Nauki Techniczne

International Journal of Electronics and Telecommunications

Opis

International Journal of Electronics and Telecommunications (IJET, eISSN 2300-1933, untill 2013 also print ISSN 2081-8491) is a periodical of Electronics and Telecommunications Committee of Polish Academy of Sciences and it is published by Warsaw Science Publishers of PAS. It continues tradition of the Electronics and Telecommunications Quarterly (ISSN 0867-6747) established in 1955 as the Rozprawy Elektrotechniczne. The IJET is a scientific periodical where papers present the results of original, theoretical, experimental and reviewed works. They consider widely recognized aspects of modern electronics, telecommunications, microelectronics, optoelectronics, radioelectronics and medical electronics.

The authors are outstanding scientists, well‐known experienced specialists as well as young researchers – mainly candidates for a doctor's degree. The papers present original approaches to problems, interesting research results, critical estimation of theories and methods, discuss current state or progress in a given branch of technology and describe development prospects. All the papers published in IJET are reviewed by international specialists who ensure that the publications are recognized as author's scientific output.

The printed periodical is distributed among all those who deal with electronics and telecommunications in national scientific centers as well as in numeral foreign institutions, and it is subscribed by many specialists and libraries. Its electronic version is available at http://ijet.pl.

The papers received are published within half a year if the cooperation between author and the editorial staff is efficient. The papers may be submitted to the editorial office by the journal web page http://ijet.pl.

Journal Metrics:

IMPACT FACTOR 2024: 0.7

CiteScore metrics from Scopus 2024: 1.6

SCImago Journal Rank (SJR) 2024: 0.217

Source Normalized Impact per Paper (SNIP) 2024: 0.452

Citation Indicator (JCI) 2024: 0.14

ISSN

eISSN 2300-1933 (since 2013), ISSN 2081-8491 (until 2012)

Wydawcy

Polish Academy of Sciences Committee of Electronics and Telecommunications

Editor-in-Chief
Ryszard S. Romaniuk, Warsaw University of Technology, Institute of Electronic Systems, Poland

Managing Editor
Danuta Sobczak-Bartosiewicz, Warsaw University of Technology, Poland

Technical Editors
Maciej Linczuk, Warsaw University of Technology, Institute of Electronic Systems, Poland

Secretary in-Charge
Danuta Ojrzenska-Wojter, Warsaw University of Technology, Institute of Telecommunications, Poland

Administrative Assistant
Danuta Sobczak-Bartosiewicz, Warsaw University of Technology, Poland

Editorial Advisory Board
Prof. Victor-Valeriu Patriciu, Director Doctoral School of Electronics, Informatics and Communications for Defense and Security, Military Technical Academy Bucharest, Romania, Romania

Prof. Bart Scheers, Royal Military Academy, Belgium

Dr. Eli Winjum, Norwegian Defence Research Establishment, Norway

Wladyslaw Skarbek, Warsaw University of Technology, IRE, Poland

Christian Napoli, University of Catania, Italy

Rosario Giunta, University of Catania, Italy

Christopher Chiu, University of Technology Sydney, Australia

Prof. Emiliano Tramontana, University of Catania, Italy

Prof Robin Braun, University of Technology Sydney, Australia

Dr David Davis, University of Technology Sydney, Australia

dr Brian Culshaw, University of Strathclyde, UK, United Kingdom

Grzegorz Chmaj, University of Nevada, United States

Giuseppe Pappalardo, University of Catania, Italy

Michael Affenzeller, University of Applied Sciences Upper Austria

Prof. Stavros Hatzopoulos, Laboratory of Hearing Science Audiology Dept., University of Ferrara, Italy, Italy

Prof Nikita M Ryskin, Saratov State University, Russian Federation

Prof. Adam Wolisz, Technische Universität Berlin, Department of Electrical Engineering and Computer Science Telecommunication Networks

Prof. Edmundo Monteiro, Departamento de Engenharia Informatica Universidade de Coimbra Portugal, Portugal

Prof. Zoubir Mammeri, IRIT, Université Paul Sabatier 118 Route de Narbonne F-31062 Toulouse Cedex 9 FRANCE, France

Dr Paul D Polishuk, IGI, Boston, MA, USA

Giuseppe Macchiarella, Politecnico di Milano,Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Italy

Prof. Bernd Steinbach, Bergakademie Freiberg Fakultät für Mathematik und Informatik Institut, Germany

Jan Szmidt, Warsaw University of Technology, Poland

Zenon Chaczko, University of Technology Sydney, Australia

Józef Modelski, Warsaw University of Technology, Poland

Wiesław Woliński, Warsaw University of Technology, Poland

Ryszard Klempous, Wroclaw University of Technology, Poland

Radomir Stanković, University of Niš, Serbia

Javier Poncela, University of Malaga, Spain

Marek Turowski, CFD Research Corporation, United States

Dawid Zydek, NV Energy, United States

Wojciech Szpankowski, Purdue University, United States

Jacek Żurada, University of Louisville, United States

Tadeusz Luba, Warsaw University of Technology, Poland

Stefan Hahn, Warsaw University of Technology, Poland

Gilbert De Mey, Ghent University, Belgium

Svetlana Yanushkevich, University of Calgary, Canada

Viktor Krozer, Technical University of Denmark, Denmark

Adam Morawiec, European Electronic Chips & Systems Design Initiative, France

Herman Rohling, Technical University of Hamburg, Germany

Franco Davoli, University of Genowa, Italy

Michał Mrozowski, Gdańsk University of Technology, Poland

Włodzimierz Janke, Koszalin University of Technology, Poland</

Principal Contact
Ryszard S. Romaniuk
Professor
Warsaw University of Technology, Institute of Electronic Systems, room 217, Nowowiejska 15/19, Warsaw 00-665, Poland
Phone: +48222345110
Fax: +48228252300
Email: ryszard.romaniuk@pw.edu.pl

Support Contact
Danuta Bartosiewicz
Email: danuta.bartosiewicz@pw.edu.pl

International Journal of Electronics and Telecommunications is an open access journal with all content available with no charge in full text version.

The journal content is available under the Creative Commons Attribution 4.0 International License (CC BY 4.0) https://creativecommons.org/licenses/by/4.0/.

Roczniki i numery
Instrukcja dla autorów

Wybierz numer

Zawartość

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1

1 Immersive recording of vocal ensemble on location – practical considerations and case study

Kaja Kosmenda , Witold Mickiewicz

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.155466

Słowa kluczowe: immersive sound immersive recording microphone techniques 3D microphone arrays recording techniques

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The dynamic development of spatial sound technology has led to a rapid movement from classic stereo and surround formats to immersive systems, including 7.1.4 and other Dolby Atmos configurations as a primary production format. As part of the project, a custom 3D microphone array was developed and built, inspired by contemporary research on techniques for recording three-dimensional acoustic space. The aim of the work was to obtain a realistic representation of space in the form of a true multi-channel recording while maintaining configuration flexibility and low construction costs. The recorded material was used to study various methods of reference recordings mixing for immersive loudspeaker configurations. Two approaches were analyzed: direct assignment of signals to 7.1.4 system channels and object-based rendering using Dolby Atmos Renderer within Pro Tools, allowing for dynamic positioning of sources in space. The results indicate that the channel-based approach regarding immersive mixing provides the best sound quality , while objectbased rendering offers greater creative flexibility and the possibility of reducing the number of microphones. Further research focuses on the development of binaural immersive listening methods using obtained audio and the creation of authentic 3D recordings for streaming platforms.

