2022 - Repozytorium publikacji - Politechnika Gdańska

Pokaż publikacje z roku

Publikacje z roku 2022

Pokaż wszystkie

Multiplicative Long Short-Term Memory with Improved Mayfly Optimization for LULC Classification
- Andrzej Stateczny
- Shanthi Mandekolu Bolugallu
- Parameshachari Bidare Divakarachari
- Kavithaa Ganesan
- Jamuna Rani Muthu
2022 Pełny tekst Remote Sensing
Land Use and Land Cover (LULC) monitoring is crucial for global transformation, sustainable land control, urban planning, urban growth prediction, and the establishment of climate regulations for long-term development. Remote sensing images have become increasingly important in many environmental planning and land use surveys in recent times. LULC is evaluated in this research using the Sat 4, Sat 6, and Eurosat datasets. Various spectral feature bands are involved, but unexpectedly little consideration has been given to these characteristics in deep learning models. Due to the wide availability of RGB models in computer vision, this research mainly utilized RGB bands. Once the pre-processing is carried out for the images of the selected dataset, the hybrid feature extraction is performed using Haralick texture features, an oriented gradient histogram, a local Gabor binary pattern histogram sequence, and Harris Corner Detection to extract features from the images. After that, the Improved Mayfly Optimization (IMO) method is used to choose the optimal features. IMO-based feature selection algorithms have several advantages that include features such as a high learning rate and computational efficiency. After obtaining the optimal feature selection, the LULC classes are classified using a multi-class classifier known as the Multiplicative Long Short-Term Memory (mLSTM) network. The main functionality of the multiplicative LSTM classifier is to recall appropriate information for a comprehensive duration. In order to accomplish an improved result in LULC classification, a higher amount of remote sensing data should be processed. So, the simulation outcomes demonstrated that the proposed IMO-mLSTM efficiently classifies the LULC classes in terms of classification accuracy, recall, and precision. When compared with ConvNet and Alexnet, the proposed IMO-mLSTM method accomplished accuracies of 99.99% on Sat 4, 99.98% on Sat 6, and 98.52% on the Eurosat datasets.
Multispectral Imaging Using Fluorescent Properties of Indocyanine Green and Methylene Blue in Colorectal Surgery—Initial Experience
- Wojciech Polom
- Marcin Migaczewski
- Jaroslaw Skokowski
- Maciej Swierblewski
- Tomasz Cwalinski
- Leszek Kalinowski
- Michal Pedziwiatr
- Marcin Matuszewski
- Karol Polom
2022 Pełny tekst Journal of Clinical Medicine
Introduction: Image-guided surgery is becoming a new tool in colorectal surgery. Intraoperative visualisation of different structures using fluorophores helps during various steps of operations. In our report, we used two fluorophores—indocyanine green (ICG), and methylene blue (MB)— during different steps of colorectal surgery, using one camera system for two separate near-infrared wavelengths. Material and methods: Twelve patients who underwent complex open or laparoscopic colorectal surgeries were enrolled. Intravenous injections of MB and ICG at different time points were administered. Visualisation of intraoperative ureter position and fluorescent angiography for optimal anastomosis was performed. A retrospective analysis of patients treated in our departments during 2020 was performed, and data about ureter injury and anastomotic site complications were collected. Results: Intraoperative localisation of ureters with MB under fluorescent light was possible in 11 patients. The mean signal-to-background ratio was 1.58 0.71. Fluorescent angiography before performing anastomosis using ICG was successful in all 12 patients, and none required a change in position of the planned colon resection for anastomosis. The median signal-to-background ratios was 1.25 (IQR: 1.22–1.89). Across both centres, iatrogenic injury of the ureter was found in 0.4% of cases, and complications associated with anastomosis was found in 5.5% of cases. Conclusions: Our study showed a substantial opportunity for using two different fluorophores in colorectal surgery, whereby the visualisation of one will not change the possible quantification analysis of the other. Using two separate dyes during one procedure may help in optimisation of the fluorescent properties of both dyes when using them for different applications. Visualisation of different structures by different fluorophores seems to be the future of image-guided surgery, and shows progress in optical technologies used in image-guided surgery.
