The study is devoted to increasing the survivability of information systems operating on mobile platforms under limited computational resources and destructive impacts. Our goal is to develop a two-level method for multi-criteria optimization of policies for resource allocation among critical and non-critical services. A mathematical model of information systems based on a mobile platform is offered with consideration of state dynamics, global resource constraints and limitations related to ensuring the system survivability as well as vector criteria that characterize the survivability, efficiency of resource usage and quality of service. In order to decompose the problem, we used the Lagrange function, which allows to distinguish an upper level of policy selection and a lower level of configuring their parameters according to subgradient rules. Method specifics have been studied using a simulation model for several representative scenarios of resource degradation. It is shown that the proposed management regime ensures higher values of an integral survivability indicator in critical services in comparison to the balanced static policy and the strict priority policy while increasing a share of cycles with maintaining target thresholds at approximately 10-15%. At the same time, the average values of the efficient resource utilization remain close to all the considered regimes, and the quality of service metric degrades uniformly without showing prolonged failures even in strict scenarios. The proposed two-level method enables coordinated management of policies and their parameters combining improvement of survivability of information systems on mobile platforms while ensuring rational utilization of platform’s limited resources. The results obtained can be used for designing resource management systems of onboard computing complexes, unmanned and robotic platforms, as well as other mobile systems.

Information technology integrates various methods, tools, and processes for creating, collecting, processing, storing, protecting, and transmitting information, forming the backbone of modern business. The network-based audio analytics system combines hardware and software to collect, analyze, and interpret audio data, addressing tasks in security and monitoring. The context diagram of the information technology for the network-based audio analytics system highlights key parameters like input data, output data, control parameters, and mechanisms. Functional decomposition can help in understanding and optimizing system performance by breaking down tasks into manageable parts, ensuring efficient data collection, transmission, processing, storage, and visualization. Evaluation of the proposed information technology was performed

The paper presents an intelligent platform for scientific research in the field of computer vision, aimed at comprehensive comparative analysis of the accuracy, performance, and robustness of modern models under variable lighting and weather conditions. The primary objective of the development is to create a scalable system that supports experiments with a wide range of models (YOLOv8– YOLOv11, DETR, Mask R-CNN, SSD, RetinaNet, etc.) using interactive analytics, complete logging, and automated report generation. Unlike conventional testing environments, the proposed platform accounts for the characteristics of images from various application domains. For each scenario, log files are automatically stored with key metrics (mAP@0.5, mAP@0.5:.95, Precision, Recall, F1-score, IoU) and FPS, ensuring a comprehensive evaluation of both accuracy and processing speed. A distinctive practical novelty of the system is the implemented module for studying the impact of video stream preprocessing methods (CLAHE, gamma correction, median filtering, etc.) on object detection accuracy. Experimental results demonstrated, for example, that in low-visibility conditions the combination of Zero-Dce + gamma correction + CLAHE yielded an increase in mAP@0.5 in the range of 4–6%, depending on the model architecture. The platform also provides tools for assessing the effect of CUDA acceleration on the performance of each model. The developed system has undergone validation in a series of experiments, including tasks of adapting computer vision models within hardware-software complexes for assisting visually impaired individuals under limited computational resources, confirming its efficiency and practical applicability in various applied domains

