Pub Date : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813976
S. Yablochnikov, I. Yablochnikova, M. Kuptsov, I. Kuptsov, M. S. Yablochnikova
The synchronization of the processes of functioning of all components in socio-economic sphere determines the pace of its development. The education is an integral part of this sphere. Its quality depends on many different factors, primarily on the consistency of the results of educational processes and current demands of the labor market. Currently, there is no scientific interpretation of the notion of “quality of education”, methodology for determining its individual indicators and their integration into the generalized criterion. The purpose of this publication is to substantiate an innovative approach to the interpretation of the above-mentioned concept and to determine its adequate indicators, based on the principle of synchronization between the set of requirements of employers and real competencies of University graduates. Usually, the society evaluates the quality of education by determining the level of demand for specialists in the labor market, as well as their real ability to adapt in changing conditions. To a greater degree, the level of demand depends on the criteria, which are developed by employers for the selection of candidates for vacant positions. The adaptability closely correlates with intellectual potential, innovative behavior, leadership qualities and the ability to think creatively. The authors consider that the above criteria should be synchronized. The authors made an experiment and, using the theory of possibilities, synthetically produced a number of mathematical models, based on the obtained results. These models allowed to formulate and justify an integral quality indicator of the quality of the implementation of educational processes.
{"title":"To the Question of Synchronization of the Processes of Functioning of the Components of the Socio-Economic Sphere","authors":"S. Yablochnikov, I. Yablochnikova, M. Kuptsov, I. Kuptsov, M. S. Yablochnikova","doi":"10.1109/SYNCHROINFO.2019.8813976","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813976","url":null,"abstract":"The synchronization of the processes of functioning of all components in socio-economic sphere determines the pace of its development. The education is an integral part of this sphere. Its quality depends on many different factors, primarily on the consistency of the results of educational processes and current demands of the labor market. Currently, there is no scientific interpretation of the notion of “quality of education”, methodology for determining its individual indicators and their integration into the generalized criterion. The purpose of this publication is to substantiate an innovative approach to the interpretation of the above-mentioned concept and to determine its adequate indicators, based on the principle of synchronization between the set of requirements of employers and real competencies of University graduates. Usually, the society evaluates the quality of education by determining the level of demand for specialists in the labor market, as well as their real ability to adapt in changing conditions. To a greater degree, the level of demand depends on the criteria, which are developed by employers for the selection of candidates for vacant positions. The adaptability closely correlates with intellectual potential, innovative behavior, leadership qualities and the ability to think creatively. The authors consider that the above criteria should be synchronized. The authors made an experiment and, using the theory of possibilities, synthetically produced a number of mathematical models, based on the obtained results. These models allowed to formulate and justify an integral quality indicator of the quality of the implementation of educational processes.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128369171","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813930
E. V. Druk, K. E. Legkov, L. V. Levko
In article presented the model of decision support system heterogeneous onboard storage system function. The main difference of model is the fact of considering stored data importance. Model can be applied for analyses of different structures of data storage systems and ways of storage for different stages of lifecycle (from constructing to exportation). Modelling of data storage system function based on decomposition information processes of system, detection their interconnections and dependences of quality indicators from system structure and ways of storage.
{"title":"The System Approach to the Organization of Heterogeneous Data Storage System for Decision Support System","authors":"E. V. Druk, K. E. Legkov, L. V. Levko","doi":"10.1109/SYNCHROINFO.2019.8813930","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813930","url":null,"abstract":"In article presented the model of decision support system heterogeneous onboard storage system function. The main difference of model is the fact of considering stored data importance. Model can be applied for analyses of different structures of data storage systems and ways of storage for different stages of lifecycle (from constructing to exportation). Modelling of data storage system function based on decomposition information processes of system, detection their interconnections and dependences of quality indicators from system structure and ways of storage.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127226695","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813961
A. I. Volkov, V. G. Semin, E. R. Khakimullin
The article presents the results of the development of a method for analyzing the structure and estimating the parameters of multicomponent Gaussian signals. The results of solving the problems of modeling and analyzing the structure for different dimensions of linear mixtures of Gaussian time signals are presented. The results of solving the problems of modeling and estimating the parameters of typical variants of binary mixtures of signals with different degrees of overlap, formed by linear overlapping of elementary signals of the same shape, but differing in duration and amplitude, are given. Such signals are often found in applied problems of electrical engineering, radio engineering in a wide class of applied information-measuring systems. The method allows to estimate the true values of the parameters of signals subject to distortion as a result of overlap. This method does not require a priori information about the structure of a multicomponent signal; It has high accuracy and ease of computational implementation. The method provides the ability to automate the processing of multicomponent signals, expands the capabilities of primary information converters.