Przejdź do artykułu

Autorzy i Afiliacje

Kaja Kosmenda

Witold Mickiewicz

West Pomeranian University of Technology in Szczecin, Poland

2 Educational computer game supporting skills development in timbre solfege

Paulina Bielesz , Krzysztof Gawlas

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-5 | DOI: 10.24425/ijet.2026.157863

Słowa kluczowe: timbre solfege educational game formants sound spectrum sound engineering technical ear training

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents Sound Jobs, an educational computer game designed to develop timbre solfege skills for sound engineers and audio professionals. Unlike existing eartraining tools that operate as standalone applications or webbased services, Sound Jobs integrates listening exercises within an engaging game narrative set in the 1970s hacking culture. The system was developed using the Unity game engine integrated with FMOD Studio middleware, enabling precise control over audio signal processing parameters essential for timbre discrimination tasks. The game offers three modes (Jobs, Training, and Testing) with exercises covering equalization recognition, dynamic range discrimination, distortion detection, reverb characterization, and delay identification. Evaluation through user surveys with Music in Multimedia students and professional audio engineers revealed positive reception, with participants particularly appreciating the gamification approach and the progressive difficulty system. Based on feedback, a second version was developed incorporating game save functionality and interface improvements. The tool is currently employed in timbre solfege instruction at the University of Silesia. Future development plans include expanding the sound material library and establishing a public repository for broader accessibility.

Przejdź do artykułu

Autorzy i Afiliacje

Paulina Bielesz

Krzysztof Gawlas

University of Silesia, Poland
Institute of Music, University of Silesia, Cieszyn, Poland

3 Using Vowel Characteristics for Multi-channel Signal Decorrelation and Reverberation

Michele Pizzi , Bartłomiej Mróz

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157864

Słowa kluczowe: audio decorrelation multi-channel reverberation linear predictive coding timbre control spatial audio vowel synthesis

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents a novel audio decorrelation method that integrates velvet noise with parametric modeling of vowel filters derived from recorded speech. By capturing vocal timbre, the technique extends decorrelation and artificial reverberation tools, offering new creative possibilities. Velvet noise is filtered to model vowel resonances, enabling users to imprint speech or singing characteristics onto multichannel effects. Inspired by choir acoustics, the system synthesizes distinct vowels per channel, producing speech-like textures that are convolved with input audio. The approach emphasizes immersive, voice inspired sound design, with discussion of implementation challenges, creative applications, listening tests, and directions for future research.

Przejdź do artykułu

Autorzy i Afiliacje

Michele Pizzi

Bartłomiej Mróz

Independent Researcher
Department of Multimedia Systems, Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, Poland

4 Acoustic analysis of selected homographs for speech recognition systems

Dominik Lentas , Michał Łuczyński

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157865

Słowa kluczowe: homographs speech signal machine learning MFCC SVM

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents an acoustic analysis of selected homographs in the context of automatic speech recognition (ASR) systems. The study focuses on the Polish words “Dania” (eng. Denmark) and “dania” (eng. meals), which, despite identical spelling, differ subtly in pronunciation. These differences pose challenges for ASR systems, especially when context is unavailable.

The methodology includes spectrograms analysis MFCC (Mel-Frequency Cepstral Coefficients) extraction, and classification using a Support Vector Machine (SVM) algorithm. A custom audio database was created using recordings from ten speakers, followed by manual segmentation and normalization of samples. Spectrograms and formant trajectories were analyzed to identify phonetic distinctions, particularly the presence of the semi-vowel [j] in “Dania”.

A subjective listening test involving 27 participants was conducted to assess human recognition accuracy. Results showed an average recognition rate of 58%, indicating significant ambiguity. In contrast, the machine learning model achieved up to 79% accuracy with randomly stratified data and 75% accuracy when tested on the same samples used in the subjective test.

The findings suggest that MFCC-based classification combined with SVM is a promising approach for distinguishing homographs in speech, outperforming human listeners in controlled conditions. Limitations include the small dataset and variability in speaker articulation. The study highlights the importance of phonetic exception handling in ASR systems and proposes extending the method to other homographic pairs.

Przejdź do artykułu

Autorzy i Afiliacje

Dominik Lentas

Michał Łuczyński

Wroclaw University of Science and Technology, Poland

5 Analysis and categorization of the Rusyn language using the whisper model: demographic influences on linguistic convergence

Paweł Małecki

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157866

Słowa kluczowe: Artificial Neural Network ANN Automatic Speech Recognition ASR Rusyn Minority Languages Automatic Classification

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The article presents a detailed linguistic analysis of the Rusyn language, focusing on its complex and evolving features, such as pronunciation, as well as individual, regional, and historical variabilities. The investigation employed an artificial neural network based on the OpenAI Whisper model to perform analysis and categorization. Although the Whisper model was trained on data from the majority of state official languages, it was not specifically trained with samples of the Rusyn language due to its niche and minority/ethnic status. Consequently, speech samples in Rusyn were classified according to the most closely related available labels, allowing for the assessment of linguistic similarity between Rusyn and other (mostly) Slavic languages. The study incorporated a diverse user base segmented by gender, age, and geographic location (Poland, Ukraine, Slovakia, Serbia), revealing significant resemblances to the dominant languages within these countries and demonstrating correlations between the computed linguistic similarity and the speakers’ age.

Przejdź do artykułu

Autorzy i Afiliacje

Paweł Małecki

Faculty of Electrical Engineering and Communication, AGH University of Krakow, Krakow, Poland

6 Radar detection of high architectural objects in urban environments – an experimental study

Urszula Libal , Arkadiusz Byndas , Dawid Sysak , Tomasz Karaś

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157867

Słowa kluczowe: radar signal processing UAV situational awareness collision avoidance UAV obstacle avoidance target detection radar system X-band radar

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The increasing presence of unmanned aerial vehicles (UAVs) in urban airspace necessitates reliable detection and classification of tall architectural structures to ensure flight safety and effective collision avoidance. This paper presents an experimental study on radar detection of high-infrastructural objects, such as residential blocks, tall buildings, and similar structures, in a complex urban environment. Using a custom Xband radar system, real-world measurements were performed in a metropolitan area characterized by a diverse array of tall obstacles. The study investigates the detectability of these urban objects. The results demonstrate that even single radar echoes can reliably reveal the presence of tall structures, while averaging methods further enhance detection performance and resolution. The results underscore the strong capability of X-band radar systems for deployment within UAV frameworks for situational awareness and collision avoidance. Their utility is particularly evident in demanding urban landscapes where adverse weather can compromise the effectiveness of optical sensors. The study also discusses practical considerations for radar deployment in city environments, providing valuable insights for the development of robust UAV navigation systems.

Przejdź do artykułu

Autorzy i Afiliacje

Urszula Libal

e-mail:

ORCID:

Arkadiusz Byndas

Dawid Sysak

Tomasz Karaś

Wroclaw University of Science and Technology, Faculty of Electronics, Photonics and Microsystems, Poland

7 Deep learning approach for retinopathy identification in combined clinical datasets

Michał Zmonarski , Ewa Skubalska-Rafajłowicz , Aleksandra Zgryźniak , Sławomir Zmonarski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157868

Słowa kluczowe: Diabetic retinopathy detection deep learning CNN-VGG16 sequential transfer learning

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This work presents a system for automatic detection of various stages of diabetic retinopathy (DR) based on fundus images of patients. The system was built based on a relatively new and little-used image database: ”Dataset of fundus images for the study of diabetic retinopathy” version v3 CastilloBenitez21. The primary dataset was expanded using clinical fundus photographs acquired from the Department of Nephrology at Wroclaw Medical University. The diagnostic system was developed based on various variants of convolutional neural networks (CNNs) that were pre-trained on ImageNet data. The CNN classifier, based on VGG16 with transfer learning, proved to be effective and gave a global accuracy of 83.15%. The evaluation of discrimination between the non-DR and the DR state resulted in an accuracy of 89.7%, with a sensitivity of 94.9%, a specificity of 88.3%, and a Matthews Correlation Coefficient of 0.7665.