The subject matter of the article is research into machine learning methods for object detection in images and videos under complex urban conditions, particularly under poor lighting, the presence of precipitation, high scene complexity, and limited computational resources. The goal of this research is to identify the most effective deep learning models based on convolutional neural networks for object detection tasks under challenging imaging conditions, considering the practical requirements for accuracy and processing speed. The tasks to be solved are: analysis of object detectors (YOLO v8–11, DETR, SSD, Mask R-CNN, Faster R-CNN, RetinaNet); preparation of a dataset with real weather conditions and pedestrian environments in Ukraine; experimental evaluation of selected detectors using the metrics mAP@0.5, mAP@.5:.95, Recall, Precision, IoU, FPS, and F1-Score; and analysis of the obtained results. The methods used are: convolutional neural networks, automated image annotation, comparative analysis of quality metrics (F1-score, mAP@0.5:.95, Precision, Recall, IoU, FPS), and manual correction of annotations. The following results were obtained: the YOLOv10-m and YOLOv11-m models demonstrated the best quality indicators under conditions of limited visibility and varying lighting. The YOLOv11-m model was the most balanced in terms of accuracy and speed across all tested conditions - snow, rain, and sunshine. YOLOv11-m is recommended as the baseline model for implementation in real-time systems, particularly in intelligent assistants for people with visual impairments. Conclusions: The scientific novelty of the results obtained is as follows: 1) a comprehensive evaluation of modern deep learning architectures for object detection (YOLOv8–v11, Faster R-CNN, SSD, Mask R-CNN, DETR, RetinaNet) was carried out under non-laboratory conditions, including real weather scenarios such as snow, rain, and poor lighting, which are typical for urban environments in Eastern Europe; 2) the software tool for automated model evaluation was developed, allowing simultaneous testing of multiple architectures and visualization of performance metrics (F1-score, mAP@0.5, mAP@.5:.95, IoU, Precision, Recall, FPS) with support for manual annotation correction and comparative model analysis; 3) it was experimentally established that the YOLOv11-m model demonstrates the best balance of accuracy and inference speed across various complex imaging conditions, justifying its recommendation as a baseline model for real-time vision-based assistive systems.

In today’s world of information technology and computing science, one of the most promising areas is the development and improvement of computer networks. Over the past decades, significant progress in this area has been observed due to the constant expansion of computing resources, as well as the development of new methods and algorithms for data processing. One of the important branches of computing science is fog computing, which is studied as a tool for modeling and analyzing systems with fuzzy data. Fog computing finds its application in many areas, including artificial intelligence, pattern recognition, decision making, and others. In this paper the specifics of building systems with fog computing were analyzed in detail, and the specifics of using polling networks, in particular sensor networks, were also considered. Various approaches to the integration of polling networks in the context of sensor technologies have been studied, which allows to increase the efficiency of data collection and transmission. Based on the obtained results, a method of organizing fog computing was developed, which takes into account the specifics of modern network architectures. A new architecture of the method is proposed, which contributes to improving the performance and reliability of the system due to the optimization of computing resources and ensuring more efficient data management. Mathematical experiments were also conducted to verify the effectiveness of the proposed solutions, which showed significant improvements compared to traditional methods.

The work is devoted to a detailed review of the main aspects of physical vulnerability for people with visual impairments, as well as technological means for navigation and adaptation to the surrounding environment, which can significantly enhance their sense of safety and security. The relevance of the topic is justified by its large social focus, because such systems help people with visual impairments to socialize more easily and ensure greater inclusion. This is particularly important in urban environments where insufficient attention is paid to inclusivity and the comfort of visually impaired individuals (e.g., lack of audible traffic lights, tactile paving, etc.). The subject of the article is the study of hardware components that ensure the functionality of support systems for people with visual impairments. The goal of this paper is to systematize knowledge about existing technological tools for people with visual impairments and to analyze the hardware characteristics of the components of such solutions. The task of this work is to examine the psychophysiological factors and aspects of physical vulnerability for people with visual impairments, review existing assistance systems for visually impaired individuals, identify the hardware base required for creating a “vision” system of the surrounding environment, and analyze the characteristics of sensors considering the external conditions in which visually impaired people may find themselves. The objectives are achieved through the use of methods such as comparative analysis, classification and categorization, and a systematic review of the literature in the relevant problem domain. The results of the work include a proposed classification of assistive devices for people with visual impairments, which encompasses the following classes: navigation applications and devices; sensory systems for obstacle and object detection; wearable devices with augmented reality (AR) features; “vision” systems for the surrounding environment; and text recognition systems. The evaluation and analysis of the advantages and disadvantages of devices in each of these classes demonstrate that a new solution should meet the criteria of compactness, wearability, energy efficiency, ease of use, and high accuracy in detecting environmental conditions, obstacles, and objects on the user's path. Conclusions. To ensure data complementarity in tasks of detecting moving objects in intelligent assistance systems for visually impaired individuals, the optimal approach is to combine multiple sensors using the Multisensor Fusion methodology. Specifically, this involves high-resolution cameras that provide detailed scene imaging and LiDARs that ensure precise distance measurement and 3D modeling of the environment. Such an approach compensates for the limitations of individual sensors and provides a more comprehensive understanding of the scene, improving data quality through the integration of diverse information sources. Further research will focus on conducting experimental research aimed at practically justifying the joint use of cameras, audio sensors, and LiDARs for obtaining heterogeneous data that provide the most comprehensive depiction of the environment surrounding visually impaired individuals.

