DOI: 10.7256/2454-0714.2024.1.69900

EDN: HYTKBH

Abstract: The study is dedicated to analyzing methods and tools for optimizing the performance of high-load systems using cloud, fog, and edge technologies. The focus is on understanding the concept of high-load systems, identifying the main reasons for increased load on such systems, and studying the dependency of the load on the system's scalability, number of users, and volume of processed data. The introduction of these technologies implies the creation of a multi-level topological structure that facilitates the efficient operation of distributed corporate systems and computing networks. Modern approaches to load management are considered, the main factors affecting performance are investigated, and an optimization model is proposed that ensures a high level of system efficiency and resilience to peak loads while ensuring continuity and quality of service for end-users. The methodology is based on a comprehensive approach, including the analysis of existing problems and the proposal of innovative solutions for optimization, the application of architectural solutions based on IoT, cloud, fog, and edge computing to improve performance and reduce delays in high-load systems. The scientific novelty of this work lies in the development of a unique multi-level topological structure capable of integrating cloud, fog, and edge computing to optimize high-load systems. This structure allows for improved performance, reduced delays, and effective system scaling while addressing the challenges of managing large data volumes and servicing multiple requests simultaneously. The conclusions of the study highlight the significant potential of IoT technology in improving production processes, demonstrating how the integration of modern technological solutions can contribute to increased productivity, product quality, and risk management.

DOI: 10.7256/2454-0714.2024.1.70173

EDN: PQMMUM

Abstract: In the modern world, teamwork is becoming more and more common. Different participants may be in different places, but they still need to work together on the same project, including graphic diagrams. An important aspect of this approach is the ability to observe changes made by other participants in real time. This allows, first of all, to reduce the frequency of conflicts when simultaneously editing the same schema element. However, existing solutions for sharing data in real-time collaborative editing of graphical diagrams face a number of problems, such as delays in data transmission. The subject of research in this article is the development of a minimum viable web application that allows users to perform collaborative graphical editing of a canvas in real time. The object of the study is a model of the process of collaborative editing in real time, taking into account the resolution of emerging conflicts. The research methodology is based on a theoretical approach to identifying mathematical formulas that describe changes in the state of a document when it is jointly edited by users. The characteristics of the use of the HTTP and WebSocket protocols in multi-user client-server applications are given. To use the WebSocket protocol, the Socket.IO library is used. The application server is built using the Express framework. The authors' main contribution to the topic is a model of the real-time collaborative editing process, as well as a mechanism for detecting conflicts for any number of users and a conflict resolution function for each pair of conflicting changes when online collaborative editing of documents. Within the framework of this study, an algorithm for collaborative editing of graphic schemes in real time is additionally proposed and its implementation in the form of a software system is given. The algorithm proposed as a result of the study in the JavaScript programming language can be used as a basis for developing more rich web applications using the Socket.IO library and be the object of future research affecting multi-user interaction and real-time conflict resolution.

DOI: 10.7256/2454-0714.2024.1.70144

EDN: VPNJNF

Abstract: The objects of research are mobile operating systems and their shells. The subject of the study is the functionality of the Android, iOS and HarmonyOS operating systems, their history of creation and development trends. The authors consider in detail such aspects of the topic as the history of the creation of Android, iOS, HarmonyOS operating systems and TouchWiz, HTC Sense, MIUI and others shells, modern trends in the field of mobile operating systems, which reflect the influence of technological innovations and geopolitical aspects on the development of this sphere. They conduct a detailed analysis of the OS using performance testing applications (AnTuTu Benchmark, 3DMark Benchmark). The purpose of this research is to study the history of the development of mobile OS and shells from the origins to the current trends of technological progress. Research methods are based on the collection and systematization of information, analysis and comparison of systems, as well as performance tests. The scientific novelty of this article lies in the use of OS and shells in mobile devices that meet all the needs and requirements of the user, given the rapid development of digital technologies and their increasing introduction into our daily lives. The main conclusions of the study are the identification of the most common OS, the definition of modern trends, which include the integration of artificial intelligence, multimodality, security and privacy, as well as the expansion of flexibility and portability. The rapid development of technology and the universe of mobile applications makes mobile OS and shells key components of a successful user experience in the world of mobile technology. Understanding the history and current trends in the field of mobile operating systems and shells will allow to more accurately predict technological changes and potential impacts in the future.