Przejdź do artykułu

Autorzy i Afiliacje

Michał Zmonarski

Ewa Skubalska-Rafajłowicz

Aleksandra Zgryźniak

Sławomir Zmonarski

Faculty of Information and Communication Technology, Wroclaw University of Science and Technology, Wroclaw, Poland
Clinic of Ophthalmology, University Teaching Hospital, Wrocław, Poland
Dept. of Nephrology and Transplantation Medicine, Wrocław Medical University, Wrocław, Poland

8 Context-aware uncertainty modeling for pedestrian intention detection in urban environments

Yusuf Yesilyurt , Marek Woda

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-10 | DOI: 10.24425/ijet.2026.157869

Słowa kluczowe: Pedestrian intention detection uncertainty modelling aleatoric uncertainty epistemic uncertainty cost-sensitive learning autonomous driving PIE dataset

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The present study investigates the application of uncertainty modelling for the purpose of detecting pedestrian intentions in contexts pertaining to autonomous driving. The proposed framework integrates two mechanisms: thresholdmodulation networks for aleatoric uncertainty and cost-sensitive learning for risk-aware decision making.

Experiments on the PIE dataset with ResNet50, VGG16, and AlexNet demonstrate that cost-sensitive learning enhances F1- scores marginally (0.05-0.58 percentage points) by prioritising recall for crossing pedestrians. ResNet50 demonstrates the strongest performance (98.30% accuracy, 96.35% F1-score), significantly outperforming more elementary architectures. Threshold networks have been observed to introduce computational overhead, resulting in approximately a doubling of training time, accompanied by slight performance reductions.

The study provides empirical evidence for the trade-offs between uncertainty modelling complexity and classification performance in pedestrian intention detection, offering insights for designing safety-oriented perception systems with appropriate computational constraints.

Przejdź do artykułu

Autorzy i Afiliacje

Yusuf Yesilyurt

Marek Woda

Wrocław University of Science and Technology, Wrocław, Poland

9 Application of Large Language Models to automatic classification of vulnerabilities according to the CVSS 3.1 standard

Michal Walkowski , Nikita Zhukov , Slawomir Sujecki

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157870

Słowa kluczowe: Security CVSS Score Well-known Vulnerabilities Large Language Model

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

We evaluated three chatbot models (ChatGPT-4omini, Gemini 2.0 Flash, Deepseek Chat) to automate CVSS 3.1 vulnerability scoring using 4,459 CVE records. Gemini achieved the highest accuracy across prompt strategies, while ChatGPT showed vector-score inconsistencies, and Deepseek underestimated severity. Results suggest that chatbots can support analysts but require validation mechanisms.

Przejdź do artykułu

Autorzy i Afiliacje

Michal Walkowski

e-mail:

ORCID:

Nikita Zhukov

Slawomir Sujecki

e-mail:

ORCID:

Department of Telecommunications and Teleinformatics, Wroclaw University of Science and Technolgy, Poland
Department of Telecommunications and Teleinformatics, Wroclaw University of Science and Technology, Poland; Faculty of Electronics, Military University of Technology, Poland

10 Performance analysis of tabular and Fuzzy Q-learning under varying state and action space resolution

Roman Zajdel

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-10 | DOI: 10.24425/ijet.2026.157871

Słowa kluczowe: Reinforcement Learning Q-learning Fuzzy Systems State Discretization

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Reinforcement learning (RL) algorithms, such as Q-learning, are widely applied to control tasks involving continuous state spaces that require discretization or function approximation. However, the effect of state and action space resolution on learning efficiency and convergence stability remains a significant challenge, particularly when comparing classical tabular approaches with fuzzy function approximations. This study presents an in-depth experimental analysis of Q(0)-learning and trace-based Q(λ)-learning, applied to three benchmark control problems: Cart–Pole, Ball–Beam, and Mountain Car. The experiments systematically investigate how increasing the granularity of state discretization (number of bins), the number of fuzzy sets, and the size of the action space influence convergence speed and result variance. The results clearly demonstrate that Q(λ)- learning consistently outperforms Q(0)-learning in both tabular and fuzzy settings, providing faster convergence and greater stability at higher discretization resolutions. Furthermore, fuzzy Q(λ)-learning exhibits superior scalability and generalization capabilities, particularly for complex underactuated systems such as Ball–Beam. These findings highlight the practical advantages of combining eligibility traces with fuzzy state representation in reinforcement learning. This approach supports the design of more robust controllers for real-world dynamic systems.

Przejdź do artykułu

Autorzy i Afiliacje

Roman Zajdel

Faculty of Electrical and Computer Engineering, Rzeszow University of Technology, Rzeszow, Poland

11 Synchronous and asynchronous bertsekas methods for energy-aware networks and solution of Regularized Linear Systems

Anthony Nwachukwu , Andrzej Karbowski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-10 | DOI: 10.24425/ijet.2026.157872

Słowa kluczowe: Augmented Lagrangian methods Bertsekas decomposition Asynchronous optimization Synchronous optimization Energy-aware routing Bandwidth allocation Linear Systems Distributed algorithms Mixed-integer nonlinear programming (MINLP) Dual decomposition Regularized Linear Systems

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper develops and analyzes augmented Lagrangian-based methods for two classes of large-scale optimization problems relevant to modern computational systems: energy-aware network routing with bandwidth allocation and the solution of regularized linear systems. In the first problem, routing and bandwidth allocation are jointly optimized in communication networks under energy constraints, modeled as a mixed-integer nonlinear program. In the second, regularized linear systems are formulated to address ill-posed or illconditioned problems by introducing stabilization terms such as ℓ2 regularization. For both problems, synchronous and asynchronous distributed optimization schemes are designed using decomposition techniques grounded in augmented Lagrangian theory. Extensive numerical experiments across diverse datasets, including network flow instances and benchmark regularized linear systems, demonstrate that the asynchronous variants retain comparable solution quality while significantly improving computational performance, particularly under delay and scalability conditions. These findings reinforce the practical value of asynchronous augmented Lagrangian methods for distributed, high-dimensional, and delay-sensitive optimization problems.

Przejdź do artykułu

Autorzy i Afiliacje

Anthony Nwachukwu

Andrzej Karbowski

Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland

12 Framework for intelligent prediction of the mobile players retention

Piotr Bilski , Adrian Bilski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157873

Słowa kluczowe: mobile gaming retention analysis artificial intelligence player analysis

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The paper presents the novel approach for the analysis of the mobile game players’ data to predict retention, i.e. duration of remaining inside the game. The definition and measures of evaluating retention from the mobile game perspective are described. The architecture of the implemented system is presented with the detailed explanation of the subsequent (specifically data collection and processing) modules. Three specific problems related to the retention analysis (focused on the gameplay duration and making financial transactions using actual currency) are presented. Task-oriented evaluation measures (to learn about the accuracy of the proposed approach) are described. Experiments regarding the efficiency of the proposed approach using the data set from the My Spa Resort mobile game from CherryPick Games company are presented, proving usefulness of the approach. Future prospects of the solution and technical limitations are described.

