Кафедри
Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/35393
Переглянути
4 результатів
Результати пошуку
Документ Conveyorized implementation of aswm image filter on PLD(PC Technology Center, 2021) Vasylchenkov, Oleg; Liberg, Igor; Mozhaiev, Mykhailo; Salnikov, DmytroThe object of research is the adaptive switching weighted median image filter (ASWM) algorithm. This algorithm is one of the most effective in the field of impulse noise suppression. The computational complexity and algorithmic features of this adaptive nonlinear filter make it impossible to implement a filter that works in real time on modern PLD microcircuits. The most problematic areas of the algorithm are the weight coefficient estimation cycle, which has no limit on the number of iterations and contains a large number of division operations. This does not allow implementing the filter on PLDs with a sufficiently effective method. In the course of the research, the programming model of the filter in Python was used. The performance of the algorithm was assessed using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM) metrics.Modeling made it possible to find out empirically the number of iterations of the cycle for estimating the weight coefficients at different levels of noise density and to estimate the effect of artificial limitation of the maximum number of iterations on the filter performance. Regardless of the intensity of the noise impact, the algorithm performs less than 40 iterations of the evaluation cycle. Let’s also simulate the operation of the algorithm with different variants of the division module implementation. The paper considers the main of them and offers the most optimal in terms of the ratio of accuracy/hardware costs for implementation. Thus, a modified algorithm was proposed that does not have these disadvantages.Thanks to modifications of the algorithm, it is possible to implement a pipelined ASWM image filter on modern PLDs. The filter is synthesized for the main families of Intel PLDs. The implementation, which is not inferior in terms of SSIM and PSNR metrics to the original algorithm, requires less than 65,000 FPGA logical cells and allows filtering of monochrome images with FullHD resolution at 48 frames/s at a clock frequency of 100 MHz.Документ Method of modeling of a social profile using Big Data structure transformation optimization(Національний технічний університет "Харківський політехнічний інститут", 2021) Mozhaiev, Mykhailo; Buslov, PavloThe object of the research are methods and algorithms of optimizing of the Big Data transformation to build a social profile model, the subject of the research are methods of constructing of a social profile. For decision-making person, the problem of scientific methodological and instrumental re-equipment is relevant for the effective fulfillment of a set of managerial tasks and confronting of fundamentally new challenges and threats in society. This task is directly related to the problem of building of a model of the social profile of both the individual and the social group as a whole. Therefore, the problem of optimizing of methods of constructing of a mathematical model of a social profile is certainly relevant. During the research, methods of the mathematical apparatus of graph theory, database theory and the concept of non-relational data stores, Big Data technology, text analytics technologies, parallel data processing methods, methods of neural networks' using, methods of multimedia data analyzing were used. These methods were integrated into the general method, called the method of increasing of the efficiency of constructing of a mathematical model of a social profile. The proposed method improves the adequacy of the social profile model, which will significantly improve and simplify the functioning of information systems for decision -making based on knowledge of the social advantages of certain social groups, which will allow dynamic correction of their behavior. The obtained results of testing the method make it possible to consider it as an effective tool for obtaining of an objective information model of a social portrait of a social group. This is because the correctness of setting and solving of the problem ensured that adequate results were obtained. Unlike the existing ones, the proposed modeling method, which uses an oriented graph, allows to improve significantly the quality and adequacy of this process. Further research should be directed towards the implementation of proposed theoretical developments in real decision-making systems. This will increase the weight of automated decision-making systems for social climate analysis.Документ Modeling nonlinear elements of critical computer network(Національний технічний університет "Харківський політехнічний інститут", 2020) Mozhaiev, MykhailoThe subject of research discussed in the paper is indicators of a critical network performance. The research targetis a model of nonlinear elements of a critical network. The research objectiveis creation of a model for nonlinear elements of computer network (CN) telecommunications facilities of a critical system providing the desired parameters of QoS. The paper fulfills the following tasks: analysis of the main factors causing impaired service quality in CN; creation of a model for a small nonlinearity impact on forming free oscillations by generating a relevant motion equation; analysis of oscillator free motion presented in the form of the Duffing equation; working out a general integral of the Duffing equation as applied to a stiff system.The research methods used are: the foundations of the theory of computer systems and networks and the nonlinear differential equations theory. The results obtained are as follows: the main factors presumably causing impaired network services of forensic systems are analyzed; it was found that one of the main causes is the telecommunications component of CN, which possesses a number of critical parameters, including lack of stability and robustness of data signal frequency; numerical simulation of the findings was performed. Conclusions: a formula was devised to define the relationship between the free oscillation frequency and the oscillation systemenergy with reference to nonlinearity which takes into account the parameters of the oscillation system initial state at startup; nonlinearity of the oscillation system of a self-oscillator has a significant impact on accuracy and stability of its output oscillation frequencies; it was determined that for equivalent nonlinearity parameter values k>0.1 there is a considerable mismatch between the reference signal and the actual signal transmitted in the network, which can cause a large deterioration of QoS; further research should be aimed at development of hardware-software tools making it possible to reduce the impact of small nonlinearities of telecommunications equipment elements of critical networks on quality of performance.Документ Analysis and comparative researches of methods for improving the software(Національний технічний університет "Харківський політехнічний інститут", 2020) Mozhaiev, Mykhailo; Davydov, Viacheslav; Liqiang, ZhangThe results analysis of main methods for identifying software vulnerabilities presents in the article. The results of authors’ research, synthesizing and regulating knowledge about systems for detecting software vulnerabilities, are presented. The software analysis methods used during certification tests are considered. It is shown that the methods and techniques existing for software security analysis use do not ensure the result accuracy under fuzzy input data conditions. This drawback is aggravated by strict requirements for the test scenarios implementation speed. This is largely due to the fact that experts, in order to a decision make, have to conflicting information large amounts analyzed. Consequently, it is necessary to develop a system for identifying vulnerabilities, the main task of which will be to the conflicting information amount minimize used by an expert when making a decision. The most promising direction the existing identifying vulnerabilities systems efficiency increasing is seen in reducing the burden on an expert by methods for identifying vulnerabilities and implementinga decision support system improving. This will significantly reduce the time spent on a decision making on software security, and, as a result, will the software security testing procedure accessible to a developer’s wide range make more.