Multi-task Video Enhancement for Dental Interventions
- Efkleidis Katsaros
- Piotr Kopa Ostrowski
- Krzysztof Włódarczak
- Emilia Lewandowska
- Jacek Rumiński
- Damian Siupka-Mróz
- Łukasz Lassmann
- Anna Jezierska
- Daniel Węsierski
2022
A microcamera firmly attached to a dental handpiece allows dentists to continuously monitor the progress of conservative dental procedures. Video enhancement in video-assisted dental interventions alleviates low-light, noise, blur, and camera handshakes that collectively degrade visual comfort. To this end, we introduce a novel deep network for multi-task video enhancement that enables macro-visualization of dental scenes. In particular, the proposed network jointly leverages video restoration and temporal alignment in a multi-scale manner for effective video enhancement. Our experiments on videos of natural teeth in phantom scenes demonstrate that the proposed network achieves state-of-the-art results in multiple tasks with near real-time processing. We release Vident-lab at https://doi.org/10.34808/1jby-ay90, the first dataset of dental videos with multi-task labels to facilitate further research in relevant video processing applications.
Multi-Temporal Analysis of Changes of the Southern Part of the Baltic Sea Coast Using Aerial Remote Sensing Data
- Krystyna Michałowska
- Ewa Głowienka
2022 Pełny tekst Remote Sensing
Understanding processes that affect changes in the coastal zone and the ability to predict these processes in the future depends on the period for which detailed monitoring is carried out and on the type of coast. This paper analyzes a southern fragment of the Baltic coast (30 km), where there has been no anthropogenic impact (Slowinski National Park). The study was carried out covering a time interval of 65 years. Historic and current aerial photographs (orthophotomaps) from the following years: 1951, 1964, 1975, 1984, 1995, 2004, and 2016 were used. Changes in the position of the foredune toe line (FTL) in each years’ images were used. For each time interval (1951–1964, 1964–1975, 1975–1984, 1984–1995, 1995–2004, 2004–2016), the coastal area over which morphodynamic processes (erosion and accumulation) took place was calculated. The calculated RL (reference line)—FTL positions allowed us to determine differences in the shoreline course in subsequent years and to determine the extent of shifts/changes of the coastline in each time period. The study results showed an equilibrium between the processes of accumulation and erosion, proving that the development of the studied natural coastline is balanced. There was only a change in the trend of the characteristics of changes from erosive into accumulative ones and vice versa. Moreover, along the studied coast section, a certain periodicity in the coastline changes can be observed. The intervals where predominant erosion occurs alternate with those when accumulation prevails, and then the cycle repeats. The analysis of historic/current aerial images and orthophotomaps from 1951–2016 indicated that strong storms have a significant impact on the magnitude of change (accumulation/erosion) and the formation of the studied coastline.
Multivariate Statistical Analysis for Mutual Dependence Assessment of Selected Polyphenols, Organic Acids and Metals in Cool-Climate Wines
- Magdalena Fabjanowicz
- Vasil Simeonov
- Marcin Frankowski
- Wojciech Wojnowski
- Justyna Płotka-Wasylka
2022 Pełny tekst MOLECULES
Polyphenols, organic acids and metal ions are an important group of compounds that affect the human health and quality of food and beverage products, including wines. It is known that a specific correlation between these groups exist. While wines coming from the New World and the Old World countries are extensively studied, wines coming from cool-climate countries are rarely discussed in the literature. One of the goals of this study was to determine the elemental composition of the wine samples, which later on, together as polyphenols and organic acids content, was used as input data for chemometric analysis. The multivariate statistical approach was applied in order to find specific correlations between the selected group of compounds in the cool-climate wines and the features that distinguish the most and differ between red and white wines and rosé wines. Moreover, special attention was paid to resveratrol and its correlation with selected wine constituents.
