Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628918
V. Krizhanovski, V. Komarov, S. Serhiienko, V. Kryzhanovskyi
This work proposes application of dynamic Allan variance for detection of failures or external interventions in data acquisition systems, cyber-physical systems, and Internet-of-Things (IoT). The work analyzed a number of sample data sequences to which a random noise of various spectra was added by means of simulation starting from some point of time. It was demonstrated that the dynamic Allan variance could detect the changes in the statistical characteristics of the random data sequence caused by the added noise. This can be one of the methods of automatic data control in sensor networks.
{"title":"Application of Allan variance for data control in sensor networks","authors":"V. Krizhanovski, V. Komarov, S. Serhiienko, V. Kryzhanovskyi","doi":"10.1109/aict52120.2021.9628918","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628918","url":null,"abstract":"This work proposes application of dynamic Allan variance for detection of failures or external interventions in data acquisition systems, cyber-physical systems, and Internet-of-Things (IoT). The work analyzed a number of sample data sequences to which a random noise of various spectra was added by means of simulation starting from some point of time. It was demonstrated that the dynamic Allan variance could detect the changes in the statistical characteristics of the random data sequence caused by the added noise. This can be one of the methods of automatic data control in sensor networks.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127347850","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628959
A. Kuznetsov, Iryna Lokotkova, Oleksii Smirnov, T. Kuznetsova, Serhii Florov, O. Lebid
Spread-Spectrum Steganography (SSS) technology is used to hide information messages in image containers. For this purpose, propagating discrete signals are used, in specially formed pseudo-random sequences (PRS) with special correlation properties. This technology is similar to the direct-sequence spread spectrum (DSSS) used in telecommunications systems to reduce the effects of random noise in information channels. The properties of expansion PRS directly affect the quality of communication in DSSS and, accordingly, the efficiency of SSS. This article investigates various methods of PRS formation and conducts experiments to assess the intensity of bit errors and the quality of the image container. We show that it is most appropriate to use orthogonal discrete Walsh-Hadamard signals that provide the best performance.
{"title":"Using Orthogonal Signals to Hide Information in Images","authors":"A. Kuznetsov, Iryna Lokotkova, Oleksii Smirnov, T. Kuznetsova, Serhii Florov, O. Lebid","doi":"10.1109/aict52120.2021.9628959","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628959","url":null,"abstract":"Spread-Spectrum Steganography (SSS) technology is used to hide information messages in image containers. For this purpose, propagating discrete signals are used, in specially formed pseudo-random sequences (PRS) with special correlation properties. This technology is similar to the direct-sequence spread spectrum (DSSS) used in telecommunications systems to reduce the effects of random noise in information channels. The properties of expansion PRS directly affect the quality of communication in DSSS and, accordingly, the efficiency of SSS. This article investigates various methods of PRS formation and conducts experiments to assess the intensity of bit errors and the quality of the image container. We show that it is most appropriate to use orthogonal discrete Walsh-Hadamard signals that provide the best performance.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131737626","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628961
Chunzhi Wang, Le Yuan, M. Medvetskyi, M. Beshley, A. Pryslupskyi, H. Beshley
The use of artificial intelligence in modern technology is not a novelty. However, its use in telecommunication systems is little studied. This is not surprising because the implementation of third-party software modules in traditional networks is too complex, in contrast to software-defined networks, which have become very popular in the last few years. This paper presents the development of a machine learning module for predicting QoE (Quality of Experience) in software-defined networks. The module allows to predict and provide customer-defined quality of service and reduce the load on network equipment by reducing the amount of signaling traffic in the network. A software-defined network architecture with an integrated machine learning module is proposed. The study compared the predicted QoE level and the results obtained with the QoE monitoring system in the virtual network in the Mininet environment. In addition, graphs of the network load by signal packets using the machine learning module and the standard monitoring system are presented. We have proven that using a machine learning module reduces signaling traffic on the network by 30%.
{"title":"Machine Learning-Enabled Software-Defined Networks for QoE Management","authors":"Chunzhi Wang, Le Yuan, M. Medvetskyi, M. Beshley, A. Pryslupskyi, H. Beshley","doi":"10.1109/aict52120.2021.9628961","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628961","url":null,"abstract":"The use of artificial intelligence in modern technology is not a novelty. However, its use in telecommunication systems is little studied. This is not surprising because the implementation of third-party software modules in traditional networks is too complex, in contrast to software-defined networks, which have become very popular in the last few years. This paper presents the development of a machine learning module for predicting QoE (Quality of Experience) in software-defined networks. The module allows to predict and provide customer-defined quality of service and reduce the load on network equipment by reducing the amount of signaling traffic in the network. A software-defined network architecture with an integrated machine learning module is proposed. The study compared the predicted QoE level and the results obtained with the QoE monitoring system in the virtual network in the Mininet environment. In addition, graphs of the network load by signal packets using the machine learning module and the standard monitoring system are presented. We have proven that using a machine learning module reduces signaling traffic on the network by 30%.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131183158","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628957
V. Strukov, Vladislav Gudilin
The purpose of the research work is to prove the effectiveness of the method of experimental investigation of web application security, which allows for a limited time to detect the maximum possible number of vulnerabilities in the computer systems, in order to fix promptly these security problems. Based on the results of an experimental study, the authors propose methodology for identifying appropriate types of vulnerabilities for cybersecurity professionals.