The study is dedicated to the relevant topic of automated detection of muscle imbalance and postural deformities, which is particularly in demand among patients with orthopedic prostheses and in pediatric orthopedics. The authors propose a portable monitoring system that uses computer vision methods to assess the level of the pelvis, shoulders, and shoulder blades, ensuring the storage of photogrammetric data for subsequent analysis of rehabilitation results. The purpose of the work is to study methods for detecting optical markers on the human body when analyzing gait. The research tasks included conducting an analysis with a justification of the need to study computer graphics methods in the context of photogrammetric systems used in rehabilitation orthopedics; studying the impact of color characteristics of markers on detection accuracy; studying the impact of marker shape on detection accuracy; and analyzing the obtained results. The subject of the study is computer graphics and machine vision methods for detecting markers on the subject's body. The object of the study is photogrammetric technologies in orthopedics. As a result of the study, it was established that the use of the HSV color format for marker detection demonstrates high accuracy and low error even under changing lighting conditions. It was found that the shape of the marker affects detection accuracy, with the best results shown by the square shape. The research results confirmed the feasibility of using photogrammetry methods to assess joint asymmetry and muscle imbalance. Further research will focus on increasing the speed and accuracy of marker detection with non-stationary camera placement and a complicated background.

A key aspect in evaluating the performance of a UAV or its swarm is reliability. The reliability is calculated based on various mathematical models. Traditionally, Binary-State System (BSS) models, which assess two states—operational and faulty—are employed. However, some studies suggest using a Multi-State System (MSS) model, which allows for a detailed analysis by considering multiple states beyond just operational and faulty. Both mathematical models allow for the evaluation of Unmanned Aerial Vehicle (UAV) swarms based on availability, which is considered as a probability of swarm mission implementation. There is one more similar assessment computed based on MSS, which is named the probabilities of the performance level. There are not any recommendations for applications of these mathematical models and assessments for reliability analyses of UAV swarms. This paper introduces a comparative study on the availability of UAV swarms using both BSS and MSS models and the probability of performance levels of UAV swarms. This study provides quantitative and qualitative recommendations to exploit these mathematical models and assessments for UAV swarms according to computational complexity and informativeness. The comparative analysis shows that the evaluation of UAV swarm failure should be based on BSS, and the analysis of operation states should be implemented based on probabilities’ performance levels instead of swarm availability. These results are confirmed by quantitative and statistical examinations of UAV swarms of different types based on both BSS and MSS. The number of UAVs is changed from 2 to 20 in these examinations.