Muramyl dipeptide-based analogs as potential anticancer compounds: Strategies to improve selectivity, biocompatibility, and efficiency
- Eliza Iwicka
- Justyna Hajtuch
- Krystyna Dzierzbicka
- Iwona Inkielewicz-Stępniak
2022 Pełny tekst Frontiers in Oncology
According to the WHO, cancer is the second leading cause of death in the world. This is an important global problem and a major challenge for researchers who have been trying to find an effective anticancer therapy. A large number of newly discovered compounds do not exert selective cytotoxic activity against tumorigenic cells and have too many side effects. Therefore, research on muramyl dipeptide (MDP) analogs has attracted interest due to the urgency for finding more efficient and safe treatments for oncological patients. MDP is a ligand of the cytosolic nucleotide-binding oligomerization domain 2 receptor (NOD2). This molecule is basic structural unit that is responsible for the immune activity of peptidoglycans and exhibits many features that are important for modern medicine. NOD2 is a component of the innate immune system and represents a promising target for enhancing the innate immune response as well as the immune response against cancer cells. For this reason, MDP and its analogs have been widely used for many years not only in the treatment of immunodeficiency diseases but also as adjuvants to support improved vaccine delivery, including for cancer treatment. Unfortunately, in most cases, both the MDP molecule and its synthesized analogs prove to be too pyrogenic and cause serious side effects during their use, which consequently exclude them from direct clinical application. Therefore, intensive research is underway to find analogs of the MDP molecule that will have better biocompatibility and greater effectiveness as anticancer agents and for adjuvant therapy. In this paper, we review the MDP analogs discovered in the last 10 years that show promise for antitumor therapy. The first part of the paper compiles the achievements in the field of anticancer vaccine adjuvant research, which is followed by a description of MDP analogs that exhibit promising anticancer and antiproliferative activity and their structural changes compared to the original MDP molecule.
Musical Instrument Identification Using Deep Learning Approach
- Maciej Blaszke
- Bożena Kostek
2022 Pełny tekst SENSORS
The work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata description and a review of related works. This is followed by showing the dataset prepared for the experiment and its division into subsets: training, validation, and evaluation. Then, the analyzed architecture of the neural network model is presented. Based on the described model, training is performed, and several quality metrics are determined for the training and validation sets. The results of the evaluation of the trained network on a separate set are shown. Detailed values for precision, recall, and the number of true and false positive and negative detections are presented. The model efficiency is high, with the metric values ranging from 0.86 for the guitar to 0.99 for drums. Finally, a discussion and a summary of the results obtained follows.
Mussel‐inspired biomaterials: From chemistry to clinic
- Ali Taghizadeh
- Mohsen Taghizadeh
- Mohsen Khodadadi Yazdi
- Payam Zarrintaj
- Joshua D. Ramsey
- Farzad Seidi
- Florian J. Stadler
- Haeshin Lee
- Mohammad Saeb
- Masoud Mozafari
2022 Pełny tekst Bioengineering & Translational Medicine
After several billions of years, nature still makes decisions on its own to identify, develop, and direct the most effective material for phenomena/challenges faced. Likewise, and inspired by the nature, we learned how to take steps in developing new technologies and materials innovations. Wet and strong adhesion by Mytilidae mussels (among which Mytilus edulis—blue mussel and Mytilus californianus—California mussel are the most well-known species) has been an inspiration in developing advanced adhesives for the moist condition. The wet adhesion phenomenon is significant in designing tissue adhesives and surgical sealants. However, a deep understanding of engaged chemical moieties, microenvironmental conditions of secreted proteins, and other contributing mechanisms for outstanding wet adhesion mussels are essential for the optimal design of wet glues. In this review, all aspects of wet adhesion of Mytilidae mussels, as well as different strategies needed for designing and fabricating wet adhesives are discussed from a chemistry point of view. Developed muscle-inspired chemistry is a versatile technique when designing not only wet adhesive, but also, in several more applications, especially in the bioengineering area. The applications of muscle-inspired biomaterials in various medical applications are summarized for future developments in the field.
Nanocząstki w chemioterapii: charakterystyka, strategie projektowania, mechanizm wnikania oraz degradacja wewnątrzkomórkowa
- Joanna Pilch
2022 Pełny tekst Postępy Biochemii
Pomimo znaczącego postępu w leczeniu nowotworów skuteczne metody ich leczenia po-zostają ograniczone. Wciąż jedną z głównych metod terapii pozostaje chemioterapia, jednakże często wywołuje ona wiele efektów ubocznych. Związane jest to m. in. z brakiem istotnych różnic pomiędzy komórkami nowotworowymi a prawidłowymi, właściwościami fizykochemicznymi samych chemioterapeutyków, a także zjawiskiem lekooporności. W celu obniżenia działań niepożądanych oraz podniesienia specyficzności chemioterapeuty-ków względem komórek nowotworowych poszukiwane są nowe metody ich dostarczania do komórek guza. Jedną z nich jest zastosowanie nanocząstek (ang. Nanoparticles, NPs) jako platform transportujących. W niniejszym artykule przedstawiono charakterystykę NPs po-siadających zastosowanie w chemioterapii m. in.: kropek kwantowych, nanocząstek złota, dendrymerów, miceli oraz liposomów. Omówiono także strategię w projektowaniu i opty-malizacji syntezy nanocząstek oraz oceny różnych mechanizmów ich wnikania do komórek, jak również ich degradację wewnątrzkomórkową oraz toksyczność.