{"title":"Method of Analysis of the Structure and Estimation of Parameters of Linear Combinations of Gaussian Temporary Signals","authors":"A. I. Volkov, V. G. Semin, E. R. Khakimullin","doi":"10.1109/SYNCHROINFO.2019.8813961","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813961","url":null,"abstract":"The article presents the results of the development of a method for analyzing the structure and estimating the parameters of multicomponent Gaussian signals. The results of solving the problems of modeling and analyzing the structure for different dimensions of linear mixtures of Gaussian time signals are presented. The results of solving the problems of modeling and estimating the parameters of typical variants of binary mixtures of signals with different degrees of overlap, formed by linear overlapping of elementary signals of the same shape, but differing in duration and amplitude, are given. Such signals are often found in applied problems of electrical engineering, radio engineering in a wide class of applied information-measuring systems. The method allows to estimate the true values of the parameters of signals subject to distortion as a result of overlap. This method does not require a priori information about the structure of a multicomponent signal; It has high accuracy and ease of computational implementation. The method provides the ability to automate the processing of multicomponent signals, expands the capabilities of primary information converters.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126592409","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813960
E. N. Vilderman, L. Belov
This paper is a research on the possibility of forming an ensemble of orthogonal signals, which provides an approach to the maximum possible values of the transmission rate of, messages over Gaussian communication channels and its energy efficiency without the use of noise-resistant coding. The object of a study was a three-dimensional surface-spherical ensemble of eighteen signal points. A spatial signal diagram, idealized waveforms of summary signal and partial signals at subcarrier frequencies were examined to find out the possible problems that stand on the way of implementation of hyperphase modulation technology. An assessment of the prospects for the use of hyperphase modulation in typical data transmission systems, including satellite based are outlined in this paper.
{"title":"Hyperphase Signal for Communication Systems","authors":"E. N. Vilderman, L. Belov","doi":"10.1109/SYNCHROINFO.2019.8813960","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813960","url":null,"abstract":"This paper is a research on the possibility of forming an ensemble of orthogonal signals, which provides an approach to the maximum possible values of the transmission rate of, messages over Gaussian communication channels and its energy efficiency without the use of noise-resistant coding. The object of a study was a three-dimensional surface-spherical ensemble of eighteen signal points. A spatial signal diagram, idealized waveforms of summary signal and partial signals at subcarrier frequencies were examined to find out the possible problems that stand on the way of implementation of hyperphase modulation technology. An assessment of the prospects for the use of hyperphase modulation in typical data transmission systems, including satellite based are outlined in this paper.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"234 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125070473","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813991
S. Kozlov, A. N. Kubankov
The subject of research in the article is the structure of the main functional processes in the life cycle of high-tech integrated management systems and the conditions for its improvement to achieve a rational variant of the structure of processes in terms of their interoperability and synchronization, which constitute the full group of processes. The main provisions that determine the interrelation of interoperability of processes and the conditions of their synchronization are given. We consider the methodological approaches to the decomposition of the end-to-end process in the life cycle of high-tech integrated management systems, to the analysis of its components and their rational synthesis in the framework of the end-to-end process. In the course of decomposition, organizational, organizational, technical, and technical-technological processes are distinguished, constituting a complete group of processes that determine the functional properties and scope of an integrated management system. Their general description is presented. The classification of functional processes as part of their full group with the selection of the main, supporting and auxiliary processes is given. The description of the basic conditions for achieving synergistic properties of integrated control systems based on the synchronization of processes at the level of their components is considered. The basis for ensuring synchronization at the process level in the life cycle of management systems is based on the methods of decomposition of the end-to-end process in the life cycle of the management system, highlighting the organizational, organizational-technical and technical-technological processes that make up the full group of processes, methods for analyzing the nature of the interaction between processes based on modeling their attributes with the identification of the most vulnerable, in terms of ensuring consistency and synchronization of their implementation, with the required measures for their adjustment, holding (if necessary) at the next decomposition level component processes the same identifying vulnerable components processes, assembly processes with a view to ensuring the required synchronism during their implementation to create an integrated control system. During the decomposition and assembly of processes in the life cycle of a control system, the most preferable sets of process parameters should be determined by their attributes, which should be used as the basis for the technical requirements for its elements and the system as a whole.