Relevance. In the rapidly evolving field of network-based audio analytics systems, the detection and analysis of audio events play a crucial role across various applications, including security, healthcare, and entertainment. Subject. This paper examines a method for recognizing audio events in network-based audio analytics systems, including preprocessing, sound separation, and the creation of machine learning models for analyzing audio signals. Objective. The objective is to develop and improve integrated methods for analyzing audio signals in network-based audio analytics systems to enhance the accuracy, speed, and reliability of data analysis. Methods. The proposed approach uses a modified ResNet architecture for multi-event classification and a convolutional neural network for separating sound sources in multi-channel recordings. Results. The method achieves competitive results, comparable to baseline results in contemporary challenges like DCASE and demonstrates robust performance in noisy environments. Conclusions. The proposed method shows potential for improving the accuracy and reliability of audio event recognition in real-world scenarios, particularly in complex acoustic environments.

Метою даної роботи є проведення комплексного аналізу методів та підходів до виявлення аномалій в мережах Інтернету речей (IoT). З урахуванням стрімкого розвитку IoT і збільшення кількості підключених пристроїв, проблема виявлення аномального трафіку стає актуальною для забезпечення безпеки та ефективності цих мереж. У роботі розглядаються різні методи та підходи до виявлення аномалій, включаючи статистичний аналіз, мережевий моніторинг, поведінковий аналіз, а також застосування сучасних технологій машинного та глибокого навчання. Кожен із цих методів розглядається з точки зору його застосовності в контексті IoT та оцінюються його переваги та обмеження. Робота також розглядає сучасні виклики і перспективи розвитку у галузі безпеки IoT, з фокусом на захисті від кіберзагроз та посиленні систем виявлення аномалій.

Метою даної роботи є проведення аналізу методів управління процесами передачі даних та трафіком які зможуть забезпечити підвищення ефективності передачі даних у мультисервісних комп'ютерних мережах. Зростаючі потреби суспільства в нових послугах телекомунікаційних мереж призводять до зміни ідеології побудови останніх кожне десятиріччя. Сьогодні, на зміну технологіям, що використовують мультиплексування з розділенням та ущільненням за довжиною хвилі, приходять мультисервісні технології, основним принципом концепції яких є відділення одна від одної функцій перенесення та комутації, функцій керування транзакціями та функцій керування послугами. Зокрема, це можуть бути різноманітні корпоративні мережі, де важливо контролювати доступ до ресурсів, хмарні середовищах, де надаються різноманітні послуги, онлайн-ігрові сервіси, де потрібна низька затримка та стабільне з'єднання. Щоб підвищити ефективність мультисервісних комп’ютерних мереж сьогодні інтегрують технічні засоби, що використовують асинхронний режим передачі (технологія АТМ або B-ISDN), з застосунками для мережі Інтернет. При побудові таких мереж важливо враховувати класифікацію мережевих характеристик, а саме категорію трафіку для вибору оптимального методу управління. В даній статті розглянуто метод програмного управління параметрами з'єднанням та методи статистичного мультиплексування передачі даних, проаналізовані основні переваги та проблеми означених методів, які вимагають подальшого їх дослідження.

The article describes the use of Grid technology in telecommunication systems and the creation of Grid telecommunication systems. Network service providers are focusing on huge consolidated data centers. Particular attention began to be paid to improving the methods of scheduling data processing tasks. The shortcomings of modern approaches to planning are considered. These include the inability to provide the maximum total priority of tasks performed at individual planning stages in distributed computing systems. The developed planning procedure is described. It overcomes this shortcoming. But at the same time, to reduce the total processing time of tasks in the system in comparison with the planning procedure based on solving the problem of the least coverage. The desire for the maximum sum of priorities of the selected tasks is the main criterion for selecting tasks from the queue, which we will characterize by the importance coefficient. The coefficient of preservation of importance and the coefficient of acceleration of the operation of the Grid system segment are described. The article also proposes a solution to improve the efficiency and quality of task servicing. It is proposed to expand the functionality of distributed telecommunication systems based on the use of computer clusters using Grid technologies.