Nanomaterials for photothermal and photodynamic cancer therapy
- Behzad Nasseri
- Effat Alizadeh
- Farhad Bani
- Soodabeh Davaran
- Abolfazl Akbarzadeh
- Navid Rabiee
- Ali Bahadori
- Mojtaba Ziaei
- Mojtaba Bagherzadeh
- Mohammad Saeb
- Masoud Mozafari
- Michael R. Hamblin
2022 Applied Physics Reviews
In recent years, the role of optically sensitive nanomaterials has become powerful moieties in therapeutic techniques and has become particularly emphasized. Currently, by the extraordinary development of nanomaterials in different fields of medicine, they have found new applications. Phototherapy modalities, such as photothermal therapy (PTT) by toxic heat generation and photodynamic therapy (PDT) by reactive oxygen species, are known as promising phototherapeutic techniques, which can overcome the limitations of conventional protocols. Moreover, nanomaterial-based PDT and PTT match the simultaneous immune therapy and increase the immune system stimulation resulting from the denaturation of cancer cells. Nevertheless, nanomaterials should have sufficient biocompatibility and efficiency to meet PDT and PTT requirements as therapeutic agents. The present review focuses on the therapeutic potency of PDT, PTT, and also their combined modalities, which are known alternative protocols with minimal morbidity integrated into gold standard treatments such as surgery, chemotherapy, and radiation therapy at tumor treatment and cancer-related infectious diseases. In addition, for deeper understanding, photoablation effects with emphasis on the nature, morphology, and size of photosensitive nanomaterials in PDT and PTT were studied. Finally, transportation techniques and moieties needed as carriers of photosensitizers and photothermal therapy agents to hard-accessed regions, for example, cancerous regions, were investigated
Nanosorbents as Materials for Extraction Processes of Environmental Contaminants and Others
- María José Santoyo Treviño
- Sergio Zarazúa
- Justyna Płotka-Wasylka
2022 Pełny tekst MOLECULES
The aim of this work focuses on the application of nanomaterials (NMs) in different sorp- tive extraction techniques for the analysis of organic contaminants from environmental samples of distinct matrix compositions. Without any doubt, the integration of specific NMs such as carbona- ceous nanomaterials, magnetic nanoparticles (MNPs), metal–organic frameworks (MOFs), silica na- noparticles, and ion-imprinted NPs with so lid-phase extraction techniques counting d-SPE, solid- phase microextraction (SPME), and stir bar sorptive extraction (SBSE) impact on the improvements in analytical performance. The application of NMs assorbents in the extraction of organic pollutants in environmental samples allows for providing better sensitivity, repeatability, reproducibility, and reusability.
Nanostructure of the laser-modified transition metal nanocomposites for water splitting
- Jakub Wawrzyniak
- Jakub Karczewski
- Emerson Coy
- Jacek Ryl
- Katarzyna Grochowska
- Siuzdak Katarzyna
2022 Pełny tekst NANOTECHNOLOGY
Although hydrogen is considered by many to be the green fuel of the future, nowadays it is primarily produced through steam reforming, which is a process far from ecological. Therefore, emphasis is being put on the development of electrodes capable of the efficient production of hydrogen and oxygen from water. To make the green alternative possible, the solution should be cost-efficient and well processable, generating less waste which is a huge challenge. In this work, the laser-based modification technique of the titania nanotubes containing sputtered transition metal species (Fe, Co, Ni, and Cu) was employed. The characteristics of the electrodes are provided both for the hydrogen and oxygen evolution reactions, where the influence of the laser treatment has been found to have the opposite effect. The structural and chemical analysis of the substrate material provides insight into pathways towards more efficient, low-temperature water splitting. Laser-assisted integration of transition metal with the tubular nanostructure results in the match-like structure where the metal species are accumulated at the head. The electrochemical data indicates a significant decrease in material resistance that leads to an overpotential of only +0.69 V at 10 mA/cm2 for nickel-modified material.
