (KAN) was devised and programmatically implemented to predict the functional efficiency of the platform. The results demonstrate a significant increase in accuracy: KAN achieves an MSE of 0.00055727 on synthetic data and 0.00041720 on the experimental sample, while other architectures demonstrate 0.00105989 and higher. The key innovation of KAN is the use of an asymmetric chi-square kernel in parallel with the Gaussian kernel, as well as the integration of input estimates that take into account the triple interaction of factors. This explains the network's ability to effectively capture complex nonlinear dependences between numerous platform parameters (rolling resistance, aerodynamic drag, climbing force, etc.) and environmental conditions. The use of an asymmetric kernel significantly simplifies the network architecture, allowing for high accuracy at lower computational complexity. In practice, the results serve as an additional tool for optimizing mission planning of robotic platforms. This makes it possible to optimize equipment selection, construct strategic logistics routes, and increase the safety and reliability of autonomous systems under actual conditions. The achieved Technology Readiness Level is 4 - TECHNOLOGY FOR DETERMINING WEIGHT COEFFICIENTS OF COMPONENTS OF INFORMATION SECURITY
S Onyshchenko, A Hlushko, O Laktionov, S Bilko
Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, 2025
Purpose. Development of a technology for determining weighting coefficients based on an improved methodology to ensure the accuracy of determining the level of information security, taking into account its components. Methodology. The process of creating and conducting an experiment on the technology for determining weight coefficients of components of information security at the macro level is studied. The proposed technology utilizes two comprehensive assessments that consolidate information into a single score. One comprehensive indicator is based on considering the human factor, while the other excludes the human factor through the use of artificial intelligence. Arrays of resulting assessments are used to determine the level of information security, which allows improving the efficiency of the information security diagnostic process. Findings. The proposed technology, by utilizing a comprehensive indicator, demonstrates more effective diagnostic results, as determined by the standard deviation criterion. The integrated indicator that considers the human factor demonstrates a standard deviation value of 0.0195, while the comprehensive indicator without considering the human factor shows a value of 0.0047. Originality. The proposed technology differs from the existing ones by employing a comprehensive indicator that takes into account a six-digit interaction of integrated indicators, with weight coefficients determined using artificial intelligence tools. Practical value. The developed approach provides a more accurate result of integral assessment of the level of information security. This will allow the development of effective state instruments to enhance the level of information security, considering its current value, and to justify strategic directions for strengthening the state’s information security. - MODELS FOR INDUSTRY DIFFERENTIATION IN DECISION-MAKING SYSTEMS WITH AN APPLICATION TO THE UKRAINIAN ECONOMY
Alina Hlushko, Oleksandr Laktionov, Alina Yanko, Oleksandr Isaiev
Radioelectronic and Computer Systems, 2025
This article is devoted to the study of the problem of using adaptive models of differentiation of sectors of the real sector of the economy as a key component of modern decision support systems (DSS). The subject of the study is models of differentiation of real sectors of the Ukrainian economy for integration into decision support systems to optimize public administration. This research aims to develop and validate adaptive models of industry differentiation into clusters (groups) to improve the effectiveness of decision-making systems applied to the real sector of Ukraine’s economy. The research object is the process of sectoral differentiation, which allows determining the structural features and patterns of economic sector functioning. DSS architecture is proposed that integrates multifactor analysis and machine learning algorithms for automated selection of strategic scenarios. For clustering, we used production volume indicators and the number of strategically important enterprises in Ukraine for the pre-war period (2015–2021), which serve as a benchmark model for comparative analysis. A comparative assessment of the effectiveness of the classical K-means, DBSCAN, and Ensemble model algorithms was conducted with quantitative verification of the results using the Silhouette Score and Davies-Bouldin Score metrics. Empirical analysis showed that the DBSCAN and Ensemble models provide the highest quality of clustering (Silhouette Score 0.8387; Davies-Bouldin Score 0.0777), forming a reliable grouping of economic sectors. DSS module was developed based on the results obtained to form indicative tactical support measures, in particular, infrastructure strengthening of high-potential clusters and structural reorganization of vulnerable ones. Conclusions. The developed models form a universal methodological framework that is suitable for use in different countries, particularly in countries with a “peaceful” economy. DSS specialists can use the research results to identify key sectors of the economy, develop adaptive policies, and increase the stability and competitiveness of economic systems in a dynamic environment. - DEVELOPMENT OF A HARDWARE-SOFTWARE SOLUTION FOR DETECTION OF COMPLEX-SHAPED OBJECTS IN VIDEO STREAM
