{"title":"Performance Analysis of Stego Images Detection Using Shallow Denoising Autoencoders","authors":"D. Progonov","doi":"10.1109/PICST54195.2021.9772180","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772180","url":null,"abstract":"Early detection of sensitive information leakage in communication systems is topical task today. This requires usage of advanced statistical processing methods for detection negligible changes of cover files, such as digital images, caused by message hiding. One of promising approaches for solving the task is learning an appropriate representation of cover and formed stego images that is sensitive to data embedding. This approach is widely used in modern stegdetectors based on utilization of convolutional neural networks. Achieving of high detection accuracy by stegdetector requires usage deep convolutional networks, whose computation-intensive re-train procedure limits fast adaptation to unknown embedding methods. For overcoming this limitation, we propose to use special types of neural networks, namely autoencoders that provides fast adaptation to changes of inputted data by preserving high restoration accuracy. The work is devoted to performance analysis of usage shallow denoising autoencoders for detection of stego images formed by advanced embedding methods. It is revealed that considered networks allows improving detection accuracy up to 1.5%-2% for the most difficult case of small cover image payload (less than 10%).","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114866273","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":"Evaluation of the Consistency Between the Network's Characteristics and the Video Data Traffic in Computer Systems","authors":"O. Tymochko, P. Open’ko, V. Larin","doi":"10.1109/PICST54195.2021.9772220","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772220","url":null,"abstract":"The current computer networks state is characterized by high growth rates of the volumes of information circulating in them, an increase in the number of users and the expansion of the provided services. However, the development speed of the consumer segment significantly exceeds the equipment functionality of modern networks. It leads to the inability to provide all applications with the required throughput. Therefore, the issues of improving existing and developing new technologies for processing data streams for transmission in computer networks are still relevant. The problem of up-to-date video delivery with controlled loss of quality in computer networks lies in several aspect levels. One of which includes the relevance for the practice of reconciling the variable video stream intensity and the dynamically available network characteristics. On the one hand, the variables are the structural and semantic characteristics of the video frames. This leads to variable values of the compressed video stream intensity. On the other hand, the variables are the characteristics of the network itself. This is due to network heterogeneity, load unevenness, network switching nodes, dynamically changing number of network users and their service needs.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131924582","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}
I. Shostko, A. Tevyashev, O. Zemlyaniy, Yuliia Kulia
{"title":"Introduction of Private LTE Networks to Provide Specific Communication Tasks in Various Spheres of Society and the State","authors":"I. Shostko, A. Tevyashev, O. Zemlyaniy, Yuliia Kulia","doi":"10.1109/PICST54195.2021.9772142","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772142","url":null,"abstract":"The work is devoted to the study of world experience in the implementation of private LTE networks to provide specific communication tasks in various spheres of society and the state. Private LTE is a network created within one organization. It is based on the same technology as the public networks of this standard, but is not connected to the public infrastructure. All its elements - from the sensors to the control center - are in a closed loop. A comparison of options for building private LTE networks. The possibility of connecting existing subscriber equipment using different wireless communication standards was evaluated; network deployment speed and configuration; ease of operation and maintenance; cost of building a private LTE network and its maintenance.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132879529","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}
A. Kuznetsov, N. Poluyanenko, S.O. Kandii, Yu. S. Zaichenko, D. Prokopovich-Tkachenko, Tatiana Katkova