Przejdź do artykułu

Autorzy i Afiliacje

Piotr Bilski

Adrian Bilski

e-mail:

ORCID:

Warsaw University of Technology, Poland
Warsaw University of Life Sciences, Poland

13 Processing heterogeneous cryptocurrency exchange data for law enforcement: A proposal for an online tool

Przemysław Rodwald , Natan Kołodziej

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157874

Słowa kluczowe: cryptocurrencies investigations crypto exchanges data

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The growing number of criminal investigations involving cryptocurrency-related offenses, mainly investment fraud or crypto scams, has led to an increased frequency of Law Enforcement Agencies requesting information from cryptocurrency exchanges. However, the data provided by these entities often varies significantly in terms of format, structure, and level of detail, which complicates efficient processing and analysis. This article proposes the development of an online tool designed to automatically process data received from various cryptocurrency exchanges. The tool aims to convert disparate datasets into a standardized and readable format, thereby enhancing the effectiveness of investigative procedures and improving the consistency and quality of data analysis in criminal cases. The paper outlines the core functional assumptions of the proposed solution, presents its system architecture, and discusses example use cases. A prototype implementation has been deployed and evaluated on sample datasets from five major cryptocurrency exchanges.

Przejdź do artykułu

Autorzy i Afiliacje

Przemysław Rodwald

e-mail:

ORCID:

Natan Kołodziej

Educational Division of the Cyber Security Training Centre of Excellence, Warsaw, Poland
student of Computer Science at the Polish Naval Academy, Gdynia, Poland

14 Spatiotemporal Deep Learning on dynamic infrared thermography for classification of post-COVID-19 and post-myocardial infarction patients

Jakub Skwierczyński , Krzysztof Krupka , Andrzej Rusiecki , Łukasz Jeleń

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157875

Słowa kluczowe: dynamic infrared thermography deep learning thermoregulation analysis hyperparameter optimization CNN

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Dynamic infrared thermography is emerging as a noninvasive technique for monitoring microvascular health, yet its interpretation remains largely qualitative and laborintensive. This work systematically benchmarks four deep learning architectures: 2D CNN, 3D CNN, CNN–LSTM, and CNN–Transformer, evaluated for automated DIRT sequence classification in a clinically relevant cohort of post-COVID-19 and post-myocardial infarction patients. The study introduces a rigorous pipeline encompassing thermal image acquisition, standardized preprocessing, tailored data augmentation, and stratified cross-validation to ensure reliable evaluation. Purely spatial models such as the 2D CNN underperform, achieving a macro F1 score of 73.5% and accuracy of 80.1%, while temporally aware models yield substantial gains: CNN–LSTM reaches a macro F1 score of 91.4% and accuracy of 92.7%, and the CNN–Transformer achieves 88.8% and 90.6% prior to hyperparameter optimization. After automated hyperparameter optimization, both models converge to a macro F1 score of 93.8% and accuracy of 94.8%, with the Transformer requiring less than half the parameters. Functional ANOVA analysis highlights that learning rate is the most influential factor for LSTM tuning, while dropout dominates for the Transformer. These findings establish a foundation for robust, sequence-aware DIRT analysis, demonstrating that modern deep learning models, when rigorously validated, can transform DIRT into a quantitative biomarker for longitudinal vascular assessment.

Przejdź do artykułu

Autorzy i Afiliacje

Jakub Skwierczyński

Krzysztof Krupka

Andrzej Rusiecki

e-mail:

ORCID:

Łukasz Jeleń

Department of Computer Engineering, Wrocław University of Science and Technology, Wrocław, Poland
The Karol Godula Upper Silesian Academy of Entrepreneurship in Chorz´ow, Poland

15 Methods for assessing the effectiveness of information security systems in distributed information systems

Yuliia Kostiuk , Bohdan Bebeshko , Nataliia Kotenko , Natalia Mazur , Karyna Khorolska , Tetiana Zhyrova

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-10 | DOI: 10.24425/ijet.2026.157876

Słowa kluczowe: information systems security effectiveness information protection cyber threats mathematical modelling threat decomposition hierarchical analysis pairwise comparison matrix adaptive tuning

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The article considers methods and approaches to assessing the effectiveness of information security systems in distributed information systems, in particular, a mathematical model for determining the current effectiveness of such systems is derived. The model is based on the calculation of protection potentials, the level of equipment of system elements with security features, and the efficiency of management processes. The article decomposes the main types of threats - theft, copying, disclosure, blocking, modification and destruction of information. To determine the probability of attacks, Bayesian inference and hierarchical analysis (MHA) methods are used to obtain quantitative risk indicators for each category of threat. A new approach to assessing the level of losses arising from the amount of resources required to localize the consequences of attacks is developed. A methodology for modelling the impact of threats using a matrix of pairwise comparisons is proposed, which allows optimising the cost of security measures without increasing the overall cost by replacing expensive methods with alternative more efficient approaches. Particular attention is paid to insider threats, which both attack models and analysis of real incidents confirm. The practical application of the proposed models allows one to increase the efficiency of protection, reduce the cost of system maintenance and ensure its flexibility in responding to constantly changing cyber threats.

Przejdź do artykułu

Autorzy i Afiliacje

Yuliia Kostiuk

Bohdan Bebeshko

Nataliia Kotenko

Natalia Mazur

e-mail:

ORCID:

Karyna Khorolska

Tetiana Zhyrova

Borys Grinchenko Kyiv Metropolitan University, Ukraine
State University of Trade and Economics, Ukraine

16 Real-time reversible image steganography with lightweight vision transformers for embedded systems

Olga Veselska , Ruslana Ziubina , Vasyl Martsenyuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157877

Słowa kluczowe: reversible steganography Vision Transformers MobileViT TinyViT embedded systems image hiding attention mechanism lightweight models

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents a real-time, resource-efficient framework for reversible image steganography that utilizes lightweight Vision Transformers (ViTs), specifically designed for edge computing devices. Building upon the foundational StegoTransformer model, the proposed architecture incorporates MobileViT and TinyViT for embedding and extracting hidden image data. The system is optimized to function effectively under constrained computational resources, enabling secure and reversible data hiding on platforms such as Jetson Nano, Raspberry Pi, and mobile devices. Experimental results indicate competitive performance in terms of payload capacity, visual fidelity, and message recovery accuracy, while achieving low latency and memory consumption suitable for real-world deployment.

Przejdź do artykułu

Autorzy i Afiliacje

Olga Veselska

Ruslana Ziubina

Vasyl Martsenyuk

University of Bielsko-Biala, Bielsko-Biala, Poland

17 Cyber Soldier project - A threat-led methodology for assessing the Digital Resilience of cybersecurity systems

Mariusz Stawowski , Adam Sobczyk , Mateusz Gajda , Tomasz Wojtas , Tomasz Pająk , Krzysztof Siwy , Grzegorz Blinowski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157878

Słowa kluczowe: cybersecurity threat intelligence digital resilience

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

We present Cyber Soldier Methodology and tool set that introduces a threat-led methodology for assessing the digital resilience of cybersecurity systems within organizations required to comply with European regulatory frameworks such as the Digital Operational Resilience Act (DORA). Unlike traditional vulnerability assessments or penetration testing, this methodology focuses on reproducing the tactics, techniques, and procedures (TTPs) of real adversaries to evaluate the effectiveness of cybersecurity controls and operational resilience mechanisms in production environments.

The proposed methodology integrates threat intelligence, red team scenario design, and detection performance analysis into a unified process aimed at measuring the organization’s preparedness for sophisticated cyber threats.

We demonstrate how the presented framework bridges the gap between strategic compliance requirements under DORA and the operational practice of resilience testing. We also provide some initial data the application of Cyber Soldier toolset in real-world environments.