Oleksandr Laktionov, Alina Yanko, Alina Hlushko
Technology Audit and Production Reserves, 2024
The object of the study is the process of diagnosing complex-shaped objects in a video stream. The paper investigates the applied problem of creating a hardware-software solution for detecting complex-shaped objects in a video stream. Single-board computers Raspberry Pi models 4 and 5 with additional UPS HAT (D) modules and 21700 batteries were used as hardware, ensuring operation in the absence of power supply. Serial Camera Interface cameras and Full HD 1080p webcams were connected to the single-board computers to study effective methods of video processing using several studied video processing architectures. Eight video processing architectures based on the Oriented Features from Accelerated Segment Test and Rotated Binary Robust Independent Elementary Features and Scale-Invariant Feature Transform methods were considered. Each video processing architecture was tested using a one-minute video, where its average performance was determined. The limitations of video processing were a region of interest of 400x300 pixels and the presence of a limited number of reference images. To automate the launch of programs on single-board computers, the systemd initialization system was used. Known video processing algorithms were considered and a modification of the algorithm was proposed by using a double check for the presence of an object in the video stream. A hardware-software solution was implemented, consisting of a single-board computer with external cameras connected to it, and software for detecting complex-shaped objects in the video stream was created. The solution is useful as an auxiliary tool for detecting complex-shaped objects in the video stream on robotic platforms, in industry, everyday life, the educational process, and when repairing electronic modules. The practical significance of the study lies in the fact that the architecture for processing complex-shaped objects has been further developed. They provide for a double check for the presence of an object in the video stream, which increases the processing time of one frame, and on the other hand, increases the efficiency of object detection based on only one reference photo. - IMPLEMENTATION OF UNSUPERVISED LEARNING MODELS FOR ANALYZING THE STATE'S SECURITY LEVEL
Oleksandr Laktionov, Oleksandr Shefer, Iryna Laktionova, Vasyl Halai, Andrii Podorozhniak
Advanced Information Systems, 2024
Objective. Enhancing the effectiveness of preliminary analysis of the state's security level through the implementation of clustering models. Methodology. The process of creating unsupervised learning models and their peculiarities in tasks of analyzing the state's security level has been investigated. Techniques for creating the basic k-means model and its improvement through the use of Pearson correlation as a distance metric have been considered. Determining cluster centers was performed by both the basic method and the Cochran's maps method. The optimal quality indicator, according to the results of clustering, was considered to be the model demonstrating the minimum value of the Davies-Bouldin index. Results. An improved unsupervised learning model based on the k-means algorithm for analyzing the state's security level has been developed. The model is characterized by two clusters, with centroids determined as 1.112 and 1.009. Scientific novelty. The proposed model for clustering the state's security level differs from existing ones by using as input estimates derived from a comprehensive indicator based on the principles of interaction and emergent properties. This allows obtaining advantages of the clustering model in terms of the Davies-Bouldin index. The existing clustering model demonstrates a value of 0.4765, while the proposed one achieves 0.2166. Practical significance. The proposals serve as a useful additional tool for preliminary analysis of the state's security level during air alerts and extend the functionality of the previously researched forecasting technology. - PRACTICAL PRINCIPLES OF INTEGRATING ARTIFICIAL INTELLIGENCE INTO THE TECHNOLOGY OF REGIONAL SECURITY PREDICTING
Oleksandr Shefer, Oleksandr Laktionov, Volodymyr Pents, Alina Hlushko, Nina Kuchuk
Advanced Information Systems, 2024 - IMPROVEMENT OF THE METHOD FOR OPTIMIZATION OF PREDICTING THE EFFICIENCY OF A ROBOTIC PLATFORM
O. Laktionov, I. Laktionova
Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, 2024 - MODEL OF AN AUTOMATED CONTROL SYSTEM FOR THE POSITIONING OF RADIO SIGNAL TRANSMISSION/RECEPTION DEVICES
Bohdan Boriak, Alina Yanko, Oleksandr Laktionov
Radioelectronic and Computer Systems, 2024 - IDENTIFICATION OF AIR TARGETS USING A HYBRID CLUSTERING ALGORITHM
Oleksandr Laktionov, Alina Yanko, Nazar Pedchenko
Eastern European Journal of Enterprise Technologies, 2024 - INVESTIGATION OF COMBINED ENSEMBLE METHODS FOR DIAGNOSTICS OF THE QUALITY OF INTERACTION OF HUMAN-MACHINE SYSTEMS
Oleksandr Laktionov, Leonid Lievi, Andrii Tretiak, Mykola Movin
Naukovyi Visnyk Natsionalnoho Hirnychoho Universytetu, 2023 - IMPROVING THE METHODS FOR DETERMINING THE INDEX OF QUALITY OF SUBSYSTEM ELEMENT INTERACTION
Alexander Laktionov
Eastern European Journal of Enterprise Technologies, 2021 - Application of index estimates for improving accuracy during selection of machine operators
Alexander Laktionov
Eastern European Journal of Enterprise Technologies, 2019