DOI: 10.7256/2454-0714.2024.1.69437

EDN: WVZVVU

Abstract: Object-oriented approaches to programming have their own scope of applicability. For a number of tasks, preference is traditionally given to classical methods of structured programming. These preferences are not uncommon in a deterministic world and in machine-representation-oriented systems. Historically, classical methods developed from von Neumann's architecture of machine representation. While solving the problems of deterministic world the advantage of approaches, opposite to OOP is shown. For example, the Oberon modular language and system in classic distribution demonstrate minimalistic way of reliability, which differs from vast majority of program systems maximizing amount of features supported. Data-oriented programming technology also steps aside traditional object-oriented paradigm because data from code separation is needed. The instrumental approach proposed by author is linking Oberon technologies with data-oriented programming, keeping interface interaction mechanisms from OOP. The instrument with no data, but associated with data is introduced instead of an object. MultiOberon restrictive semantics makes an opportunity to turn off OOP restriction and switch on instruments usage. Instrument is instantiated automatically on program module loading. Instrument is queried either by its type or by the type of record associated. All the functionality is implemented in MultiOberon compiler. Instrumental approach was used for SCADA-platform software development, which targets complex automation and diagnostics. It is used in dynamically loaded plugins for data types matched shared memory data types. The instrumental approach offers a different branch of development from OOP for the classic Oberon programming language and the classical approach

DOI: 10.7256/2454-0714.2024.1.69919

EDN: WZDHQO

Abstract: The object of the research is artificial neural networks (ANN) with convolutional architecture for image classification. The subject of the research is the study and development of algorithms for constructing ensembles of convolutional neural networks (SNS) in conditions of limited training sample. The aim of the study is to develop an algorithm for the formation of an effective model based on an ensemble of convolutional SNS using methods of averaging the results of each model, capable of avoiding overfitting in the process of improving the accuracy of the forecast and trained on a small amount of data, less than 10 thousand examples. As a basic network, an effective SNA architecture was developed as part of the ensemble, which showed good results as a single model. The article also examines methods for combining the results of ensemble models and provides recommendations for the formation of the SNA architecture.  The research methods used are the theory of neural networks, the theory of machine learning, artificial intelligence, methods of algorithmization and programming of machine learning models, a comparative analysis of models based on different algorithms using classical ensembling with simple averaging and combining the results of basic algorithms in conditions of limited sampling, taking into account weighted average. The field of application of the obtained algorithm and model is medical diagnostics in medical institutions, sanatoriums during primary diagnostic admission, using the example of a research task, the model is trained to classify dermatological diseases according to input photographs. The novelty of the study lies in the development of an effective algorithm and image classification model based on an ensemble of convolutional NS that exceed the prediction accuracy of basic classifiers, the process of retraining an ensemble of classifiers with deep architecture on a small sample volume is investigated, from which conclusions are drawn on the design of an optimal network architecture and the choice of methods for combining the results of several basic classifiers. As a result of the research, an algorithm has been developed for the formation of an ensemble of SNS based on an effective basic architecture and weighted average averaging of the results of each model for the classification task of image recognition in conditions of limited sampling.

DOI: 10.7256/2454-0714.2024.1.69794

EDN: XAZVOW

Abstract: The study addresses the crucial topic of designing and implementing smart systems in agricultural production, focusing on the development of a "Smart Greenhouse" utilizing neural networks. It thoroughly examines key technological innovations and their role in sustainable agriculture, emphasizing the collection, processing, and analysis of data to enhance plant growth conditions. The research highlights the efficiency of resource use, management of humidity, temperature, carbon dioxide levels, and lighting, as well as the automation of irrigation and fertilization. Special attention is given to developing adaptive algorithms for predicting optimal conditions that increase crop yield and quality while reducing environmental impact and costs. This opens new avenues for the sustainable development of the agricultural sector, promoting more efficient and environmentally friendly farming practices. Utilizing a literature review, comparative analysis of existing solutions, and neural network simulations for predicting optimal growing conditions, the study makes a significant contribution to applying artificial intelligence for greenhouse microclimate management. It explores the potential of AI in predicting and optimizing growing conditions, potentially leading to revolutionary changes in agriculture. The research identifies scientific innovations, including the development and testing of predictive algorithms that adapt to changing external conditions, maximizing productivity with minimal resource expenditure. The findings emphasize the importance of further studying and implementing smart systems in agriculture, highlighting their potential to increase yield and improve product quality while reducing environmental impact. In conclusion, the article assesses the prospects of neural networks in the agricultural sector and explores possible directions for the further development of "Smart Greenhouses".