Relevance. The sound is a source of data that provides information necessary for survival and warns of potential dangers. Audio analytics solutions allows detecting and responding in time to illegal actions and violations of the law, which are accompanied by appropriate sounds. Therefore, the problem of reducing delays in the transmission of audio streams in network-based systems of audio analytics becomes relevant. The object of research is the process of audio signals transmitting. The subject of the research is mathematical models of audio and video streams transmission in network systems. The purpose of this paper is to develop an approximate method for quickly solving optimization equations for a network of connecting links and to assess the adequacy of the developed method. Research results. A method for selecting the network structure of the audio analytics system is proposed. The optimization of the network structure of audio analytics system under non-ordinary Poisson load is presented. The optimization of the basic network of audio analytics system was studied according to the cost criterion. Comparisons of the optimization results shows that the given link distribution options are not significantly different from each other and are close in cost.

Industrial Internet of NanoThings (IIoNT) traffic model proposed. The model is based on the developed algorithm for Dynamic Data Composition Control. The application of the algorithm made it possible to reduce the total amount of transmitted information from the end nodes of IIoNT. The model made it possible to determine the parameters of aggregation traffic of IIoNT cluster gateway. With the calculated parameters, the value of the aggregated package is maximized. The main limitation is not exceeding the value of the boundary delay for the transmission of sensor readings. The model also allows you to dynamically determine the required amount of the gateway buffer memory.

Drones, or UAVs, are developed very intensively. There are many effective applications of drones for problems of monitoring, searching, detection, communication, delivery, and transportation of cargo in various sectors of the economy. The reliability of drones in the resolution of these problems should play a principal role. Therefore, studies encompassing reliability analysis of drones and swarms (fleets) of drones are important. As shown in this paper, the analysis of drone reliability and its components is considered in studies often. Reliability analysis of drone swarms is investigated less often, despite the fact that many applications cannot be performed by a single drone and require the involvement of several drones. In this paper, a systematic review of the reliability analysis of drone swarms is proposed. Based on this review, a new method for the analysis and quantification of the topological aspects of drone swarms is considered. In particular, this method allows for the computing of swarm availability and importance measures. Importance measures in reliability analysis are used for system maintenance and to indicate the components (drones) whose fault has the most impact on the system failure. Structural and Birnbaum importance measures are introduced for drone swarms’ components. These indices are defined for the following topologies: a homogenous irredundant drone fleet, a homogenous hot stable redundant drone fleet, a heterogeneous irredundant drone fleet, and a heterogeneous hot stable redundant drone fleet.

Актуальність. Тактильний Інтернет – це одна з основних технологій, що визначає чергову еволюцію мережі Інтернет, яка дозволяє передавати тактильні відчуття в режимі реального часу. Транзакція є основною процесу комунікації та обслуговування в Тактильному Інтернеті та використовується для передачі даних між різними вузлами в мережі. Моделюючи процес обробки транзакцій у Тактильному Інтернет-середовищі, можна спрогнозувати продуктивність роботи за різних сценаріїв і визначити області для подальшого вдосконалення. Це надасть змогу забезпечити надійність та доступність, а також низьку затримку у вузлах мережі Тактильного Інтернету. Метою даної роботи є моделювання процесу обробки транзакцій для забезпечення надійності, доступності та низької затримки при передачі даних у середовищі Тактильного Інтернету. Об’єктом дослідження є процес обробки транзакцій у середовищі Тактильного Інтернету. Предметом дослідження є методи оптимізації архітектури Тактильного Інтернету. Результати. В даній статті описані кроки процесу обробки транзакцій у Тактильному Інтернет-середовищі, включаючи збір даних, аналіз і генерацію команд керування. Розглянуто основні складові архітектури Тактильного Інтернету, а саме ведучий, ведений та мережний домени, і пропонується використання програмно-конфігурованих мереж для керування мережним трафіком та підвищення продуктивності мережі Тактильного Інтернету. Крім того, розглядаються питання масштабування ресурсів, на основі трирівневої архітектури Тактильного Інтернету та зменшення кількості керованих інтелектуальних контролерів з використанням протоколу Open Flow. Висновок. Розглянута модель процесу обробки транзакцій в середовищі Тактильного Інтернету здатна забезпечити тактильний зворотний зв’язок з низькою затримкою та покращити ефективність мережі, що буде мати позитивний вплив на взаємодію з користувачем і дозволить створювати нові програми та сценарії в таких сферах, як медицина, робототехніка, віртуальна та доповнена реальність.