Przejdź do artykułu

Autorzy i Afiliacje

Mariusz Stawowski

1 2

e-mail:

ORCID:

Adam Sobczyk

Mateusz Gajda

Tomasz Wojtas

Tomasz Pająk

Krzysztof Siwy

Grzegorz Blinowski

Military University of Technology, Poland
CLICO Sp. z o.o., Poland
Warsaw University of Technology, Poland

18 Airdrop Sybil Attack detection framework supported by machine learning

Kamil Kaczyński , Aleksander Wiącek

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157879

Słowa kluczowe: Blockchain Airdrop ZKsync Sybil Attack Detection Graph Isomorphism Network

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Airdrop Sybil attacks can be a lucrative labour, and tokens received from one airdrop by an effective hunter can reach thousands of dollars. Sybil attacks in this context are not always desired by projects and are often seen by honest players as inappropriate behaviour, which can reflect badly on a project’s reputation. For such a reason, it is well expected that Sybil attacks detection systems will be constantly improved. In this work, a multistep framework is presented. Its idea is to sort blockchain addresses and assign them a score that will indicate if a given address is closer to a normal or a Sybil class. A graph isomorphism network was used to classify topologies, and its parameters were tuned on a dataset labelled by the authors. In other steps, a DBSCAN was used for the account clustering task. Users of the framework can assign arbitrary weights to each step, which will determine how important a step is to them and result in a different score for a given address. The best weights were found with a grid search method as well as a threshold after which the address is considered Sybil. In this paper a set of EOAs from ZKsync rollup was analyzed. In the end, 76% of all the accounts analyzed were marked as Sybils. Compared to the official ZKsync eligibility list, we found 342 addresses that received airdrop tokens but were marked as Sybil by our solution.

Przejdź do artykułu

Autorzy i Afiliacje

Kamil Kaczyński

Aleksander Wiącek

Military University of Technology, Warsaw, Poland

19 Data exploration algorithms in anomaly detection in communication protocols

Michał Kaczmarczyk , Kacper Kocemba , Maciej Stranz , Mateusz Winnicki , Sebastian Plamowski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157880

Słowa kluczowe: Anomaly detection communication protocols cybersecurity machine learning intrusion detection ensemble learning

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Cybersecurity in modern communication networks is of paramount importance, particularly in critical infrastructure sectors. Anomaly detection in communication protocols is a key component in identifying and mitigating cyber threats. This study explores data-centric approaches for anomaly detection using machine learning algorithms. We evaluate the effectiveness of ensemble models incorporating Isolation Forest, XGBoost, and Autoencoders to reduce false positives while maintaining high accuracy. Our methodology involves training on both labeled and unlabeled datasets, including NSL-KDD and CIC-IDS2017, to simulate real-world attack scenarios. Experimental results demonstrate that the proposed ensemble learning approach enhances detection performance, offering a balanced trade-off between precision and false alarm reduction. These findings contribute to the development of robust and scalable intrusion detection systems suitable for deployment

Przejdź do artykułu

Autorzy i Afiliacje

Michał Kaczmarczyk

Kacper Kocemba

Maciej Stranz

Mateusz Winnicki

Sebastian Plamowski

Warsaw University of Technology, Faculty of Electronics and Information Technology, Institute of Control and Computational Engineering, Poland

20 Artificial Intelligence as a research support tool: reliability, transparency and epistemic risks in academic knowledge production

Miłosz W. Romaniuk , Maciej Gąsienica-Szostak , Martyna Karwińska

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157881

Słowa kluczowe: artificial intelligence research workflow text summarization authorship detection epistemic reliability

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The rapid integration of generative AI into the research process forces us to look closer at whether these tools can actually be trusted. This generates tension, which becomes particularly visible when AI systems replace transparent analytical procedures with probabilistic outputs that cannot be independently reconstructed or epistemically audited by human researchers. In this paper, we move beyond the excitement over efficiency to examine the accuracy of AI-driven summarization and authorship detection. Our analysis reveals that beneath the speed of these systems lie significant risks, including systematic biases and a tendency toward 'hallucinated' certainty. Rather than rejecting these tools, we propose a new methodological framework that helps scholars use AI while safeguarding the integrity of their results.

Przejdź do artykułu

Autorzy i Afiliacje

Miłosz W. Romaniuk

Maciej Gąsienica-Szostak

Martyna Karwińska

The Maria Grzegorzewska University (APS), Warsaw, Poland

21 Ethical and legal challenges of generative AI in scientific writing: authorship, transparency and translation plagiarism

Miłosz W. Romaniuk , Adrianna Malik , Michał Kokoszka

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157882

Słowa kluczowe: generative AI scientific writing research ethics copyright law translation plagiarism

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

As generative AI tools become common in academic writing, they are blurring the traditional lines of authorship and originality. This article explores the friction between current copyright laws and the emerging reality of AI-assisted manuscripts, specifically looking at the rise of 'translation plagiarism.' These challenges are intensified by a structural conflict of interests between authors seeking efficiency, publishers prioritizing scalability and liability reduction, and AI developers operating beyond traditional accountability frameworks. By blending legal theory with practical case studies, we show where current editorial standards are failing to keep pace. We conclude by offering an integrated model for publishers and institutions to handle AI involvement more transparently.

Przejdź do artykułu

Autorzy i Afiliacje

Miłosz W. Romaniuk

Adrianna Malik

Michał Kokoszka

The Maria Grzegorzewska University (APS), Warsaw, Poland

22 Artificial Intelligence in Education and Information Ecosystems: Learning Outcomes, Virality and the Social Impact of Automation

Miłosz W. Romaniuk , Andrzej Manujło , Roman Androszczuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157883

Słowa kluczowe: artificial intelligence higher education learning outcomes information ecosystems content virality

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

AI is no longer just a tool. It has become a fundamental part of our educational and information ecosystems. This study investigates how AI-generated assignments and content algorithms are changing the way students and scholars interact with knowledge. While the efficiency gains are obvious, our findings point to a deeper problem: a growing cognitive dependency that could weaken critical thinking. By connecting educational technology with information studies, we provide a roadmap for updating academic literacy and curriculum design for the AI era.

Przejdź do artykułu

Autorzy i Afiliacje

Miłosz W. Romaniuk

Andrzej Manujło

Roman Androszczuk

The Maria Grzegorzewska University (APS), Warsaw, Poland

23 A 5-dBm IIP3 3.5-mW LNA for 802.11ax Receiver in 40 nm CMOS

Piotr Kaczmarczyk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157884

Słowa kluczowe: low-noise amplifier (LNA) gain switching inductive degeneration 802.11ax radio-frequency integrated circuit (RFIC)

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This article presents an inductively degenerated common-source low-noise amplifier (LNA) for a 5–6-GHz wireless local area network (LAN) receiver integrated circuit (IC). The LNA is equipped with gain-switching to prevent fast saturation in a presence of a large input signal. The simulated parameters, particularly the high linearity expressed in the input third-order intercept point (IIP3) of 5 dBm, make the design a promising solution for IEEE 802.11ax compliant receivers. Additionally, the low power consumption of 3.5mW makes it suitable for portable devices.

Przejdź do artykułu

Autorzy i Afiliacje

Piotr Kaczmarczyk

AGH University of Krakow, Poland

24 Optimal thermal placement of electronic functional blocks using symbolic algebra. A new application of Groebner Analysis

Gilbert De Mey , Andrzej Kos , Adam Miszczak , Alexis De Vos

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157885

Słowa kluczowe: analytical optimization arrangement of functionalblocks on integrated circuit substrate reduction of maximumtemperature of integrated circuit

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The paper presents a new idea and algorithm for arranging topography of functional blocks (hereinafter referred to as components) on an integrated circuit substrate, e.g. a digital processor, power circuit etc., in such a way as to minimize the mutual thermal interactions of individual components. Our analytical method finds the global optimum, which distinguishes it from numerical methods that can only find local minima. This leads to uniform temperature distribution, and therefore full use of the thermal properties of the electronic system, minimizing the maximum temperature on the substrate, and consequently allows for increasing the throughput. Presented approach is universal and allows for solving many similar global minimum search problems.

