Journal of Electrical Engineering and Information Technologies

226. RISK ASSESSMENT FOR TESTING MEASURING INSTRUMENT SOFTWARE (Проценка на ризици од употреба на софтвер за тестирање мерни инструменти)

Valentyn Gaman, Oleh Velychko, Serhii Kursin — Tue, 05 Aug 2025 00:00:00 +0000

Abstract: This article is devoted to analysis and development of methodology to assess total risks from use of measuring instrument software based on subjective assessment of the probability of threats and the possible extent of damage. In the absence of statistical data on the probability for occurrence of threats and data on the possible size of losses from realization of these threats, it is suggested to use expert assessment on distribution of probabilities and size of the loss with assignment of conditional points. The proposed classification of possible threats and vulnerabilities in measurement software can be used to establish the overall risk for all threats. A generalized procedure for assessing specific risks has been developed to determine the level of verification during software testing of measuring instruments

227. COMPARISON BETWEEN CONTRASTIVE LEARNING AND RECURRENT NEURAL NETWORKS FOR POWER SYSTEM INERTIA ESTIMATION (Споредба помеѓу контрастно учење и рекурентни невронски мрежи за за проценка на инерција кај електроенергетски системи)

Pande Popovski, Anton Chaushevski — Tue, 05 Aug 2025 00:00:00 +0000

Abstract: The lack of power system inertia is becoming a potential issue as penetration of renewable energy sources in the power system increases. This is a result of an agenda set at worldwide level, to maximize integration of renewables and turn away from fossil fuels. Along with the potential problem of lack of power system inertia comes the difficulty of estimating equivalent power system inertia in a system that is becoming increasingly influenced by power electronics. While model-based analyses are possible, they do become increasingly difficult to solve. As a way to circumvent the inconvenience of estimating equivalent power system inertia, Machine Learning has proven to be a viable option. Recurrent, Convolutional, Physics Informed Neural Networks, including other types of regression focused approaches have been previously analyzed on this topic, and proven to be potentially useful. This paper makes a comparison between two approaches to estimation of equivalent power system inertia. The first approach is proposed by the authors, and it involves combination of Contrastive Learning and Ridge Regression. The second approach is Recurrent Neural Networks, which have been previously implemented on this kind of problem. Both methods are tested on simulated data from the IEEE 24-bus system. Different performance metrics are compared, on different dataset sizes. The results obtained from the study show that the method proposed by the authors produces better results in cases when there is deficiency of training data, leading to the conclusion that the proposed methodology may be potentially useful for such cases.

228. DETECTION OF ANOMALIES IN AIRCRAFT USING MACHINE LEARNING ALGORITHMS (Детекција на аномалии кај воздухоплови со примена на алгоритми од машинско учење)

Melanija Gerasimovska, Dushko Stavrov, Gorjan Nadzinski, Vesna Ojleska Latkoska — Tue, 05 Aug 2025 00:00:00 +0000

Abstract: This paper investigates the application of machine learning (ML) algorithms for anomaly detection in aviation, focusing on predictive maintenance and improving safety through early fault identification. Time-series vibration sensor data from helicopters is used to evaluate four anomaly detection methods: Isolation Forest (IF), One-Class SVM, Local Outlier Factor (LOF), and Convolutional-Reconstruction Autoencoder (CRAE). Both supervised and unsupervised detection approaches are considered. One-Class SVM demonstrated the highest performance, achieving accuracy of 93.9% and F1-score of 93.6%, followed by LOF (91.9%) and Isolation Forest (86%). CRAE underperformed with F1-score of 66.5%, primarily due to minimal preprocessing. These results highlight the effectiveness of simpler ML models over complex deep learning architectures in environments with limited data and real-time constraints.

