Bohdan Derysh

Bohdan Derysh

Auto-generated profile, based on publicly available information

Bohdan Derysh

West Ukrainian National University, Ukraine

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 January 2023 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
OBOleh Berezsky
Oleh Berezsky
OPOleh Pitsun
Oleh Pitsun
GMGrygoriy Melnyk
Grygoriy Melnyk
TDTamara Datsko
Tamara Datsko
Ivan IzoninIvan Izonin
Ivan Izonin
BDBohdan Derysh
Bohdan Derysh
The paper explored the problem of automatic diagnosis based on immunohistochemical image analysis. The issue of automated diagnosis is a preliminary and advisory statement for a diagnostician. The authors studied breast cancer histological and immunohistochemical images using the following biomarkers progesterone, estrogen, oncoprotein, and a cell proliferation biomarker. The authors developed a breast cancer diagnosis method based on immunohistochemical image analysis. The proposed method consists of algorithms for image preprocessing, segmentation, and the determination of informative indicators (relative area and intensity of cells) and an algorithm for determining the molecular genetic breast cancer subtype. An adaptive algorithm for image preprocessing was developed to improve the quality of the images. It includes median filtering and image brightness equalization techniques. In addition, the authors developed a software module part of the HIAMS software package based on the Java programming language and the OpenCV computer vision library. Four molecular genetic breast cancer subtypes could be identified using this solution: subtype Luminal A, subtype Luminal B, subtype HER2/neu amplified, and basalt-like subtype. The developed algorithm for the quantitative characteristics of the immunohistochemical images showed sufficient accuracy in determining the cancer subtype “Luminal A”. It was experimentally established that the relative area of the nuclei of cells covered with biomarkers of progesterone, estrogen, and oncoprotein was more than 85%. The given approach allows for automating and accelerating the process of diagnosis. Developed algorithms for calculating the quantitative characteristics of cells on immunohistochemical images can increase the accuracy of diagnosis.

14 September 2022
Verified
Book Chapter
Closed access
PDF file
OBOleh Berezsky
Oleh Berezsky
OPOleh Pitsun
Oleh Pitsun
PLPetro Liashchynskyi
Petro Liashchynskyi
BDBohdan Derysh
Bohdan Derysh
NBNatalia Batryn
Natalia Batryn

23 December 2020
Verified
Book Chapter
Closed access
PDF file
OBOleh Berezsky
Oleh Berezsky
OPOleh Pitsun
Oleh Pitsun
LDLesia Dubchak
Lesia Dubchak
KBKateryna Berezka
Kateryna Berezka
TDTaras Dolynyuk
Taras Dolynyuk
BDBohdan Derish
Bohdan Derish

30 September 2026 in Innovative technologies and scientific solutions for industries
Verified
Journal Article
Open access
PDF file
BDBohdan Derysh
Bohdan Derysh
LDLesia Dubchak
Lesia Dubchak
Carsten WolffCarsten Wolff
Carsten Wolff
RBRuslan Brukhanskyi
Ruslan Brukhanskyi
NVNadiia Vasylkiv
Nadiia Vasylkiv
Information-analytical assessment of daily operating modes of an industrial biogas plant using production records from a supervisory control and data acquisition system. Aim. To improve the validity of integrated operating-efficiency assessment by accounting for feedstock-specific physical properties, the time inertia of anaerobic digestion, and dependence between criteria. Objectives. To correct the source-data structure and record counts; substantiate the criterion system; replace an equal fresh-mass feedstock coefficient with a substrate-specific methane-potential model; introduce a process lag; determine adaptive weights and operating-mode classes; perform physics-based and temporal consistency checks, analyze dependencies between criteria, conduct sensitivity analysis, and formulate operational recommendations. Methods. Daily production-log preprocessing, literature-based biochemical methane-potential coefficients and scenario TS and VS/TS values, a fixed 10-day lag, min-max normalisation, Shannon entropy, the CRITIC method, quartile classification, correlation analysis, and one-at-a-time weight sensitivity analysis were applied. Results. The 2024 dataset contains 366 daily records; the 10-day forward lag leaves 356 observations for the integrated performance score. The estimated methane potential averaged 3904.83 Nm3/day. Its correlation with future electricity generation was 0.176 at a 10-day lag, while the maximum within 0–30 days occurred at 13 days (0.227). Final weights for , , , , and were 0.3207, 0.1746, 0.0197, 0.0909, and 0.3941, respectively. Mean IPS was 0.4682; for active modes and . The 356 lag-valid days comprised 51 high-efficiency, 102 typical, 51 low-efficiency, and 152 shutdown modes. Perturbing one final weight by ±10% changed mean by at most 1.234%. Conclusions. The model provides a reproducible decomposable assessment of daily operation, avoids treating equal fresh masses of different substrates as energetically equivalent, explicitly accounts for process inertia, and supports diagnosis of the dominant causes of reduced performance. Transfer of the numerical weights and thresholds to other plants requires independent external validation.

27 June 2026 in Innovative technologies and scientific solutions for industries
Verified
Journal Article
Open access
PDF file
LDLesia Dubchak
Lesia Dubchak
NVNazar Vivchar
Nazar Vivchar
OSOleg Savenko
Oleg Savenko
BDBohdan Derysh
Bohdan Derysh
OZOleg Zastavnyy
Oleg Zastavnyy
The subject of the study is methods and software tools for intelligent diagnostics of wind turbine blade defects based on neuro-fuzzy models capable of operating effectively in conditions of limited, fuzzy, or partially defined input data. The goal of the study is to develop a software implementation and conduct an experimental study of a neuro-fuzzy Wang–Mendel network for classifying wind turbine blade defects, and to justify its feasibility as the basis of an intelligent system for monitoring the technical condition of energy facilities. The main tasks are to analyze modern methods of defect classification, develop the architecture of a neuro-fuzzy model, create a software package for training and classification, implement an algorithm for automatically forming a fuzzy rule base, optimize the parameters of membership functions, and conduct experimental studies to assess the effectiveness of the proposed approach. The study used methods of fuzzy logic, neuro-fuzzy systems, mathematical modeling, data classification, parameter optimization, and software implementation of intelligent systems in Python using modern data processing and numerical computing libraries. The Wang–Mendel algorithm provides automatic formation of fuzzy rules based on training data and adaptation of model parameters to increase classification accuracy. As a result, an intelligent software complex for classifying wind turbine blade defects was developed, which provides effective data processing and decision-making based on fuzzy rules. Experimental studies were conducted on a training sample of 160 records and a test sample of 64 records, describing the probabilities of the presence of various types of defects. Conclusions: according to the training results, an accuracy of 91% was achieved on the training sample and 94% on the test sample with a low level of mean square error, which confirms the high efficiency, generalization ability, and practical suitability of the proposed model for use in intelligent systems for monitoring the technical condition of wind turbines in conditions of limited data and resources.