Information, Computing and Intelligent systems

Method for Mapping Cyclo-Dynamic Dataflow Into Pipelined Datapath

2024-05-28T13:02:33+03:00

An overview of high-level synthesis (HLS) systems for designing pipelined datapaths is presented in the paper. The goal is to explore methods of mapping algorithms to the pipelined datapaths implementing the cyclic data flow graphs with dynamic schedules. The cyclo-dynamic dataflow (CDDF) is selected as the very expressive model for describing a wide domain of the dataflow algorithms. CDDF is distinguished in that, the algorithm period depends on the calculated data and has a dynamic schedule. A set of mapping conditions is formulated that provide the deadlock-free schedule of CDDF when it is mapped into the pipelined datapath. Due to the proposed method, the algorithm is represented by a set of CDDF and finite state machines (FSMs). The latter are subgraphs of CDDF. CDDF is optimized using retiming and pipelining methods. After that CDDF and its FSMs are described by the hardware description language like VHDL as well as the synchronous dataflow is described. The proposed method involves describing cyclo-dynamic data flow graphs in VHDL and optimizing them for implementation in the field programable gate arrays (FPGAs). The example of the sequence detector design shows the method implementation in detail. More sophisticated LZW decompression algorithm mapping demonstrates that the proposed method is rather effective and can give the pipelined datapath which effectivenes is comparable with that of the best hardware solution. The method can be implemented in modern HLS systems.

Time Portrait of the Student’s Behavior and Possibilities of its Use

2023-11-30T17:35:22+02:00

The object of research presented in this article is the process of classifying students' behavior based on a formalized description of task performance during a certain learning cycle.

The purpose of this study is to create a formalized description of the behavior of students regarding the performance of tasks during a certain learning cycle to improve the reliability of the characteristics of each student during automated data analysis in information systems.

To achieve this goal, a temporal portrait of the student's behavior is proposed. This is a stylized presentation of a time series in the form of a line, the shape of which represents the delay or advance of the deadlines for completing tasks when studying a certain discipline.

The main types of student behavior are highlighted. Each type of behavior corresponds to the shape of the line on the time portrait.

To provide information systems with the capabilities of behavior analysis, the issue of portrait classification by neural networks has been investigated. It is proposed to perform classification using a multilayer neural network. To speed up learning and facilitate further classification, it is proposed to divide the network into several subnets, each of which can be trained independently.

The issues of appropriate training of neural networks based on datasets of real training classes with groups of students are analyzed. The ability of the neural network to classify portraits of students' behavior has been proven.

The results of the research can be used for data analysis in computerized learning support systems

Method of Dynamic Reconfiguration of Software-Configured Networks

2024-05-29T15:10:10+03:00

The article presents a method of dynamic reconfiguration of a wireless software-configured network using random geometric intersection graphs.

Different implementations of SDN controllers have different characteristics, but despite the peculiarities of certain vendors, they can communicate with each other using the Openflow protocol. In the conditions of growth of various types of traffic and especially media, which is sensitive to delays, there is a problem in providing delay and speed indicators for data transmission channels.

The purpose of this study is to increase the fault tolerance of software-configured networks that use wireless communication methods. This will make it possible to continue data transmission and prevent information loss when certain communication channels are lost, or they are overloaded by other networks or means of influence.

The object of research is the process of generating the topology of a software-configured network using graph theory, namely, random geometric intersection graphs. Also, the object of the study is the impact of the wireless communication channel load on the quality characteristics of the data transmission channels.

To achieve the goal, the following tasks were set:

- analyze the methods of using different types of random graphs to generate the topology of software-configured networks. Determining the characteristics of graphs that affect network fault tolerance indicators.

- determine the influence of the wireless channel load indicator on the data transfer rate. Conduct research with different types of access point settings in IEEE 802.11 n, ac, ax protocols with different multi input multi output (MIMO) modes.

As a result of the study, the clustering coefficients were compared and an algorithm was developed for generating the topology for a software-configured network using random geometric intersection graphs. The impact of communication channel congestion in wireless networks was also investigated. MIMO has been found to affect network performance more than QAM and OFDMA.

The results of practical studies confirm the correctness of the selected methods for the reconfiguration of wireless SDN networks.

Method of Increasing Data Transmission Stability in Software Defined Network Considering Metrics of Quality of Service

2024-05-07T16:55:16+03:00

This article presents a description of the method of increasing the stability of data transmission in a software-defined network (SDN) by means of its dynamic reconfiguration, considering the parameters of the quality of service (QoS) of communication channels and the reliability of nodes.

The existing algorithms do not provide a comprehensive solution to the problem of determining the most optimal path that would provide a connection from the source point to the destination. They consider only certain parameters of the network, depending on which the time spent on communication between nodes is less than in the case of other routes. In conditions of growth in the number of users of computer networks and the number of node switches, there is an urgent problem of increasing the stability of data transmission in branched computer networks. It is proposed to solve this by considering the quality of service parameters of communication channels when constructing routes.