Przejdź do artykułu

Autorzy i Afiliacje

Gilbert De Mey

Andrzej Kos

e-mail:

ORCID:

Adam Miszczak

Alexis De Vos

University of Ghent, Belgium
AGH University of Kraków, Poland
Technical University of Lodz, Poland

25 Severity is not exploitability: A simple taxonomy and context score for better CVE triage

Grzegorz Siewruk , Tomasz Bondaruk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157886

Słowa kluczowe: devsecops vulnerability analysis vulnerability management cybersecurity

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Modern security teams face a constant backlog of vulnerabilities and limited engineering time for patching. In practice, organizations turn this into a triage problem: deciding which findings to remediate first, which to monitor, and which to postpone, often encoding these choices into SLAs, dashboards, and automated patching workflows driven by scanner output. Today this prioritization is usually based on Common Vulnerability Scoring System (CVSS) base severity, even though severity does not equal exploitability. This paper presents a compact, single-tag taxonomy for exploitability preconditions (exposure, environment, configuration, authentication, cryptography, and related factors) and a transparent context score that estimates how easy a vulnerability is to exploit in a given deployment. We enriched a dataset of 2,426 Common Vulnerabilities and Exposures (CVE) with constraint annotations and compared the context score against CVSS severity and the Exploit Prediction Scoring System (EPSS). The score shows weak association with both signals, indicating it captures complementary information about situational ease rather than impact or ecosystem pressure. Grouped by severity, notable shares of medium- and even low-severity findings emerge as easy to exploit under common configurations. In a telecom self-care platform case study (100 findings), reordering by the context score surfaced 28 straightforward fixes across severities, reducing immediate exposure and consolidating root causes that a severity-only plan would postpone. We conclude that combining EPSS with the proposed context score yields a more effective, auditable triage process for applied informatics settings.

Przejdź do artykułu

Autorzy i Afiliacje

Grzegorz Siewruk

1 2

Tomasz Bondaruk

Warsaw University of Technology
IDEAS Research Institute Warsaw, Poland

26 Signal processing using octonionic modules – a path towards a new computational intelligence model

Wieslaw Citko , Wieslaw Sienko

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157887

Słowa kluczowe: computational intelligence Hopfield neural networks word sequence recognition

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This study proposes a modular structure designed for pattern and word sequence recognition. The developed structure is based on an extended Hopfield neural network. The architecture of the word sequence recognition system employs octonionic modules, which are implemented as transversal filter banks. The structure can be used to recognize word sequences containing data represented as both real and complex numbers. The proposed procedure for synthesizing the word sequence recognition system may be useful for the development of computational intelligence systems.

Przejdź do artykułu

Autorzy i Afiliacje

Wieslaw Citko

Wieslaw Sienko

Department of Marine Telecommunications, Faculty of Electrical Engineering, Gdynia Maritime University, Poland

27 Current knowledge on supercapacitors, hybrid supercapacitors, and comparison with Lithium-Ion Cells – a review

Mariusz Staniak , Mirosław Lewandowski

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157888

Słowa kluczowe: energy storage hybrid supercapacitor EDLC litium-ion cell

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The growing demand for efficient and durable energy storage technologies has accelerated the development and deployment of advanced electrochemical systems. This review presents a comparative analysis of three key energy storage technologies: electric double-layer capacitors (EDLC), lithium-ion hybrid capacitors (LIC), and conventional lithium-ion batteries. The study explores their internal structures, charge storage mechanisms (non-faradaic vs. faradaic), electrochemical characteristics, and performance parameters including energy density, power density, cycle life, and thermal stability.

LIC, which combine a capacitive electrode with a battery-type
electrode, are shown to bridge the performance gap between EDLC and lithium-ion batteries by offering significantly higher power density and cycle life than batteries, and greater energy density and lower self-discharge than EDLC. Commercial examples such as SECH and VinaTech LIC are discussed in terms of operational parameters and practical deployment.

Quantitative comparisons indicate that LIC can reach energy
densities up to 77 Wh/kg and withstand over 50,000 chargedischarge cycles, positioning them as promising candidates for high-frequency cycling, fast-charging, and hybrid grid-storage systems. The paper concludes that further advancements in electrode materials and solid-state electrolytes are essential to unlock the full potential of LIC in both mobile and stationary energy storage applications.

Przejdź do artykułu

Autorzy i Afiliacje

Mariusz Staniak

Mirosław Lewandowski

Warsaw University of Technology, Poland

28 Review of methods evaluating video quality in adaptive streaming

Syed Uddin , Mikolaj Leszczuk , Michal Grega , Waqas Ur Rehman

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157890

Słowa kluczowe: video streaming QoE ABR algorithm latency

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The video streaming industry is growing. There is demand for high quality videos. These videos are stream to the consumers with a promising quality and low latency. There are various methods to measure the video quality of experience (QoE) in a streaming environment. The main goal of this paper is to provide an overview of methods and techniques to measure the QoE in adaptive streaming domain. This paper provide overview of metrics and QoE models which asses the video quality in streaming. This paper also discusses the dataset exist in video streaming. This paper highlights the challenges and future strategies that should be considered building models for assessing the video quality in adaptive streaming.

Przejdź do artykułu

Autorzy i Afiliacje

Syed Uddin

Mikolaj Leszczuk

Michal Grega

Waqas Ur Rehman

AGH University of Krakow, Poland
Birmingham City University, United Kingdom

29 Single-frequency impedance monitoring of Li-ion 18650 cells for battery management applications

Krzysztof Kuliński

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-6 | DOI: 10.24425/ijet.2026.157891

Słowa kluczowe: Li-ion battery diagnostics single-frequency EIS battery management system (BMS) power electronics reliability

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents an impedance-based analysis of three types of cylindrical Li-ion 18650 cells subjected to controlled charge–discharge cycling under various temperatures and load conditions. The main objective was to evaluate whether single-frequency impedance monitoring can provide a reliable indicator of operational degradation that could be implemented in practical electronic systems. Measurements were performed using an RLC bridge in the frequency range of 42 Hz to 10 kHz, with particular emphasis on impedance at 100 Hz as a diagnostic reference point. Results demonstrate a clear correlation between impedance growth and the number of cycles, temperature, and discharge current, confirming the applicability of this method for real-time condition monitoring. The findings highlight the potential of simplified impedance diagnostics for integration into battery management systems (BMS), embedded electronics, and telecommunication power supply units, where compact, low-cost, and efficient diagnostic solutions are required.

Przejdź do artykułu

Autorzy i Afiliacje

Krzysztof Kuliński

Silesian University of Technology, Poland

30 HybridGaze: A naturalistic dataset and multistream model for robust gaze estimation

Michał Chwesiuk , Piotr Popis

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157892

Słowa kluczowe: eye tracking appearance-based gaze estimation feature-based gaze estimation eye tracking dataset Deep learning data synchronization

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Gaze estimation plays a central role in computer vision and human-computer interaction, enabling applications in assistive systems, attention modeling, and human-robot collaboration. However, existing datasets often rely on infrared-based hardware, are collected in constrained laboratory environments, or lack precise synchronization between stimuli and gaze data, which limits model generalization to real-world conditions.