{"title":"Experimental Investigation of Web Application Security","authors":"V. Strukov, Vladislav Gudilin","doi":"10.1109/aict52120.2021.9628957","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628957","url":null,"abstract":"The purpose of the research work is to prove the effectiveness of the method of experimental investigation of web application security, which allows for a limited time to detect the maximum possible number of vulnerabilities in the computer systems, in order to fix promptly these security problems. Based on the results of an experimental study, the authors propose methodology for identifying appropriate types of vulnerabilities for cybersecurity professionals.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133440745","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628983
P. Kravets, V. Lytvyn, Y. Burov, V. Vysotska, L. Chyrun, V. Panasyuk
This work aims to develop the functions and structure of intelligent agents with fuzzy logic based on methods of reinforcement learning and their application to solve practical problems of decision-making in conditions of uncertainty. To achieve this goal, it is used fuzzy inference based on production rules knowledge bases to develop an algorithm for the operation of an intelligent agent. The empirical verification of the developed algorithm efficacy is carried out for the task of agent finding the optimal value of the function in the cell space with the determination of the direction of movement according to the rules of fuzzy logic.
{"title":"Making Optimal Decisions with Learning Method Based on Fuzzy Logic","authors":"P. Kravets, V. Lytvyn, Y. Burov, V. Vysotska, L. Chyrun, V. Panasyuk","doi":"10.1109/aict52120.2021.9628983","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628983","url":null,"abstract":"This work aims to develop the functions and structure of intelligent agents with fuzzy logic based on methods of reinforcement learning and their application to solve practical problems of decision-making in conditions of uncertainty. To achieve this goal, it is used fuzzy inference based on production rules knowledge bases to develop an algorithm for the operation of an intelligent agent. The empirical verification of the developed algorithm efficacy is carried out for the task of agent finding the optimal value of the function in the cell space with the determination of the direction of movement according to the rules of fuzzy logic.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"352 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134544034","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628925
E. Lavrov
The article deals with the problems of the so-called human factor in automated systems. The author substantiates the need for a comprehensive human-system approach to the design and operation of computerized systems of various purposes, describes the functional network methodology used to describe and evaluate operator-automation interaction, analytical and simulation modeling technology to obtain predictive estimates of interaction quality in automated systems (error-freeness, timeliness, information load and operator workload). The author shows the place of the developed models in decision support systems for the design and operation of automated systems.
{"title":"Methodology for Reliability Analysis of Human-Machine Interaction in Automated Control Systems","authors":"E. Lavrov","doi":"10.1109/aict52120.2021.9628925","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628925","url":null,"abstract":"The article deals with the problems of the so-called human factor in automated systems. The author substantiates the need for a comprehensive human-system approach to the design and operation of computerized systems of various purposes, describes the functional network methodology used to describe and evaluate operator-automation interaction, analytical and simulation modeling technology to obtain predictive estimates of interaction quality in automated systems (error-freeness, timeliness, information load and operator workload). The author shows the place of the developed models in decision support systems for the design and operation of automated systems.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133253701","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628893
D. Havrylov, Yeroshenko Valerii, R. Onyshchenko, Kateryna Zakomorna, Savchuk Maksym, Karaban Oleksandr
The aim of the article is to build a method of video processing with the possibility of its protection at the stage of quantization with subsequent arithmetic coding. That will allow at preservation of structural - statistical regularity to provide a necessary level of availability, reliability and confidentiality at video data transmission. Providing the required level of availability involves reducing the video volume by 30% compared to the original volume. In this case, the provision of the required level of reliability is confirmed by estimating the peak signal-to-noise ratio for the authorized user, which is PSNRaBT ≥ 20 dB. Ensuring the required level of confidentiality is confirmed by estimating the peak signal-to-noise ratio for unauthorized access, which is PSNRHCд ≤ 9 dB. The scientific novelty of the obtained results lies in the following: for the first time two methods of video image processing at the quantization stage are proposed. The method of using encryption tables has greater cryptographic stability, and the method of using the key matrix has greater speed. At the same time, the use of arithmetic coding will satisfy the need for availability by reducing the initial volume.
