MMMykhaylo Melnyk

Mykhaylo Melnyk

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mykhaylo Melnyk has a total of 63 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evaluating Neus-Facto Lesion Surface-Area Measurement Using a 3D-Printed Anatomical Phantom

    by Roman Burkovskyi, Mykhaylo Melnyk, Wojciech Zabierowski

    Accurate measurement of the surface area of skin lesions and chronic wounds is a key element of monitoring their dynamics—both healing and progression—yet traditional manual methods are invasive, slow, and highly operator-dependent, while two-dimensional (2D) digital approaches based on smartphone imaging distort area geometry on curved anatomical surfaces. Three-dimensional (3D) surface reconstruction removes these limitations, and among current methods the family of neural implicit surfaces—in particular Neus-Facto—demonstrates the highest geometric accuracy in a recent empirical benchmark study. However, existing evaluations use a structured-light 3D scanner as the reference, whose own measurement error is confounded with the error of the method under test; the test phantoms are isolated from the anatomical context of the body, and repeatability is assessed on frame subsets of a single video. In this work, we propose an alternative path for evaluating Neus-Facto, where the reference geometry is defined not by measurement but by design—a digital CAD model realized as a 3D-printed anatomical foot phantom with an embedded lesion region. Capture is performed with a consumer-grade smartphone following a documented protocol; repeatability is assessed on genuinely separate physical sessions at different times, with variation in camera distance and viewpoint. This setup separates the error of the method from the error of the measurement reference and more closely approximates—though it does not yet reproduce—real clinical conditions; these results indicate potential for future clinical translation, while further validation under real clinical conditions is required.

  • Open Access

    An Advanced Method of Modeling the Dynamics of a Suspended Monorail Using Fractal Analysis

    by Mariana Levkovych, Stepan Lys, Wojciech Zabierowski, Oksana Oborska, Mykhaylo Melnyk

    Fractional differential operators provide an effective approach for modeling complex technological processes, particularly physical phenomena in continuum mechanics characterized by memory and non-local effects. Different types of fractional derivatives require different numerical approximation schemes; in this study, the Caputo and Grünwald–Letnikov derivatives are considered. The aim of this work was to develop and validate a fractional differential model of longitudinal oscillations in a suspended monorail system that accounts for nonlinear and memory-dependent effects. In contrast to classical integer-order approaches, the proposed framework incorporates multiscale surface irregularity effects, including rail roughness, friction, and other disturbances influencing system dynamics, through a fractional-order formulation. A fractional differential mathematical model describing the motion of longitudinal oscillations of a large-sized cargo transported along a suspended monorail is proposed. A numerical algorithm based on finite-difference approximation of fractional operators was developed for its implementation. The scientific contribution lies in integrating multiscale surface irregularity effects into a fractional-order modeling framework to improve the accuracy of dynamic response prediction. Numerical experiments demonstrated the effectiveness of the approach, and the results were validated through comparison with existing models of monorail dynamics. Additionally, statistical validation based on correlation analysis confirmed good agreement with the experimental data. The proposed model can be applied to the design and optimization of suspended transport systems, improving vibration control, reliability, and operational safety under real dynamic loading conditions.

  • Open Access

    Synthesis of a Macromodel for a Virtual Signal Simulator of Adaptive Acoustics

    by Lviv Polytechnic National University, Mykhaylo Melnyk, Roman Holyaka, Andriy Kernytskyy, Roman Vynarovych, Mykhailo Shvarts

    This work is dedicated to the development of a macromodel for the virtual signal simulator of adaptive acoustics, Data@Sim, based on the formal analogy method. The structure of modeling electro- acoustic processes in adaptive acoustics tasks and approaches to the unification of research on electrical and acoustic signals are presented. An algorithm for synthesizing virtual signals that accounts for temporal parameters of sound wave propagation and attenuation, as well as noise and interference effects, is proposed. The model is implemented in the SPICE environment and enables verification of measurement transformations used in acoustic metrology systems. The conducted analysis demonstrates the effectiveness of the proposed approach for modeling the acoustic environment and optimizing digital processing methods for acoustic signals.

  • PROGRAMMABLE EMBEDDED SYSTEM FOR ADAPTIVE ACOUSTICS PARAMETER RESEARCH

    by Lviv Polytechnic National University, Mykhaylo Melnyk, Roman Holyaka, Roman Vynarovych, Pavlo Denysyuk

    This paper examines the structure and functional capabilities of the programmable embedded system for adaptive acoustics parameter research – AMES (Acoustic Measurement Embedded System). The core implementation platform is the PSoC 5 LP programmable system-on-chip, which provides extensive software control over acoustic parameter measurement processes. A mixed-signal conversion method based on selective charge amplification is proposed, enhancing noise immunity and measurement accuracy. The study analyzes modern approaches to adaptive acoustics and identifies key development trends in the context of automated design. The obtained results demonstrate the efficiency of the proposed system for studying the acoustic characteristics of enclosed spaces.


