Kibernetika ta kompiuterni tekhnologiyi最新文献

{"title":"Parallel Implementation of Sparse Distributed Memory for Semantic Storage","authors":"R. Vdovychenko, V. Tulchinsky","doi":"10.34229/2707-451x.22.2.6","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.6","url":null,"abstract":"Introduction. Sparse Distributed Memory (SDM) and Binary Sparse Distributed Representations (Binary Sparse Distributed Representations, BSDR), as two phenomenological approaches to biological memory modelling, have many similarities. The idea of ??their integration into a hybrid semantic storage model with SDM as a low-level cleaning memory (brain cells) for BSDR, which is used as an encoder of high-level symbolic information, is natural. A hybrid semantic store should be able to store holistic data (for example, structures of interconnected and sequential key-value pairs) in a neural network. A similar design has been proposed several times since the 1990s. However, the previously proposed models are impractical due to insufficient scalability and/or low storage density. The gap between SDM and BSDR can be bridged by the results of a third theory related to sparse signals: Compressive Sensing or Sampling (CS). In this article, we focus on the highly efficient parallel implementation of the CS-SDM hybrid memory model for graphics processing units on the NVIDIA CUDA platform, analyze the computational complexity of CS-SDM operations for the case of parallel implementation, and offer optimization techniques for conducting experiments with big sequential batches of vectors.\u0000The purpose of the paper is to propose an efficient software implementation of sparse-distributed memory for preserving semantics on modern graphics processing units. \u0000Results. Parallel algorithms for CS-SDM operations are proposed, their computational complexity is estimated, and a parallel implementation of the CS-SDM hybrid semantic store is given. Optimization of vector reconstruction for experiments with sequential data batches is proposed.\u0000Conclusions. The obtained results show that the design of CS-SDM is naturally parallel and that its algorithms are by design compatible with the architecture of systems with massive parallelism. The conducted experiments showed high performance of the developed implementation of the SDM memory block. Keywords: GPU, CUDA, neural network, Sparse Distributed Memory, associative memory, Compressive Sensing.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46262489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structure of Projective Planar Subgraphs of the Graph Obstructions for Fixed Surface","authors":"V. Petrenjuk, Dmytro Petreniuk, O. Oryshaka","doi":"10.34229/2707-451x.22.2.2","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.2","url":null,"abstract":"Consider the problem of studying the metric properties of a subgraph Gv, where v is an arbitrary vertex of obstruction graphs G of a nonorientable genus, which will determine the sets of points of attachment of one subgraph to another and allow constructing prototypes of graphs-obstruction with number of vertices greater than 10 nonorientable genus greater than 1. This problem is related to Erdosh's hypothesis [3] on the coverage of obstruction graphs of an undirected surface of the genus k, where k > 0, the smallest inclusion of the set of k + 1st graph of the homeomorphic K5, or K3,3, in [4] constructively proved for 35 minors of obstruction graphs of the projective plane, a set of 62 with no more than 10 vertices of obstruction graphs and their splits for the Klein surface, as well as some obstruction graphs for other surfaces. In [5], the existence of a finite set of obstruction graphs for a non-orienting surface was proved. A similar problem was considered in [6], where models or prototypes of obstruction graphs were considered. The prototype of the graph-obstruction of the undirected genus, we will call the graphs that have their own subgraph graph-obstruction of the undirected genus. In [7, 8] the tangent problem of covering the set of vertices with the smallest number of cycles-boundaries of 2-cells was considered, the concept of cell distance is given in [9, 10], where the boundaries of an oriented genus of graphs formed from planar graphs and a simple star glued to some of its peaks. Hypothetically, it is possible to obtain them by recursive φ-transformation of the graph-obstruction of the projective plane and a copy of its planar subgraph given on vertices, edges or parts of edges, or simple chains, i.e. achievable parts of the so-called graph-basis (graph of homeomorphic graph Kuratovsky plane). We assume that instead of one subgraph there can be several copies of subgraphs of graphs-obstructions of the projective plane.The article has an introduction and two parts, in which the structural properties of subgraphs of obstruction graphs for an undirected surface, presented as a φ-image of one of the Kuratovsky graphs and at least one planar graph, are investigated. The metric properties of the minimal embeddings of the subgraphs of the obstruction graphs for undirected surfaces are considered, and the main result is Theorems 1, 2, and Lemma 3 as the basis of the prototype construction algorithm. Keywords: φ-transformation of graphs, nonorientable surface, prototypes of graph-obstruction.