229. TOWARDS A SMARTER FUTURE: FRAMEWORK FOR SUSTAINABLE SMART CITY SOLUTIONS (Пат кон попаметна иднина: Рамка на одржливи решенија за паметни градови)

Ivo Paunovski, Valentina Angelkoska, Igor Bimbiloski — Sat, 23 Aug 2025 00:00:00 +0000

Abstract: The concept of smart city has emerged as crucial paradigm for developing efficient and intelligent urban solutions aimed at enhancing the quality of life and fostering sustainable environmental management. While realizing this vision often entails significant challenges related to costs, complexity, and connectivity, this paper introduces an innovative four-tier architecture for smart cities. This framework establishes an ICT infrastructure as its foundational layer, integrating collaborative governance, smart services, and end users. The proposed architecture is fundamentally modular and decentralized, explicitly designed to systematically address key challenges such as security, privacy, and interoperability. It supports a gradual, adaptive implementation, leveraging its inherent flexibility for deployment of smart city services. Furthermore, through illustrative scenarios grounded in existing research, the paper demonstrates the significant potential and inherent robustness of this architecture in achieving substantial operational efficiencies, environmental benefits, and overall improvements in urban living.

230. AI-POWERED X-RAY SCANNING AND BLOCKCHAIN-BASED EVIDENCE MANAGEMENT: A SYSTEM FOR CORRUPTION PREVENTION AND SECURE LEGAL ACCOUNTABILITY (Рендгенски скенери со вештачка интелигенција и управување со докази базирано на блокчејн: Систем за превенција од

Wed, 06 Aug 2025 00:00:00 +0000

Abstract: This paper proposes a system that integrates artificial intelligence (AI) with X-ray scanning technology and blockchain to enhance detection and management of illegal objects. The proposed AI tool analyzes images from X-ray scanners in real time to detect criminal or prohibited items (e.g., firearms, explosives, drugs). When AI identifies a suspicious object, it automatically stores scan details, including metadata (time, location, object detected), as immutable blockchain record. This system ensures tamper-proof evidence management, promoting transparency and accountability in law enforcement

231. INTEROPERABILITY BETWEEN FEDERATED LEARNING AND WIRELESS POWERED COMMUNICATIONS: MINIMIZING TRAINING DELAYS (Интероперабилност помеѓу федеративно учењеи безжично напојувани комуникации:Минимзирање на времето на тренирање

Slavche Pejoski, Marija Poposka, Zoran Hadzi-Velkov — Wed, 06 Aug 2025 00:00:00 +0000

Abstract: This paper explores an interoperability scenario between wireless powered transfer and federated learning (FL) technologies. In this scenario, the base station does not only coordinate training of the global FL model, but it also charges energy harvesting (EH) clients, which are responsible for training the local models. These EH clients are equipped with rechargeable batteries, enabling them to perform local processing and energy harvesting concurrently. We propose an efficient resource allocation scheme that optimizes both computing and communication parameters to minimize training latency. Simulation results show a significant latency reduction compared to state-of-the-art FL system that operates with non-overlapping local processing and energy harvesting phases.

232. STRATEGIC GOALS FOR FUTURE MOBILE GENERATION 6G (Стратешки цели за идната мобилна генерација 6G)

Darko Koloski, Toni Janevski — Wed, 06 Aug 2025 00:00:00 +0000

Abstract: 5G is in the middle of its decade, 2020-2030. Based on the experience from previous mobile generations, the mid-decade point of the previous mobile generation is the starting point of work on frameworks and standards for the future mobile generation that should mark the next decade, 2030-2040, and that is 6G. Starting with 3G, the ITU defines requirements for any mobile generation as part of its framework recommendations. Similar to IMT-2000 for 3G, IMT-Advanced for 4G, IMT-2020 for 5G, ITU Radiocommunication Sector will prepare the framework for 6G called IMT-2030, where IMT stands for international mobile telecommunications. A lot of research has been done about the look of the future of 6G, and more will come in the next years, by 2030 and beyond. Considering that the only deployed 5G standard is the one from 3GPP, unlike mobile generations until 4G which had deployments of standards from multiple standard organizations in different regions across the globe, it is expected that 3GPP will also provide the main unified standard for 6G, the next mobile generation. 3GPP standardization process on 6G networks is expected to start in mid-year 2025 and worldwide commercialization around 2029–2030. This paper highlights the most promising research areas in recent literature on overall 6G trends. It discusses development and analysis of 6G mobile technology, including the benefits and challenges associated with its development.