To address these challenges, we present HybridGaze - an open-source eye tracking dataset collected using a Tobii tracker combined with a standard RGB webcam. The recordings are processed into eye images and facial landmarks, providing synchronized gaze annotations and facial information across a variety of visual tasks. By capturing gaze data in naturalistic settings, the dataset reflects real-world visual behavior and serves as a valuable benchmark for gaze estimation research.

Furthermore, we introduce GazeModalNet, a multi-stream neural network that estimates gaze direction from two complementary sources: eye images and facial landmarks. Together, the dataset and model establish a strong foundation for developing robust, multimodal gaze estimation systems beyond laboratory constraints.

Przejdź do artykułu

Autorzy i Afiliacje

Michał Chwesiuk

Piotr Popis

Warsaw University of Technology, Poland

31 Efficient weapon detection using convolutional and transformer-based Deep Learning Models

Kamil Gomulka

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-10 | DOI: 10.24425/ijet.2026.157893

Słowa kluczowe: weapon detection object detection deep learning transformers convolutional neural networks

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Detecting weapons in public spaces remains a significant challenge in computer vision and public safety applications. While deep learning models have achieved great progress in general object detection, there is still a lack of focused studies on class-specific detection tasks, in particular those using new architectures such as transformers. In this work, a comprehensive evaluation of the state-of-the-art deep learning object detection approaches is conducted, including convolution and transformer-based architectures. Therefore, a dedicated large-scale dataset that combines images from multiple public sources is introduced, with a focus on three main weapons categories, enabling a more targeted evaluation. Furthermore, in the paper, the effectiveness of the best-performing architecture is further improved with proposed modifications, including architectural changes and determining a suitable loss function. Finally, the obtained detection approach achieves superior detection results, as evidenced by all performance criteria.

Przejdź do artykułu

Autorzy i Afiliacje

Kamil Gomulka

Rzeszow University of Technology, Poland

32 Mitigating the impact of thermal reflections in object detection using Vision-Language Models

Radosław Feiglewicz , Andrzej Kos

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157894

Słowa kluczowe: Detection accuracy Convolutional Neural Networks Vision-Language Models

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Thermal imaging is increasingly employed for navigation in challenging conditions such as dense smoke or fog. However, the limited availability of thermal images compared to RGB data makes training deep learning models, such as Convolutional Neural Networks (CNNs), significantly more difficult and often yields unsatisfactory results. Vision-Language Models (VLMs), due to their ability to perform tasks without extensive retraining or with only a small number of training samples, hold the potential to overcome current limitations in thermal imaging applications. This paper introduces a method leveraging VLMs to reduce the impact of reflections in thermal images on object detection accuracy, with a particular focus on human detection. The proposed approach improves the F1-score from 0.83 to 0.97 on a dedicated evaluation dataset, outperforming a baseline solution based solely on the widely used YOLOv11 model. Furthermore, we investigate the effects of quantization on various open-source VLMs, analyzing their performance, processing speed, and memory requirements.

Przejdź do artykułu

Autorzy i Afiliacje

Radosław Feiglewicz

e-mail:

ORCID:

Andrzej Kos

e-mail:

ORCID:

AGH University of Krakow, Poland

33 Students review of Innovations in quantum technologies, part 7

Oskar J. Gorgis , Jakub Kasjanowicz , Jakub Mielnicki , Umihito P. Murase , Filip A. Żarnowiec , Ryszard S. Romaniuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157895

Słowa kluczowe: Quantum Computing Quantum Algorithms NISQ Devices Quantum Optimization Ising Models QUBO Photonic Quantum Systems Hybrid Quantum–Classical Computing Quantum Annealing

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This paper presents a collection of student-led review studies covering selected topics in modern quantum information technologies. The contributions explore a broad range of theoretical concepts, hardware architectures, and application domains, including quantum computing models, quantum sensing, photonic systems, and optimization techniques. The reviewed works examine both gate-based and alternative quantum computing paradigms, as well as hybrid quantum–classical approaches, highlighting their potential advantages and current technological limitations. Particular attention is given to the role of quantum algorithms and physical implementations in addressing computationally challenging problems, such as combinatorial optimization and simulation tasks. Overall, the paper provides a snapshot of the current landscape of quantum technologies from an interdisciplinary perspective, emphasizing ongoing challenges related to scalability, noise, and practical applicability, while outlining promising directions for future research and development.

Przejdź do artykułu

Autorzy i Afiliacje

Oskar J. Gorgis

Jakub Kasjanowicz

Jakub Mielnicki

Umihito P. Murase

Filip A. Żarnowiec

Ryszard S. Romaniuk

Warsaw University of Technology, Poland

34 Students review of innovations in quantum technologies, part 8

Mateusz J. Berliński , Mateusz J. Broczkowski , Jędrzej J. Chmiel , Jakub Mielnicki , Dawid Nowicki , Kamil W. Wiecek , Ryszard S. Romaniuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157896

Słowa kluczowe: quantum information technology QIT teaching of QIT Ph.D. students view on QIT QIT implementation in ICT theses ICT Agriculture 5.0 Machine Learning Quantum Security OPM ARTIQ Sinara Microwaves Quantum Sensing

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

This collective work compiles essays written by graduate students at the Warsaw University of Technology, aiming to bridge the gap between established engineering disciplines, such as Electronics, Telecommunications, and Computer Science—and the emerging field of Quantum Information Technology (QIT). The pedagogical core of this project challenges authors to identify a hypothetical or practical ’quantum layer’ that could augment their standard Master’s thesis topics. This exercise serves to demonstrate that QIT is not merely an abstract physical theory but a versatile toolkit ready for cross-disciplinary application. The current 2025Z edition presents a diverse array of such hybrid concepts, ranging from environmental monitoring in Agriculture 5.0 and novel generative AI architectures, through robust cryptographic defense strategies and room-temperature biomedical sensors, to the fundamental hardware control stacks (Microwaves, ARTIQ/Sinara) required to operate quantum systems.

Przejdź do artykułu

Autorzy i Afiliacje

Mateusz J. Berliński

Mateusz J. Broczkowski

Jędrzej J. Chmiel

Jakub Mielnicki

Dawid Nowicki

Kamil W. Wiecek

Ryszard S. Romaniuk

Warsaw University of Technology, Poland

35 Influence of IQT on research in ICT, part 5

Karol Bresler-Przybył , Łukasz Nowicki , Michał Jarosik , Paweł Baran , Helena Jursza , Maciej Rosocha , Ryszard S. Romaniuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157897

Słowa kluczowe: Quantum information technology QIT teaching of QIT Ph.D. students view on QIT QIT implementation in ICT theses Ionising Radiation Microwave Materials Quantum Materials Quantum Acoustics Power Grids Electromagnetic Field Simulation

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The advanced Quantum Information Technologies subject for Ph.D. students in Electronics Engineering and ICT consists of three parts. A few review lectures concentrate on topics which may be of interest for the students due to their fields of research done individually in their theses. The lectures indicate the diversity of the QIT field, resting on physics and applied mathematics, but possessing wide application range in quantum computing, communications and metrology. The individual IQT seminars prepared by Ph.D. students are as closely related to their real theses as possible. Important part of the seminar is a discussion among the students. The task was to enrich, possibly with a quantum layer, the current research efforts in ICT. And to imagine, what value such a quantum enrichment adds to the research. The result is sometimes astonishing, especially in such cases when quantum layer may be functionally deeply embedded. The final part was to write a short paragraph to a common paper related to individual quantum layer addition to the own research. The paper presents some results of such experiment and is a continuation of previous papers of the same style.