{"title":"Possible Ways of Video Processing at the Quantization Stage","authors":"D. Havrylov, Yeroshenko Valerii, R. Onyshchenko, Kateryna Zakomorna, Savchuk Maksym, Karaban Oleksandr","doi":"10.1109/aict52120.2021.9628893","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628893","url":null,"abstract":"The aim of the article is to build a method of video processing with the possibility of its protection at the stage of quantization with subsequent arithmetic coding. That will allow at preservation of structural - statistical regularity to provide a necessary level of availability, reliability and confidentiality at video data transmission. Providing the required level of availability involves reducing the video volume by 30% compared to the original volume. In this case, the provision of the required level of reliability is confirmed by estimating the peak signal-to-noise ratio for the authorized user, which is PSNRaBT ≥ 20 dB. Ensuring the required level of confidentiality is confirmed by estimating the peak signal-to-noise ratio for unauthorized access, which is PSNRHCд ≤ 9 dB. The scientific novelty of the obtained results lies in the following: for the first time two methods of video image processing at the quantization stage are proposed. The method of using encryption tables has greater cryptographic stability, and the method of using the key matrix has greater speed. At the same time, the use of arithmetic coding will satisfy the need for availability by reducing the initial volume.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121730386","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628895
S. Berezovsky
The problem of creating 2D, 3D midday models of switching circuits for the design of N-dimensional switching structures based on a physical object - switching element by Berezovsky is considered. Particular attention is paid to the development of an ontology of noon models of switching patterns based on elements by Berezovsky. Noon-models of switching schemes are constructed using algebraic lines of the 1st and 2nd orders. Midday Models allow you to incorporate the developer solver directly into the design process. This approach allows the solver to synthesize intelligently heuristic 2D and 3D switching structures based on the geometrization theorem for bounded manifolds.
{"title":"Ontology 3D Noon-Models of Switching Patterns on Elements by Berezovsky","authors":"S. Berezovsky","doi":"10.1109/aict52120.2021.9628895","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628895","url":null,"abstract":"The problem of creating 2D, 3D midday models of switching circuits for the design of N-dimensional switching structures based on a physical object - switching element by Berezovsky is considered. Particular attention is paid to the development of an ontology of noon models of switching patterns based on elements by Berezovsky. Noon-models of switching schemes are constructed using algebraic lines of the 1st and 2nd orders. Midday Models allow you to incorporate the developer solver directly into the design process. This approach allows the solver to synthesize intelligently heuristic 2D and 3D switching structures based on the geometrization theorem for bounded manifolds.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122379884","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628949
M. Klymash, M. Kyryk, I. Demydov, O. Hordiichuk-Bublivska, H. Kopets, N. Pleskanka
This article discusses the problems of processing large amounts of information in databases to more efficiently execute user queries. The methods of distributed machine learning were described in this research, which allow a faster analysis of large data. A modification of the distributed database system architecture was proposed, which ensures the effective application of machine learning methods. Software modeling of data arrays processing using distributed machine learning has been carried out. The obtained results indicate an increase in the efficiency of processing large amounts of information in databases using distributed machine learning methods.
{"title":"Research on Distributed Machine Learning Methods in Databases","authors":"M. Klymash, M. Kyryk, I. Demydov, O. Hordiichuk-Bublivska, H. Kopets, N. Pleskanka","doi":"10.1109/aict52120.2021.9628949","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628949","url":null,"abstract":"This article discusses the problems of processing large amounts of information in databases to more efficiently execute user queries. The methods of distributed machine learning were described in this research, which allow a faster analysis of large data. A modification of the distributed database system architecture was proposed, which ensures the effective application of machine learning methods. Software modeling of data arrays processing using distributed machine learning has been carried out. The obtained results indicate an increase in the efficiency of processing large amounts of information in databases using distributed machine learning methods.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124005840","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}
Pub Date : 2021-09-21DOI: 10.1109/aict52120.2021.9628935
I. Melnyk, A. Luntovskyy
The basic matrix algorithm for statement of parallel task in the cloud computing systems are considered in this paper. This algorithm is generally based on using the approach of arithmetic-logic relations and forming of recurrent matrixes. Possibility of using different error-coding methods for sending the request on parallelization task and receiving the answer is also considered. Comparative analyze of corrective ability of RS and convolutional codes is provided. As a result of provided investigations the relation for estimation the level of task parallelization is proposed. Choosing of convolutional codes for transmitting the data for parallelization the calculation task in cloud systems using of convolutional codes is recommended.
{"title":"Estimation of Level of Algorithms Parallelization and Efficiency of Using Different Error-Correction Codes in Cloud Realizations of Parallel Computing Algorithms","authors":"I. Melnyk, A. Luntovskyy","doi":"10.1109/aict52120.2021.9628935","DOIUrl":"https://doi.org/10.1109/aict52120.2021.9628935","url":null,"abstract":"The basic matrix algorithm for statement of parallel task in the cloud computing systems are considered in this paper. This algorithm is generally based on using the approach of arithmetic-logic relations and forming of recurrent matrixes. Possibility of using different error-coding methods for sending the request on parallelization task and receiving the answer is also considered. Comparative analyze of corrective ability of RS and convolutional codes is provided. As a result of provided investigations the relation for estimation the level of task parallelization is proposed. Choosing of convolutional codes for transmitting the data for parallelization the calculation task in cloud systems using of convolutional codes is recommended.","PeriodicalId":375013,"journal":{"name":"2021 IEEE 4th International Conference on Advanced Information and Communication Technologies (AICT)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121572757","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：