{"title":"WHS Cost Function for Generating S-boxes","authors":"A. Kuznetsov, N. Poluyanenko, S.O. Kandii, Yu. S. Zaichenko, D. Prokopovich-Tkachenko, Tatiana Katkova","doi":"10.1109/PICST54195.2021.9772133","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772133","url":null,"abstract":"Nonlinear substitution boxes (S-boxes) use in most modern symmetric cryptoalgorithms. They are designed to mix input data and take the essential part in ensuring resistance against known cryptoanalytic attacks (differential, linear, algebraic and other methods of cryptoanalysis). However, the random formation of nonlinear substitutions with the required rates is an extremely complex mathematical problem. We observe the heuristic techniques of S-boxes informed search, in particular, we consider the cost function used in most known algorithms (eg, local search, gradient lift, annealing simulation, genetic search, etc.). The purpose of our research is to determine the specific parameters of the heuristic function, which on the one hand do not reduce the degree of awareness of search nodes, and on the other hand do not require significant computational costs. We investigate the influence of individual parameters on the value of the cost function and on the complexity of its calculation. We also provide specific recommendations for the formation of parameters for the heuristic search of S-boxes.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132391720","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}
N. Kuzmynchuk, O. Zyma, Olga Shayturo, T. Kutsenko, O. Terovanesova
{"title":"Security-Oriented Bankruptcy Management as a Basis for Ensuring the Enterprises Competitiveness: Information and Analytical Tool and Counteracting Crime (Legal Aspect)","authors":"N. Kuzmynchuk, O. Zyma, Olga Shayturo, T. Kutsenko, O. Terovanesova","doi":"10.1109/PICST54195.2021.9772179","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772179","url":null,"abstract":"It was undertaken the researches, the actualization of which is aimed at the substantiating scientific and practical and methodological approaches to security-oriented management of machine building enterprises in the context of the formation and implementation of information and analytical toolkit for bankruptcy diagnosis and counteracting crime (legal aspect). With the help of the methods of the logical generalization and system analysis it is substantiated the theoretical and methodical recommendations for the formation and realization of approaches to bankruptcy diagnostics of machine building enterprises of security management in the conditions of uncertainty and negative influence of the factors of external and internal environment which increases riskiness of activity. It is identified the expediency of using fuzzy modeling technology to bankruptcy probability of machine-building enterprises by applying the regression function of affiliation which allows for a qualitative diagnosis of the financial condition of the enterprise and to develop the strategic management measures aimed at maintaining financial stability, solvency and increasing competitiveness and enterprises competitiveness. The methodical approach to the estimation and forecasting of bankruptcy probability is substantiated forming the information and analytical toolkit of maintenance of security management process of the enterprises and allows to direct administrative efforts on the decision of the revealed problem spheres of activity and threats and timely identification of weak links in the process of diagnosing bankruptcy which is reinforced by the imperfect regulatory framework in the field of ensuring of the enterprises bankruptcy.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"366 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116562657","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}
H. Khudov, I. Khizhnyak, D. Misiuk, N. Shamrai, V. Chepurnyi, Igor Ruban, O. Makoveichuk, Vladyslav Khudov, I. Butko
{"title":"The Improved Mathematical Model for Interpretation of Satellite Imagery","authors":"H. Khudov, I. Khizhnyak, D. Misiuk, N. Shamrai, V. Chepurnyi, Igor Ruban, O. Makoveichuk, Vladyslav Khudov, I. Butko","doi":"10.1109/PICST54195.2021.9772162","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772162","url":null,"abstract":"The paper proposes the mathematical model for interpretation of satellite imagery. The groups of existing models for interpreting the results of remote sensing of Earth, their advantages and disadvantages were analyzed. The model for interpretation of satellite imagery is formulated in overall form. It presented as an action of next operators: the operator of coordinate transformations, operators of image clustering and operators of zoning according to selected criterion. These operators are considered in detail. Thus, the mathematical model for interpretation of satellite imagery is proposed, which carries out the reverse transformation of coordinates of imagery into cartographic coordinates and the clustering of the image into separate classes according to color and texture. Also, this model takes into account geographic zoning, which provides the possibility of advanced analysis and forecasting of temporal dynamics of data in geospatial information processing systems.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121930602","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}
V. Derbentsev, Vitalii Bezkorovainyi, Marina Silchenko, Andrii V. Hrabariev, Oksana Pomazun