The aim of the research is to increase data transmission stability in a virtual software-defined network in conditions of failures of nodes and increasing loads on communication channels.

The first objective of the research is to create a method for finding a set of non-intersecting optimal paths that would consider various metrics of the quality of service of communication channels. The second research objective is to develop a dynamic reconfiguration mechanism for SDN switch flow tables to be able to reroute traffic in the event of individual node failure.

In the course of the research, the first objective was performed by mathematically substantiating the construction of the generalized weight matrix of transitions between the nodes of the network graph. When creating a request to determine a route for traffic in the network, its status and indicators are updated in order to increase the accuracy of data on available resources and establish the optimal path that meets the quality of service criteria. It is proposed to consider four quality of service metrics for path construction: the number of hops between vertices, the available bandwidth, the time delay, and the percentage of lost packets. Using the generalized transition weight matrix, the SDN controller selects the most optimal path among a set of alternative non-intersecting paths. Then, using the reliability coefficients of the nodes as a constraint to choose the optimal path between the vertices, the controller chooses the main route from the set of alternatives according to the requirement for the reliability of the nodes set by the administrator, and considers the other routes as backup.

The second task was solved by proposing a method of dynamic network reconfiguration using known paths. If in the process of traffic transmission there is a failure in the intermediate links of the network or the communication channels between them, then monitoring data of the SDN controller are used for reconfiguration and bypassing the problem area, which allows the controller to quickly choose an alternative path for sending traffic and build a new path based on already known data about communication channels in the network.

The obtained results of theoretical studies testify to the correctness of the chosen solutions and proposals for the objectives set in the article.

Some Aspects of Improvement of the Run Length Encoding Compression Method

2023-12-01T00:04:40+02:00

The object of research presented in this article is the RLE method and its application to the compression of bitmap images.

The purpose of this research is to invent more advanced codeword formats for packing chains of repeated pixels compatible with coding single pixels of an image to increase the degree of compression by the RLE method.

To achieve this goal, a generalization of the known formats of code words in the form of a corresponding structural model was performed. This made it possible to find some directions for improvement of RLE coding. Several new ways of packing chains of pixels together with single pixels are proposed to increase the degree of image compression compared to the already-known versions of RLE. These latest methods are included in the set of packaging methods called RLE_BP. The RLE_BP encoder automatically searches for the optimal parameters of the codewords to achieve the minimum possible amount of binary code for a particular image.

Experimental studies of raster compression based on synthetic tests were performed to compare the proposed coding methods with known implementations of the RLE method. The proposed coding methods allow to achievement of greater compression of certain categories of high-resolution bitmap images compared to known ones.

The results of the performed research can be used to build a wide class of hardware and software tools.

Method оf Load Balancing іn Distributed Three-Layer IoТ Architecture

2024-09-16T17:36:25+03:00

Due to the growing number of IoT devices and the need for fast data processing with minimal delays, traditional cloud computing is becoming less efficient. To solve this problem, the concept of edge computing is used, which, although it increases performance, complicates system management and requires effective load distribution to ensure a balance between the use of edge nodes and the speed of computation. The purpose of this work was to develop a method of load balancing in the three-layer architecture of the IoT system, taking into account the actual loading of nodes.

A review of the literature was conducted and an architectural concept was chosen that corresponds to new trends and consists of three layers: devices that generate data, edge nodes that process information, and the cloud that stores data and provides it to users. A system prototype was created, which includes several Edge nodes based on the Ubuntu Server 24.04 operating system and data servers based on Raspberry Pi Desktop. A mathematical model has been developed that allows you to estimate the load on nodes depending on the type of tasks performed. On the created prototype, the efficiency of the method was checked using a mathematical model.

The research results showed that the developed method successfully distributes the load between Edge-nodes with the help of special scripts and elements of the monitoring system, which is reflected in the server load graph. The proposed method can improve system performance due to automatic load distribution among nodes. This approach can become part of a more comprehensive strategy to improve the performance and reliability of IoT systems using edge computing. Using components of the monitoring system for different platforms with different power allows to reduce the cost of the system by using cheaper and less powerful computing devices.

Combining Pretty Good Privacy and Role-Based Access Control Technologies for Access Protection to Confidential Data

2024-05-29T21:52:00+03:00

This article presents a granular access protection model for confidential information, combining PGP (Pretty Good Privacy) and RBAC (Role-Based Access Control) technologies. The aim of the research is to develop and justify a model that ensures a high level of security through efficient data encryption and flexible role-based access management. The article examines the research objects, which include modern information systems processing confidential data, and the subject of the study, which encompasses encryption and access control methods.

To achieve the stated goal, an analysis of modern approaches to data encryption and access management was conducted, their advantages and disadvantages were studied, and current issues related to data security at rest were identified. A protection model combining PGP and RBAC was developed, implemented in real conditions, and tested to evaluate its efficiency and usability. PGP usage ensures data security at rest and during transmission, while RBAC allows flexible configuration of user access rights.