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48846403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Methodological Fundamentals of Information System Design in Crop Production","authors":"Y. Babenko","doi":"10.34229/2707-451x.22.2.10","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.10","url":null,"abstract":"Introduction. The creation of new technologies for precision agriculture is intended to increase productivity, labor efficiency and improve production processes. According to the World Food Program (WFP), 811 million people are chronically hungry, 283 million are in a state of starvation or close to starvation. An estimated 45 million more in 43 countries around the world are on the brink of starvation. Today's conditions require agriculture to feed a planet with an ever-growing population, minimize costs, and develop technologies that do not pollute the planet. Therefore, modeling of biological objects, research and design of intelligent systems for agriculture are of great interest to scientists around the world today.\u0000The purpose of the paper is development of the main approaches to building a full-scale experiment from the point of view of planning methodology, data processing, and model selection. The methodical basics, principles and practical component of planning an experiment in crop production are disclosed. The results of the development of the automatic decision-making system and the basic mathematical models for the construction of the information system are presented.\u0000Results. The basis of the study of the plant organism is a natural experiment. Field experiments in crop production are difficult to reproduce and face a number of difficulties related to the accuracy of the research methods used, which consist in the reliability and accuracy of the measurement results. \u0000For the first time, a multi-level information system for monitoring the condition and needs of plants, which contains a wireless sensor network, an ontologically controlled node, a global database, a knowledge base, an explanatory module, a control module, a computer, and a human-machine interface, which allows taking management decisions, was used for the research. decision. Our algorithm system is able to take into account the variability of changes in a multivariate environment. An information system where the chlorophyll fluorescence induction parameter, induction, measured in real time, acts as a control module. This is a promising way of adjusting irrigation regimes, monitoring the condition of plants and caring for perennial plantations.\u0000Conclusions. An important part of this work is the study of the effect of induction of chlorophyll fluorescence and the study of the methodology of research on photosynthesis. This effect is very sensitive to many changes in the plant. This is an advantage of the method and is a requirement for the research methodology or the specifics of its conduct. \u0000The study of plant objects faces a number of difficulties. Of special interest is the composition of the soil and the influence of soil characteristics on the growth and development of plants, for the creation of profile soil maps. Due to the fact that the plant object is not only a collection of individual systems inside the organism, but is also exposed to the constant influence","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46156891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of a Moore Automaton Circuit in a Mixed Element Basis","authors":"A. Barkalov, L. Titarenko, O. Golovin, O. Matvienko","doi":"10.34229/2707-451x.22.2.9","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.9","url":null,"abstract":"Introduction. The control unit is one of the most important building blocks of any digital system. The main function of the control unit is to coordinate the interaction between all system blocks. Therefore, the characteristics of a control unit circuit have a significant impact on the quality of the system as a whole.\u0000To represent the law of functioning of a control unit, the models of the Moore and Mealy finite state machines (FSM) are used. When synthesizing circuits of FSMs, it is necessary to solve a number of optimization problems, such as the reducing hardware amount, increasing performance, minimizing power consumption, joint optimization of hardware-temporal characteristics. Methods for solving these problems largely depend on the used logical elements.\u0000Currently, FPGA microchips are one of the main platforms in which modern digital systems are implemented. The main blocks in the FPGA, which are used in the implementation of FSM circuits, are embedded memory blocks (EMBs), logical blocks LUT (look-up table) and a system of programmable interconnections. The best characteristics are possessed by FSM circuits implemented with EMBs. However, EMBs are widely used to implement various operational blocks of digital systems. Therefore, the designer of a control unit circuitry can use a rather limited number of EMBs.\u0000Purpose of the article. The article deals with the extreme case when there is only a single \"free\" EMB available. In this case, the FSM circuit is represented by a network consisting of this EMB and LUTs. There is proposed a method for the synthesis of an FSM with the optimization of the number of LUTs, when only one EMB block is available for implementing some part of the circuit.\u0000The proposed method is based on the using classes of pseudoequivalent states of Moore FSMs. The states are coded in such a way that the state code consists of the code of the class of pseudoequivalent states and the code of a collection of microoperations.\u0000Results. Studies of the effectiveness of the proposed method were carried out on standard FSMs. FPGAs of the Virtex-7 family from Xilinx were used as an implementation platform. The research results showed that the proposed method allows reducing the number of LUTs in FSM circuits by 12 % – 19 % in comparison with the known methods. In all cases, only a single EMB was used.