The subject matter of the article is аudio signal transmission method in network-based audio analytics system. The creation of a network-based audio analytics system leads to the emergence of new classes of load sources that transmit packetized sound data. Therefore, without constructing adequate mathematical models, it is impossible to build a well-functioning network-based audio analytics system. A fundamental question in traffic theory is the question of load source models. The development of an method for transmitting audio signals in a network-based audio analytics system becomes necessary. Based on this, the goal of the work is to create methods an method for transmitting audio signals in a network-based audio analytics system to ensure efficiency and accuracy in audio analytics. The following tasks were solved in the article: the formation of a model for the system's load sources, investigation of connection and traffic management, implementation of control and traffic monitoring functions in the network, research of methods to ensure the quality of audio signal transmission and the development of a method of transmitting an audio signal by virtual routes switching. To achieve these goals, the following methods are used: mathematical signal processing, data compression algorithms, optimization of network protocols, and the use of high-speed network connections. The obtained results include modeling of the system's load sources, examination of connection and traffic management, investigation of methods to ensure the quality of audio signal transmission and a method of transmitting an audio signal by virtual routes switching was proposed. In conclusion, the possibilities of using simulation modeling of nodes in the network-based audio analytics system are highly limited. This is explained by the fact that the acceptable level of information loss in data centers is very low. The use of the developed method enables effective control and processing of sound information in real-time. This method can find broad applications in various fields, including security, healthcare, management systems, and other industries where the analysis of audio signals is a crucial element.

Fog computing extends the capabilities of cloud computing by enabling computing at the edge of the network, involving devices such as mobile collaborative devices or fixed nodes with integrated storage, computing, and communication capabilities. Fog computing offers benefits such as improved efficiency, increased security, savings in network bandwidth, and increased flexibility. In order to provide a complete understanding of Fog computing, this paper presents its salient features and highlights the differences from cloud computing research. Cloud computing is an emerging technology that offers computing resources on a pay-per-use basis. It provides three service models, and the cloud offers cost-effective centrally managed resources for reliable computing for specific tasks. This document presents a comparison between Fog computing and cloud computing, highlighting the differences in design, deployment, services, and tools available to organizations and users. By explicating the distinctiveness of fog computing and its contrast to cloud computing, we contribute to the field by shedding light on the unparalleled potential of fog computing in conserving resources while delivering robust computational solutions at the network periphery. Our study offers a new perspective that challenges the prevailing practices and extends the discourse on optimizing distributed computing architectures.

UAVs have a great potential of application for monitoring, search, detection, communication, delivery and transportation of cargo in various sectors of economy. In spite of this, the existing software and hardware, as well as legal limitations, prevent the wide application of UAVs. There is intensive research related to automation and optimization of missions of one or more UAVs in various application areas. However, the execution of missions of both individual vehicles and their homogeneous or heterogeneous groups depends on the reliability issues of these technical devices, UAVs fleets, and control systems. In this paper, we present models for assessing fleet reliability of UAVs that are managed centralized or decentralized. The method is based on the representation of the fleet as a Binary-State System. The following topologies are considered: (a) a homogenous irredundant drone fleet, (b) a homogenous hot stable redundant drone fleet, (c) a heterogeneous irredundant drone fleet, and (d) a heterogeneous hot stable redundant drone fleet. For the listed topologies, reliability estimates were obtained as a function of the number of primary and redundant UAVs.