Natural fish oil improves the differentiation and maturation of oligodendrocyte precursor cells to oligodendrocytes in vitro after interaction with the blood–brain barrier
- Paweł Piatek
- Natalia Lewkowicz
- Sylwia Michlewska
- Marek Wieczorek
- Radosław Bonikowski
- Karol Parchem
- Przemysław Lewkowicz
- Magdalena Namiecinska
2022 Pełny tekst Frontiers in Immunology
The blood–brain barrier (BBB) tightly controls the microenvironment of the central nervous system (CNS) to allow neurons to function properly. Additionally, emerging studies point to the beneficial effect of natural oils affecting a wide variety of physiological and pathological processes in the human body. In this study, using an in vitro model of the BBB, we tested the influence of natural fish oil mixture (FOM) vs. borage oil (BO), both rich in longchain polyunsaturated fatty acids (LC-PUFAs) and monounsaturated fatty acids (MUFAs) such as oleic acid (C18:1n9c) or nervonic acid (NA), on human oligodendrocyte precursor cells (hOPCs) during their maturation to oligodendrocytes (OLs) regarding their ability to synthesize myelin peptides and NA. We demonstrated that FOM, opposite to BO, supplemented endothelial cells (ECs) and astrocytes forming the BBB, affecting the function of hOPCs during their maturation. This resulted in improved synthesis of myelin basic protein (MBP), myelin oligodendrocyte glycoprotein (MOG), proteolipid protein (PLP), and NA in mature OLs. This effect is probably the result of BBB cell and hOPC stimulation via free fatty acid receptors (FFARs), which increases insulin growth factor-1 (IGF-1), ciliary neurotrophic factor (CNTF), and brainderived neurotrophic factor (BDNF) and inhibits fibroblast growth factor 2 (FGF-2) synthesis. The unique formula of fish oil, characterized by much more varied components compared to those of BOs, also improved the enhancement of the tight junction by increasing the expression of claudin-5 and VE-cadherin on ECs. The obtained data justify consideration of naturally derived fish oil intake in human diet as affecting during remyelination.
Natural sweeteners: Sources, extraction and current uses in foods and food industries
- Roberto Castro-Muñoz
- Mariela Correa-Delgado
- Rafael Córdova-Almeida
- David Lara-Nava
- Mariana Chávez-Muñoz
- Valeria Fernanda Velásquez-Chávez
- Carlos Eduardo Hernández-Torres
- Emilia Gontarek-Castro
- Mohd Zamidi Ahmad
2022 Pełny tekst FOOD CHEMISTRY
Food producers have leaned towards alternative natural and synthetic sweeteners in food formulations to satisfy market demands. Even so, several synthetic sweeteners (e.g., aspartame, saccharin, sucralose) are becoming less popular due to health-related concerns, lower nutritional values, and controversies around their safety. Conversely, natural sweeteners confer favourable customer perceptions due to their association to a healthier lifestyle and higher nutritional values. This article discusses the evidence of natural sweeteners in the available commercial products. A comprehensive review of natural sweeteners is presented, which includes their resources, properties and extraction methods, as well as a discussion on several emerging technologies that offer improvements to the traditional extraction methods. Finally, the progress of natural sweeteners in the food industry is assessed, and the commercial food products containing these natural sweeteners are mentioned.
Nauka w świecie cyfrowym okiem młodego inżyniera - jakość życia a jakość powietrza w miastach
- Bartosz Pingot
- Przemysław Falkowski-Gilski
2022 Pismo PG
Obecne w powietrzu zanieczyszczenia biorą udział w procesach zmian klimatycznych, a także bezpośrednio wpływają na ludzkie zdrowie, przejawiając toksyczność w wyższych stężeniach oraz zwiększając ryzyko występowania szerokiej gamy chorób. Jest to szczególnie niebezpieczne dla mieszkańców dużych miast oraz tych znajdujących się w grupach ryzyka. Dlatego też bardzo ważna pozostaje kwestia monitorowania stanu zanieczyszczenia powietrza w miastach.