  • HYBRID APPROACH TO TRAFFIC SIGN RECOGNITION BASED ON COLOR SEGMENTATION AND CONVOLUTIONAL NEURAL NETWORKS

    by Lviv Polytechnic National University, Maksym Leshchuk, Mykhaylo Melnyk, Wojciech Zabierowski

    This paper presents a hybrid approach to traffic sign recognition that combines classical preprocessing techniques (color segmentation, contour detection, Haar Cascade, and HOG) with a lightweight Convolutional Neural Network (CNN) for classification. The proposed method reduces the amount of processed image data by a factor of 10–20, as only preselected regions of interest are passed to the neural network. The CNN, trained on the GTSRB dataset with data augmentation, achieved 100% accuracy on the test set, with precision and recall values ranging from 0.97 to 1.00 across individual classes. Compared to direct full-image classification using CNN alone, the hybrid pipeline ensured over 5× faster inference, making it suitable for real-time deployment on embedded platforms such as Raspberry Pi or mobile robotic systems. The practical significance of this work lies in its applicability to low-cost ADAS solutions and autonomous transport platforms. Future research directions include integration with real-time video streams and expansion to a wider range of traffic sign categories.

  • Information System for Determining Noise Level on Selected Streets of Lviv

    by Lviv Polytechnic National University, Mykhaylo Melnyk, Andriy Kernytskyy, Roman Vynarovych, Mykhailo Shvarts, Ivan Popovych

    This paper presents the outcomes of an experimental investigation into the equivalent noise levels of selected streets in Lviv according to varying times of day. Empirical mathematical models, formulated from the experimental data, provide a method to predict noise levels based on the time of day. In addition, the study includes the development of an information system. This system allows analysis of the changes in equivalent noise levels attributable to traffic flows at different times of day. Importantly, this tool can aid in the calculation of necessary noise insulation requirements for buildings adjacent to these traffic flows.

  • Mathematical Model for Attenuated Infrasound Wave Propagation

    by Mykhaylo Melnyk, Yulian Salo, Anna Timofiejczuk, Wojciech Sitek, Ivan Popovych, Roman Vynarovych

    The paper presents a comprehensive mathematical model for simulating the propagation and attenuation of infrasound waves within the atmosphere. This framework leverages a modular approach, integrating atmospheric, infrasound attenuation, and infrasound waveform propagation models.


  • DESIGNING A MOBILE FIELD HOSPITAL OF A MODULAR TYPE

    by Lviv Polytechnic National University, Pavlo Denysyuk, Mykhaylo Melnyk, Vitalii Dyshchakivskyi

    The article analyzes the main designs of mobile hospitals and classifies them according to their functional purpose. Basic three-dimensional models have been developed and proposed, with their maintenance features described. Typical dimensions of mobile field hospital structures have been determined. The results of modeling in the Autodesk CFD environment are presented.

  • PREDICTION OF THE OCCURRENCE OF STROKE BASED ON MACHINE LEARNING MODELS

    by Lviv Polytechnic National University, Yurii Patereha, Mykhaylo Melnyk

    The research conducted in the medical domain addressed a topic of significant importance, steadily growing in relevance each year. The study focused on predicting the onset of strokes, a condition posing a grave risk to individuals' health and lives. Utilizing a highly imbalanced dataset posed a challenge in developing machine learning models capable of effectively predicting stroke occurrences. Among the models examined, the Random Forest model demonstrated the most promising performance, achieving precision, recall, and F1-score metrics of 90%. These findings hold potential utility for healthcare professionals involved in stroke diagnosis and treatment.


  • IMPROVING THE NAVIGATION SYSTEM OF UNDERGROUND PIPE DEFECT DETECTION DEVICE

    by Lviv Polytechnic National University, Mykhaylo Melnyk, Roman Vynarovych, Yurii Hasiuk, Mykhaylo Shvarts

    This article addresses the issue of noise and drift in microelectromechanical gyroscopes and their impact on measurement accuracy in engineering applications. The use of a complementary filter is proposed to combine information from the accelerometer and gyroscope to reduce inaccuracies. Research shows that the accelerometer has better result repeatability, which is important for obtaining stable measurements. At the same time, the gyroscope may be more effective in measuring translational movements. The selection of sensor sensitivities and proper parameter tuning are crucial aspects. A developed system is capable of effectively filtering and measuring the angle of an object, and the use of a complementary filter improves measurement accuracy. The proposed approach can be successfully utilized for accurately detecting the angle of position of a measurement setup in defect inspection of underground pipelines.