Research results demonstrated that the proposed model provides a high level of security, flexible access management, and improved system performance. The use of public and private keys for encrypting symmetric keys further enhances protection by preventing unauthorized data access. Defining roles and privileges for each user ensures authorized access to confidential information, minimizing the risk of accidental or malicious data access. Despite the complexity of encryption and key management processes, the system showed high performance, optimized encryption and decryption processes, and effective user role and privilege management. The proposed model proved its effectiveness in ensuring a high level of security and flexible access management for confidential data.

Comparative Review of Drone Simulators

2024-03-25T18:13:01+02:00

The rapid development of Unmanned Aerial Vehicles (UAVs), particularly drones, has revolutionized various sectors, including agriculture, mapping, search and rescue operations and more. There is an urgent need for simulation environments to develop algorithms for complex trajectory evolutions in tasks like package delivery and environmental monitoring, to avoid the significant risks associated with real-world testing. One of the primary challenges in UAV research is the diversity and fragmentation of available simulation tools, complicating the selection of appropriate simulators for specific practical tasks. Researchers must balance trade-offs such as simulation speed, the accuracy of physical law emulation, sensor integration, and user interface quality. The absence of a universal simulator that includes high-fidelity physics, comprehensive sensor modeling, and scalability for drone swarm simulations is a significant issue. Known UAV simulators have certain advantages and disadvantages, but none provide a comprehensive solution to meet all the requirements for modern research and development. Integrating various sensors, such as cameras, LiDAR, GPS, and IMUs, into simulation systems remains a technical challenge, limiting the applicability of existing simulators. Additionally, the availability and support infrastructure for effective simulators can vary significantly, impacting their adoption and sustainability. Therefore, the main problem is the lack of a universal simulator that meets the diverse and specific needs of UAV research and development. A standardized approach to UAV simulation could improve the comparability of research results, simplify selection efforts, and create a unified basis for evaluating simulator performance. Advances in aerodynamic modeling, especially for quadcopters and fixed-wing UAVs, could enhance simulation accuracy and realism, better supporting the development of advanced technologies. Future research aims to develop more comprehensive, high-fidelity, and scalable simulation environments. This involves integrating innovative sensor modeling approaches, improving swarm dynamics modeling, and enhancing user accessibility and support. Key areas for improvement include sensor integration to model a wide range of sensors, improving swarm dynamics simulation to effectively model complex behaviors and interactions among multiple drones, simplifying user interfaces, providing comprehensive documentation, ensuring robust community support, developing standardized criteria for comparing and evaluating different simulators, and incorporating detailed aerodynamic principles to enhance simulation accuracy. Addressing these issues in the development of UAV simulators is crucial for advancing aerial robotics. Developing simulation environments with integrated advanced sensor capabilities, improved swarm dynamics modeling, and user-friendly interfaces can enhance the effectiveness and efficiency of UAV development. Standardized evaluation criteria and detailed aerodynamic modeling will support the evolution of UAV technologies, ensuring safer, more reliable, and innovative applications across various sectors. These enhancements will foster innovation, technological progress, and operational efficiency in real-world conditions.

Integration of Blockchain Technology into the Internet of Things (Overview)

2024-09-19T12:11:59+03:00

One of the modern trends in the development of information and communication technologies that have evolved into the Internet of Things (IoT) paradigm is the progressive idea of using blockchain technology in IoT. This trend is described in a large number of modern literature sources, which point out the significant advantages of using blockchain, primarily related to decentralization, immutability, transparency and security. This allows us to conclude that the implementation of blockchain technology in IoT information and communication systems is highly relevant. However, the authors of different studies describe significant problems, including the problem of scalability of the blockchain itself, as well as the problems of energy efficiency and limited resources in IoT devices. Due to these problems, the implementation of blockchain technology in the Internet of Things is becoming a challenge and determines the relevance and feasibility of researching this topic and finding effective solutions related to the integration of two very powerful technologies in modern information and communication systems.

The article presents an analytical overview of the issues of integrating blockchain technology into IoT, in particular, the use of the Proof-of-Work (PoW) consensus algorithm in IoT and the use of alternative blockchain protocols, including IOTA, Ethereum Light Client and Litecoin, which allow increasing the efficiency of performing tasks in IoT infrastructure, taking into account the limited resources of devices; existing problems and implementation methods, such as the use of light clients and proxy servers. The article also considers the feasibility of using a full blockchain node on IoT devices and ways to increase system efficiency by pre-processing data before sending it to the blockchain network. The article also highlights the problem of insufficient implementation of blockchain technology in various spheres of human life, as well as the search for the reasons for this problem.

The results of the analytical review make it possible to substantiate the purpose and advantages of integrating blockchain technology into the Internet of Things, as well as to summarize the main issues and substantiate a number of tasks for relevant and progressive scientific research in the field of modern information and communication systems.