Nauka w świecie cyfrowym okiem młodego inżyniera - początki techniki wirtualnej rzeczywistości
- Karol Fidurski
- Przemysław Falkowski-Gilski
2022 Pismo PG
Istnieje wiele definicji wirtualnej rzeczywistości (VR – Virtual Reality), które mniej lub bardziej pokrywają się ze sobą w różnych obszarach naukowych. Obecnie, gdy używamy określenia „VR”, odnosi się ono konkretnie do obrazów generowanych komputerowo, które zostały specjalnie zaprojektowane tak, aby dostarczyć jak najbardziej immersyjnych wrażeń. Sporo opracowań mówi również, że VR musi być interaktywna. To odróżniałoby ją od takich rozwiązań jak filmy 3D, wideo 360 itp.
Negative Poisson’s ratio from pentagons: A new auxetic structure combining three different auxetic mechanisms
- Szymon Winczewski
- Jarosław Rybicki
2022 COMPUTATIONAL MATERIALS SCIENCE
A novel class of two-dimensional auxetic structures based on the pentagon motif is proposed. Their mechanical properties are investigated by combining molecular mechanics simulations with a simple three-parameter mechanical model which assumes perfectly elastic behavior. It is predicted that the proposed structures – termed as double re-entrant honeycomb – may possess unique mechanical characteristics, which include complete and perfect auxeticity, as well as the negative Poisson’s ratio observed in both the tensile and compressive regimes. The behavior of the considered structures is explained in relation to well-known auxetic models. It is shown that the considered structures simultaneously implement three different mechanisms leading to a negative Poisson’s ratio: the opening of the re-entrant units, the rotation of the squares, and the flattening effect.
Negative result about the construction of genuinely entangled subspaces from unextendible product bases
- Maciej Demianowicz
2022 Pełny tekst PHYSICAL REVIEW A
Unextendible product bases (UPBs) provide a versatile tool with various applications across different areas of quantum information theory. Their comprehensive characterization is thus of great importance and has been a subject of vital interest for over two decades now. An open question asks about the existence of UPBs, which are genuinely unextendible, i.e., they are not extendible even with biproduct vectors. In other words, the problem is to verify whether there exist genuinely entangled subspaces (GESs), subspaces composed solely of genuinely multiparty entangled states, complementary to UPBs. We solve this problem in the negative for many sizes of UPBs in different multipartite scenarios. In particular, in the all-important case of equal local dimensions, we show that there are always forbidden cardinalities for such UPBs, including the minimal ones corresponding to GESs of the maximal dimensions.
Neural Approximators for Variable-Order Fractional Calculus Operators (VO-FC)
- Bartosz Puchalski
2022 Pełny tekst IEEE Access
The paper presents research on the approximation of variable-order fractional operators by recurrent neural networks. The research focuses on two basic variable-order fractional operators, i.e., integrator and differentiator. The study includes variations of the order of each fractional operator. The recurrent neural network architecture based on GRU (Gated Recurrent Unit) cells functioned as a neural approximation for selected fractional operators. The paper investigates the impact of the number of neurons in the hidden layer, treated as a hyperparameter, on the quality of modeling error. Training of the established recurrent neural network was performed on synthetic data sets. Data for training was prepared based on the modified Grünwald-Letnikow definition of variable-order fractional operators suitable for numerical computing without memory effects. The research presented in this paper showed that recurrent network architecture based on GRU-type cells can satisfactorily approximate targeted simple yet functional variable-order fractional operators with minor modeling errors. The presented solution is a novel approach to the approximation of VO-FC operators. It has the advantage of automatic selection of neural approximator parameters by optimization based on data customized for specific requirements.
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
- Krzysztof Laddach
- Rafał Łangowski
2022
A problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and developing original specialised evolutionary operators. This resulted in a compromise between the size of neural network and its accuracy in capturing the response of the mathematical model under which it has been learnt. The research involved an extended validation study based on data generated from a mathematical model of an exemplary system as well as the fast processes occurring in a pressurised water nuclear reactor. The obtaining simulation results demonstrate the high effectiveness of the devised neural (black-box) models of dynamic systems with time delays.