{"title":"Deep Learning Approach for Short-Term Forecasting Trend Movement of Stock Indeces","authors":"V. Derbentsev, Vitalii Bezkorovainyi, Marina Silchenko, Andrii V. Hrabariev, Oksana Pomazun","doi":"10.1109/PICST54195.2021.9772235","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772235","url":null,"abstract":"This paper is discussed the problems of the short-term forecasting of trend movement stock indices using supervised Machine (Deep) Learning approach. For this purpose, we used Recurrent Neural Networks (RNNs) based on cells of Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNNs), and stacking CNN- RNN. The main advantage of proposed approach is that CNN allows to automatically extracting features and hidden patterns from the data, which are pass to the input of the block LSTM for making prediction. For evaluation models we used daily data of five stock indices from 01/01/2015 to 1/06/2021. To assess the forecasting performance, we used the confusion matrix and Accuracy metrics and compared our results with Multilayer Perceptron (MLP) as a baseline. According to obtained results, stacking CNN-RNN outperformed MLP for all time series, but the LSTM model shown better results in flat conditions.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130344434","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}
O. Romanov, Volodymyr Mankivskyi, L. Veres, Ivan Saychenko
{"title":"Analysis of Performance in Docker Net deployed in AWS cloud","authors":"O. Romanov, Volodymyr Mankivskyi, L. Veres, Ivan Saychenko","doi":"10.1109/PICST54195.2021.9772184","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772184","url":null,"abstract":"The virtualization based on containers is a technological approach in building nowadays information systems. This approach provides a platform for various operating system services not only in the cloud but also in the local enterprise environment. This facilitates the creation of multiple containers on a single physical machine in the form of hypervisors. To accommodate many microservices, the technology is a model that consists of various operations performed by deployed services. Thus, the demand for low-overhead virtualization technology is growing rapidly. There are many easy virtualization technologies; Docker is one of them, which is an open source platform. This technology allows developers and system administrators to create, build, and run programs with minimal resources involved. This approach has become an integral part of the new development culture (DevOps).","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127114815","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}
I. Volk, A. Artyukhov, T. Vasylieva, Vita Hordiienko
{"title":"Quality of Education and Socio-Economic Development: Decision Making Approach for Assessing System Performance","authors":"I. Volk, A. Artyukhov, T. Vasylieva, Vita Hordiienko","doi":"10.1109/PICST54195.2021.9772207","DOIUrl":"https://doi.org/10.1109/PICST54195.2021.9772207","url":null,"abstract":"In this paper we propose versatile approach for evaluation of higher education institution performance in the framework of education quality. The model allows both qualitative and quantitative quality indicators to be accounted in the education quality assessment procedure. We develop two-directional testing algorithm for the proposed evaluation system and demonstrate the possibility of its further use in the decision making process. Roles of stakeholders and external factors influencing education quality are assessed via the black - gray - white box approach.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129101181","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":"Blob-Based Cell Counting Accuracy for Medical Applications","authors":"V. Baliar, Katya Mokriak, O. Mazurkiewicz","doi":"10.1109/picst54195.2021.9772200","DOIUrl":"https://doi.org/10.1109/picst54195.2021.9772200","url":null,"abstract":"This article concentrated on the performance estimation of blob-based image segmentation for object counting. The purpose of these studies is to estimate algorithm efficiency in terms of faults and correct detections and obtain corresponding dependencies considering specific nature of medical images. For study implementation Matlab model with definition of relative methodology was used. As result of study, relative algorithms and the implementations of the modern information systems are considered; qualitative and numeric efficiency assessments for the segmentation algorithm and for filtering the cells on the basis of intellectual information systems are obtained. The obtained results can be used during the providing of relative systems in medicine and during algorithms improvements at scientific studies.","PeriodicalId":391592,"journal":{"name":"2021 IEEE 8th International Conference on Problems of Infocommunications, Science and Technology (PIC S&T)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129157797","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}