\u0000Conclusions. The effectiveness of the proposed method allows us to recommend it for use in the synthesis of FSMs if there is of an extreme shortage of EMBs. Keywords: Moore FSM, FPGA, LUT, EMB, pseudoequivalent states, synthesis.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44925497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Algorithm for Calculating Primary Spectral Density Estimates Using FFT and Analysis of its Accuracy","authors":"Olena Kolomys, Liliya Luts","doi":"10.34229/2707-451x.22.2.5","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.5","url":null,"abstract":"Introduction. Fast algorithms for solving problems of spectral and correlation analysis of random processes began to appear mainly after 1965, when the algorithm of fast Fourier transform (FFT) entered computational practice. With its appearance, a number of computational algorithms for the accelerated solution of some problems of digital signal processing were developed, speed-efficient algorithms for calculating such estimates of probabilistic characteristics of control objects as estimates of convolutions, correlation functions, spectral densities of stationary and some types of non-stationary random processes were built.\u0000The purpose of the article is to study a speed-efficient algorithm for calculating the primary estimate of the spectral density of stationary ergodic random processes with zero mean. Most often, the direct Fourier transform method using the FFT algorithm, is used to calculate it. The article continues the research and substantiation of this method in the direction of obtaining better estimates of rounding errors.\u0000Results. The research and substantiation of the method in the direction of obtaining more qualitative estimates of rounding errors, taking into account the errors of the input information specification, has been continued. The main characteristics of the given algorithm for calculating the primary estimate of the spectral density are accuracy and computational complexity.\u0000The main attention is paid to obtaining error estimates accompanying the process of calculating the primary estimate of the spectral density. The estimates of the rounding error and ineradicable error of the given algorithm for calculating the primary estimate of the spectral density, which appear during the implementation of the algorithm for the classical rounding rule for calculation in floating-point mode with τ digits in the mantissa of the number, taking into account the input error, are obtained.\u0000Conclusions. The obtained results make it possible to diagnose the quality of the solution to the problem of calculating the primary estimate of the spectral density of stationary ergodic random processes with a zero mean value by the described method and to choose the parameters of the algorithm that will ensure the required accuracy of the approximate solution of the problem. Keywords: primary estimation of spectral density, fast Fourier transform, discrete Fourier transform, rounding error, input error.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44291873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of the Antenna Unit of the Superconducting Magnetometer: Research of Weak Magnetic Signals","authors":"Y. Minov, P. Shpylovyi, Yevhenii Melnyk","doi":"10.34229/2707-451x.22.2.1","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.1","url":null,"abstract":"Introduction. The article describes the optimization of the superconducting antenna design and balancing method of the superconducting antenna of magnetometer. This magnetometer is designed to study the magnetic properties of materials, as well as non-invasive study of the distribution of magnetic particles in organs of small laboratory animals, when toxic particles or drugs are introduced into the animal's body. The superconducting antenna of the magnetometer is a second-order axial gradiometer and is a part of the flux transformer of the SQUID sensor. For stable operation within the dynamic range of the magnetometer, the antenna must have a balance degree of at least 1/1000. Traditionally, it is balanced in a separate tuning module (Helmholtz coils), which creates a homogeneous magnetic field with a high degree of uniformity.\u0000The purpose. The problem is that the subsequent displacement of the SQUID magnetometer unit into the measuring complex, even within the laboratory, reduces the degree of balance of the magnetometer due to objects that create a strong gradient magnetic field, which negatively affects the measurements. \u0000Results. As a solution of this problem, the some approaches are described in the article. In order to increase the uniformity of the field inside the solenoid and eliminate field distortions at its edges, the using of solenoid with a special arrangement of turns to balance the antenna directly at the measurement site was proposed. The balancing elements for the horizontal components of the magnetic field were eliminated. Also the antenna balancing element in the form of a ring along the vertical component of the magnetic field, which does not violate the symmetry of the antenna was applied. \u0000Conclusions. Using this approach, it is possible to optimize the design of the antenna unit and the balancing process of the magnetometer antenna with a sufficient degree of balance in the vertical component directly in the geometric center of the measuring system, which reduced the time of preparing the system for work and improved the metrological indicators of the system. Keywords: superconductivity, SQUID-magnetometry, axial gradiometer, antenna balance, optimization.