AHAnatolii Husakovskyi

Anatolii Husakovskyi

*This is an algorithmically generated author record based on publicly available information.

Anatolii Husakovskyi has a total of 4 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Prompt engineering for large language models in test case generation

    by Anatolii Husakovskyi

    The purpose of this study was to perform a three-scenario comparative analysis of the accuracy of intelligent fault diagnosis in complex technical systems using ship power plants (SPPs) as a representative case. The research sought to determine which diagnostic configuration ensures the highest accuracy and robustness under varying operational conditions. Three methodological configurations were analysed: a baseline model based on Case-Based Reasoning (CBR); CBR enhanced with probabilistic analysis using Bayesian networks and Markov chains; and a comprehensive integration of CBR with probabilistic models and simulation modelling of cascading failures. Experiments were conducted under three typical operational scenarios – nominal mode, high-load mode, and limited diagnostic data – reflecting real maritime conditions. Standard classification accuracy metrics were employed, including Accuracy, Recall, and F1-score. The results showed that the basic CBR configuration achieves an average accuracy of 82-85% under nominal conditions but significantly loses efficiency when data are incomplete. Integration with probabilistic models improves metric stability, increasing accuracy to 88-90%. At the optimal configuration of method weights (CBR – αd = 0.6, probabilistic models – βd = 0.2, simulation modelling – γd = 0.2), the minimum diagnostic error of 6% was achieved, and diagnostic accuracy exceeded 93% even under noisy or incomplete data. Analysis of confusion matrices and error visualisations revealed that integrated configurations reduce the number of type II errors by approximately 35% compared to isolated approaches. Three-dimensional plots of accuracy dependence on component weights confirmed a stable maximum in the balanced-parameter zone and highlighted the significance of the simulation component under complex operational conditions. The obtained results allowed formulating practical recommendations for selecting diagnostic configurations: CBR + Bayesian Networks for stable modes and full integration for overload or data-limited scenarios. The proposed methodology is adaptable to other intelligent diagnostic systems operating under uncertainty, variable load, and incomplete information, including cyber-physical and industrial systems. It represents a universal and scalable framework for applied diagnostics requiring high accuracy, adaptability, and robustness

  • Open Access

    AI evolution and its role in transforming the automation of commercial activities

    by Mykhailo Lukash, Yevhenii Chuprun, Oksana Lysak, Anatolii Husakovskyi, Kyrylo Hanhanov

    This article examined the impact of artificial intelligence (AI) on the automation of business processes, focusing on how intelligent systems enhanced management efficiency and operational optimization. Special attention was given to cognitive neuro-fuzzy models and their role in transforming business processes in the digital era. The study was timely, considering the exponential growth of data and the complexity of modern organizational structures, which demanded fast, accurate, and adaptive management solutions. AI technologies provided such capabilities, while companies that failed to adopt them risked losing competitive advantage amid ongoing digital transformation. The study aimed to develop and justify a conceptual approach to automating business processes through AI. To achieve this, two primary methods were applied: cognitive modeling using semantic M-networks to reflect human imaginative thinking in process structures, and reinforcement learning to optimize processes based on feedback mechanisms. The methodology combined theoretical literature analysis, mathematical modeling, and empirical examination of real business processes. The findings demonstrated that integrating AI significantly improved overall business process efficiency by reducing complexity, costs, and feedback loops, while enhancing control, regulation, and financial outcomes. The M-network model illustrated how AI adapted processes to dynamic environments and supported decision-making through visualized cognitive maps. Future research directions included advancing cognitive learning algorithms to handle larger datasets, designing adaptive AI interfaces tailored to individual user behavior, and exploring AI’s influence on cross-functional collaboration to foster comprehensive digital management ecosystems.