Przejdź do artykułu

Autorzy i Afiliacje

Karol Bresler-Przybył

Łukasz Nowicki

Michał Jarosik

Paweł Baran

e-mail:

ORCID:

Helena Jursza

Maciej Rosocha

Ryszard S. Romaniuk

36 Influence of IQT on research in ICT part 6

Ahmad F. K. Khamaysa , Dawid Sygocki , Marek T. Wyrzykowski , Grzegorz T. Czarnecki , Kamil J. Krasiński , Rabiatul Adawiyah , Ryszard S. Romaniuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-9 | DOI: 10.24425/ijet.2026.157898

Słowa kluczowe: quantum information technology quantum nonlocality quantum metrology squeezed light noon states quantum computing cloud quantum neural networks quantum reinforcement learning quantum agents quantum-inspired spatio-temporal inference networks quantum machine learning quantum technologies

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

The advanced Quantum Information Technologies subject for Ph.D. students in Electronics Engineering and ICT consists of three parts. A few review lectures concentrate on topics which may be of interest for the students due to their fields of research done individually in their theses. The lectures indicate the diversity of the QIT field, resting on physics and applied mathematics, but possessing a wide application range in quantum computing, communications, and metrology. The individual IQT seminars prepared by Ph.D. students are as closely related to their real theses as possible. An important part of the seminar is a discussion among the students. The task was to enrich, possibly with a quantum layer, the current research efforts in ICT. And to imagine what value such a quantum enrichment adds to the research. The result is sometimes astonishing, especially in such cases when the quantum layer may be functionally deeply embedded. The final part was to write a short paragraph for a common paper related to individual quantum layer addition to the own research. The paper presents some results of such an experiment and is a continuation of previous papers of the same style.

Przejdź do artykułu

Autorzy i Afiliacje

Ahmad F. K. Khamaysa

Dawid Sygocki

Marek T. Wyrzykowski

Grzegorz T. Czarnecki

Kamil J. Krasiński

Rabiatul Adawiyah

Ryszard S. Romaniuk

Warsaw University of Technology, Poland

37 Influence of IQT on research in ICT part 7

Aleksander B. Mazur , Safiya Aliaksandrava , Piotr P. Jeżak , Piotr A. Fokow , Szymon S. Tokarski , Ryszard S. Romaniuk

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157899

Słowa kluczowe: quantum information technology QIT teaching of QIT Ph.D. students view on QIT QIT implementation in ICT theses

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Przejdź do artykułu

Autorzy i Afiliacje

Aleksander B. Mazur

Safiya Aliaksandrava

Piotr P. Jeżak

Piotr A. Fokow

Szymon S. Tokarski

Ryszard S. Romaniuk

Warsaw University of Technology, Poland

38 Substrate size impact on the radiation pattern of a sub-THz printed antenna

Yevhen Yashchyshyn , Peter Tokarsky

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-8 | DOI: 10.24425/ijet.2026.157900

Słowa kluczowe: Printed antenna thick substrate surface waves metasurface radiation pattern antenna directivity

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

In this paper, we study the effect of the transverse dimensions of a "thick" substrate on the printed antenna radiation properties in the sub-THz range. A four-element seriesfed dipole array operating at 100-116 GHz is chosen as a test antenna. It is printed on a rectangular grounded aluminum oxide substrate (99.5% Alumina) with a thickness of 0.05 mm, 0.1 mm, or 0.2 mm, in which only the fundamental mode of the surface wave can exist. The studies used the full-wave electromagnetic simulation method with Altair FEKO 2022 software. It is shown that pulsations can appear in the main beam of the antenna on atruncated substrate, the frequency of which increases proportionally to the width of the substrate, and the amplitude grows with increasing its thickness. With an increase in the substrate size, quasi-periodic variations in the antenna normalside directivity and gain are also observed, the period of which is equal to two surface wavelengths. The antenna radiation efficiency weakly depends on the substrate width, but increases noticeably with its thickening. It is shown that using a metasurface that significantly weakens the surface wave is an effective means of reducing the substrate edges' effect on the antenna characteristics.

Przejdź do artykułu

Autorzy i Afiliacje

Yevhen Yashchyshyn

Peter Tokarsky

Warsaw University of Technology, Poland
Institute of Radio Astronomy, National Academy of Sciences of Ukraine, Ukraine

39 Time-variant traits analysis in respiratory doppler radar’s signal

Suraya Zainuddin , Masrullizam Mat Ibrahim , Haslinah Mohd Nasir , Nur Fatin Shazwani Nor Razman , Mohd Zhafran Zainal Abidin

International Journal of Electronics and Telecommunications | 2026 | vol. 72 | No 1 | 1-7 | DOI: 10.24425/ijet.2026.157901

Słowa kluczowe: Respiratory Doppler Signal Time-variant Traits Machine Learning Statistical Feature Hilbert transform Discrete Wavelet Transform Fractal Dimension

Pobierz PDF Pobierz RIS Pobierz Bibtex

Abstrakt

Doppler radar-based respiratory monitoring offers a non-contact, physiologic assessment of breathing patterns. However, the inherent time-variant nature of respiratory signals presents challenges in accurate characterisation and classification. This study investigates the analysis of time-variant traits in respiratory Doppler radar signals using a feature extraction framework that integrates statistical features, Hilbert transform, discrete wavelet transforms (DWT), and fractal dimension analysis. The methodology begins with signal pre-processing to remove noise and enhance the signal for clarity. Statistical features, including mean, skewness, and kurtosis, are extracted to quantify signal variability. The Hilbert transform is employed to analyse instantaneous amplitude and phase variations, while DWT is used for multi-resolution decomposition to capture respiratory signal dynamics across different frequency scales over time. Additionally, fractal dimension analysis provides insights into the complexity and irregularity of breathing patterns in the time series. Machine learning-based classification models are applied to distinguish between normal and abnormal respiratory conditions. Results demonstrate the effectiveness of the proposed approach in enhancing respiratory signal characterisation and classification by utilising the Hilbert Transform over a Subspace Discriminant model with an accuracy rate of 92.3%. The findings suggest that integrating these feature extraction techniques can significantly improve non-invasive respiratory monitoring.

Przejdź do artykułu

Autorzy i Afiliacje

Suraya Zainuddin

Masrullizam Mat Ibrahim

Haslinah Mohd Nasir

Nur Fatin Shazwani Nor Razman

Mohd Zhafran Zainal Abidin

Universiti Teknikal Malaysia Melaka (UTeM), Malaysia
University Teknologi MARA (UiTM), Malaysia

Instrukcja dla autorów

Author Guidelines
We recommend the use of LaTeX2e for the preparation of your camera-ready manuscript, together with the corresponding class file.
We do not encourage the use of Microsoft Word, particularly as the layout of the pages (the position of figures and paragraphs or fonts) can change between printouts. If you would like to prepare your manuscript using MS Word please contact Editorial Office.
Please carefully read the information below, and download the relevant files.
To do so, please download JETInfo.pdf
Microsoft Windows or Macintosh LaTeX2e style file:
      Please download IEEEtran.zip
Publication requirement is to prepare no less than 6 pages including references using provided LaTeX2e style. All papers that do not meet this requirement will be rejected before review stage.

Please submit the following:
    All source LaTeX files.
    Final PDF file (for reference).
    PS/EPS or TIFF files for all figures.
    Complete contact information for all authors.
    Mailing address, a VAT/CIF/NIF/NIP number (depending on the country) of affiliated company the invoice should be sent.

IMORTANT! Before staring submission please prepare a contact information for all co-authors (full names, e-mails and affiliations). A contact information for all authors should be provided during submission process in "Step 2. Entering the Submission's Metadata". Papers submitted without contact information for all authors could be automatically rejected!