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41750308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"To the Problems of the National State Recognition System Improving","authors":"M. Ogurtsov, V. Korolyov, Oleksandr Khodzinskyi","doi":"10.34229/2707-451x.22.2.8","DOIUrl":"https://doi.org/10.34229/2707-451x.22.2.8","url":null,"abstract":"Introduction. A rapid increase in the number of objects that simultaneously take part in combat operations in the air requires improvement of systems for recognizing military objects both in terms of qualitative and quantitative indicators. This requires the development of appropriate algorithms for identifying new-generation \"friend-foe\" objects. Such algorithms can be based on various methods of information security, in particular symmetric and asymmetric cryptographic algorithms and other methods of cryptography.\u0000The purpose of the article is to survey modern systems of state recognition of objects (SSRO), identify their shortcomings and provide recommendations for their elimination.\u0000Results. The requirements for SSRO as a system for processing, transmitting, securing information and identifying objects based on cryptography and computer security methods are defined. Common and distinctive features for civil and military identification systems are highlighted. The advantages and disadvantages of the existing SSRO are shown. Recommendations are formulated to address the shortcomings of the existing SSRO. An example of a stand and a hardware and software basis for studying SSRO algorithms with backup channels is given.\u0000Conclusions. Eliminating the shortcomings of the SSRO and improving the level of its reliability will require the implementation of the following organizational and technical measures.\u00001. Replacing the current state recognition system with a more modern one, which will support more modern cryptographic algorithms and a larger number of recognition objects. Adding support for radio tag recognition (RF tags).\u00002. Support for recognition lines in various directions, including \"ground – UAV\", \"plane – tank\", \"plane – UAV\" and others. Adding support for the NATO standard – STANAG 4579, adopted in 2001, and others.\u00003. Using of broad-spectrum signals to reduce the probability of detection and interception, as well as a number of signal-code structures and a working frequency grid. Keywords: Friend-or-Foe, object identification, cryptography, backup channels.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45360000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application the Wireless Sensory Network Cluster in Digital Agriculture","authors":"H. Antonova, A. Kedych","doi":"10.34229/2707-451x.22.1.7","DOIUrl":"https://doi.org/10.34229/2707-451x.22.1.7","url":null,"abstract":"The authors made a review of \"Information technology of express-estimation of plant state in large territories in stressful environment.\" The essence of digital agriculture and its main components are briefly described. The main part of the article describes the cluster of Wireless Sensor Network. The main components of the cluster and the principle of the cluster are given. The work of the cluster is based on the \"Information technology of express-estimation of plant state in large territories in stressful environment.\" This technology is based on the method of chlorophyll fluorescence induction. The introduction of new information technology into industrial digital agriculture will make it possible to determine in real time the condition of plants suffering from the influence of one or another stress factor and develop an appropriate managerial decision to compensate the influence of a certain factor. The main technical requirements for the wireless node of the cluster are the ability to work in the field conditions; easy location on the plant; low cost; lightweight up to 25 g, small size, etc. The WSN cluster is intended for use in the agricultural sector and for environmental monitoring. Using the data collected by the cluster and an express analysis of the state of plants is carried out, which allows making the necessary managerial decision on the use of fertilizers, fungicides, pesticides, herbicides and the need for irrigation. The authors took into account that the cultivation of corn for grain occupies a large sector in the agrarian sector of Ukraine and is an urgent task. The authors analyzed the industrial technology of growing of crop for grain and it was adapted for the information technology for measuring the CFI. The main points of the technological process for the use of the WSN cluster in industrial agriculture on the example of corn are determined, and on their basis, a scheme for measuring the CFI of plants by the WSN cluster was developed. A brief step-by-step methodology has been developed for using the WSN cluster in measuring the CFI of corn. The authors also presented an analysis of energy consumption in the WSN and proposed the ways to improve the energy efficiency of the WSN nodes. Keywords: sensors, wireless sensor network, express diagnostics of plant, smart agriculture.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46318695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Artificial Neural Network Technology for Prediction of Sunflower Harvest Losses","authors":"O. Zozulya, V. Domrachev, V. Tretynyk","doi":"10.34229/2707-451x.22.1.3","DOIUrl":"https://doi.org/10.34229/2707-451x.22.1.3","url":null,"abstract":"Introduction The current stage of economic development is characterized by digitalization. Digital technologies in crop production occupy leading positions in agrocybernetics.\u0000The digitalization of society has brought to the fore new methods of studying development processes, among which a significant role is played by deep learning and its most successful methods such as artificial neural networks.\u0000“Artificial neural networks (ANNs) have gained popularity an effective tool for offering solutions to a wide variety of different case studies of biological and agricultural background. Their effectiveness emanates from their ability to model complex relationships between observation data from sensors and predicted variables without relying on assumptions about the model structure hence they can predict the real nature of the nonlinear relation between input and output data.” Yield prediction is a major challenge in precision agriculture, closely associated to the adoption of best management practices, crop pricing and security. Various techniques and methodologies have been developed to predict crop yield in agriculture.\u0000Yield forecasting requires control of many parameters, including Moisture Content pH, Soil Organic Matter, Total Nitrogen and Organic Carbon, which complicates the forecasting process .\u0000The purpose of the paper. The purpose of this paper is to find out and substantiate the possibility of predicting the probable loss of the sunflower crop by the farmer based on the analysis of the distribution of the vegetation index in the field. Our hypothesis is that the distribution of the vegetation index significantly affects the percentage of losses, of course, with additional parameters.\u0000Results. The influence of parameters that characterize the harvest on its losses is, but a clear regression relationship can not be built. Therefore, the technology of artificial neural networks is used to build the model. The model is formed in the form of an algorithm at the input of which input parameters are given (value of vegetation index at the beginning of the study, change of index value during the study period, seed moisture in the accounting area, percentage of study area from field area), at the output we get the percentage of possible crop losses. The algorithm is automatically translated into a program in the C ++ programming language (or another programming language), which allows in practice to model the farmer's possible crop losses depending on his actions in relation to growing crops. Keywords: sunflower, machine learning, artificial neural networks, forecast model.","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45198422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recognition of Geometric Figures and Determination of Their Characteristics by Means of Computer Vision","authors":"O. Golovin","doi":"10.34229/2707-451x.22.1.6","DOIUrl":"https://doi.org/10.34229/2707-451x.22.1.6","url":null,"abstract":"Introduction. Many computer vision applications often use procedures for recognizing various shapes and estimating their dimensional characteristics. The entire pipeline of such processing consists of several stages, each of which has no clearly defined boundaries. However, it can be divided into low, medium, and high-level processes. Low-level processes only deal with primitive operations such as preprocessing to reduce noise, enhance contrast, or sharpen images. The processes of this level are characterized by the fact that there are images at the input and output. Image processing at the middle level covers tasks such as segmentation, description of objects, and their compression into a form convenient for computer processing. Middle-level processes are characterized by the presence of images only at the input, and only signs and attributes extracted from images are received at the output. High-level processing involves “understanding” a set of recognized objects and recognizing their interactions.\u0000Using the example of the developed software models for recognizing figures and estimating their characteristics, it is shown that the image processing process is reduced to transforming spatial image data into metadata, compressing the amount of information, which leads to a significant increase in the importance of data. This indicates that at the input of the middle level, the image should be as informative as possible (with high contrast, no noise, artifacts, etc.) because after the transformation of the spatial image data into metadata, no further the procedures are not able to correct the data obtained by the video sensors in the direction of improving or increasing the information content.\u0000Recognition of figures in an image can be realized quite efficiently through the use of the procedure for determining the contours of figures. To do this, you need to determine the boundaries of objects and localize them in the image, often the first step for procedures such as separating objects from the background, image segmentation, detection and recognition of various objects, etc.\u0000The purpose of the article is to study the image processing pipeline from the moment of image fixation to the recognition of a certain set of figures (for example, geometric shapes, such as a triangle, quadrilateral, etc.) in an image, the development of software models for recognizing figures in an image, determining the center of mass figures by means of computer vision.\u0000Results. We proposed and tested some variants of nonlinear estimating problem. The properties of such problems depend on value of regulating parameter. The dependence of estimation on value of parameter was studied. It was defined a range for parameter's value for which estimating problem gives adequate result for initial task.\u0000Numerical examples show how much volume of calculations reduces when using a dynamic branching tree.\u0000Conclusions. The results obtained can be used in many applications of computer vi","PeriodicalId":34598,"journal":{"name":"Kibernetika ta kompiuterni tekhnologiyi","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42413698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}