{"title":"Scientific and Methodical Aspects of Synchronization of Functional Processes in the Life Cycle of Integrated Control Systems","authors":"S. Kozlov, A. N. Kubankov","doi":"10.1109/SYNCHROINFO.2019.8813991","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813991","url":null,"abstract":"The subject of research in the article is the structure of the main functional processes in the life cycle of high-tech integrated management systems and the conditions for its improvement to achieve a rational variant of the structure of processes in terms of their interoperability and synchronization, which constitute the full group of processes. The main provisions that determine the interrelation of interoperability of processes and the conditions of their synchronization are given. We consider the methodological approaches to the decomposition of the end-to-end process in the life cycle of high-tech integrated management systems, to the analysis of its components and their rational synthesis in the framework of the end-to-end process. In the course of decomposition, organizational, organizational, technical, and technical-technological processes are distinguished, constituting a complete group of processes that determine the functional properties and scope of an integrated management system. Their general description is presented. The classification of functional processes as part of their full group with the selection of the main, supporting and auxiliary processes is given. The description of the basic conditions for achieving synergistic properties of integrated control systems based on the synchronization of processes at the level of their components is considered. The basis for ensuring synchronization at the process level in the life cycle of management systems is based on the methods of decomposition of the end-to-end process in the life cycle of the management system, highlighting the organizational, organizational-technical and technical-technological processes that make up the full group of processes, methods for analyzing the nature of the interaction between processes based on modeling their attributes with the identification of the most vulnerable, in terms of ensuring consistency and synchronization of their implementation, with the required measures for their adjustment, holding (if necessary) at the next decomposition level component processes the same identifying vulnerable components processes, assembly processes with a view to ensuring the required synchronism during their implementation to create an integrated control system. During the decomposition and assembly of processes in the life cycle of a control system, the most preferable sets of process parameters should be determined by their attributes, which should be used as the basis for the technical requirements for its elements and the system as a whole.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125315308","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8814274
M. V. Balashkov, V. M. Bogachev
The singular spectral variant of exponential approximation is developed, which combines the order reduction of a polynomial by the singular method of the matrix beams on the first stage and recovering of the exponential polynomial of reduced order by the method of z-approximation on the second stage. Examples of this method application are presented typical for the circuit theory and radio electronics. In particular, the approximation of Bessel functions with accuracy ∝ 10–12 ••• 10–11is performed on the interval (0, 100π) by exponential polynomial of 28th order; the nine-stage amplifier order by sequential application of the methods of abbreviated operator equations and matrix beams is reduced three times with the absolute error of AFC approximation less than 3.10−3; the identification problem of sequence parameters for radar pulses is solved at signal/noise ratio in the range from 30 to 0 dB. Other possible areas of this method application are considered.
{"title":"The Singular Method of Exponential Approximation With its Applications","authors":"M. V. Balashkov, V. M. Bogachev","doi":"10.1109/SYNCHROINFO.2019.8814274","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8814274","url":null,"abstract":"The singular spectral variant of exponential approximation is developed, which combines the order reduction of a polynomial by the singular method of the matrix beams on the first stage and recovering of the exponential polynomial of reduced order by the method of z-approximation on the second stage. Examples of this method application are presented typical for the circuit theory and radio electronics. In particular, the approximation of Bessel functions with accuracy ∝ 10–12 ••• 10–11is performed on the interval (0, 100π) by exponential polynomial of 28th order; the nine-stage amplifier order by sequential application of the methods of abbreviated operator equations and matrix beams is reduced three times with the absolute error of AFC approximation less than 3.10−3; the identification problem of sequence parameters for radar pulses is solved at signal/noise ratio in the range from 30 to 0 dB. Other possible areas of this method application are considered.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127828228","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813947
N. Yampurin, Y. Fedosenko, V. Loginov, S. V. Pavlov
In this article is considered the problem of operational frequency management in terms of its dynamic use, taking into account non-linear distortion in high cascades transceivers. Main results contain the new method for operational management establishing, taking into account nonlinear distortions in communication channels. This method satisfies the modern requirements for its use in the systems of dynamic allocation of frequency resources. The method improves the use of communication channels efficiency.
{"title":"Frequency Distribution Algorithms in Extensive Use Cognitive Radio Systems and Internet of Things","authors":"N. Yampurin, Y. Fedosenko, V. Loginov, S. V. Pavlov","doi":"10.1109/SYNCHROINFO.2019.8813947","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813947","url":null,"abstract":"In this article is considered the problem of operational frequency management in terms of its dynamic use, taking into account non-linear distortion in high cascades transceivers. Main results contain the new method for operational management establishing, taking into account nonlinear distortions in communication channels. This method satisfies the modern requirements for its use in the systems of dynamic allocation of frequency resources. The method improves the use of communication channels efficiency.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121138475","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8813935
A. Godin, K. Klimov
A technique is proposed for using impedance-matched materials to expand the operating frequency of existing antenna radiators. The results of numerical electromagnetic modeling and experimental investigation of a waveguide slit radiator, whose operating frequency was expanding.
{"title":"Application of impedance-matched materials in antenna technology","authors":"A. Godin, K. Klimov","doi":"10.1109/SYNCHROINFO.2019.8813935","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8813935","url":null,"abstract":"A technique is proposed for using impedance-matched materials to expand the operating frequency of existing antenna radiators. The results of numerical electromagnetic modeling and experimental investigation of a waveguide slit radiator, whose operating frequency was expanding.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126615263","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8814227
I. V. Manonina, A. S. Adzhemov, V. Shestakov
The use of such technology as “electronization” of teaching in the process of learning, which means the extensive use of the capabilities of computing equipment integrated by telecommunications into a network for learning, will allow to obtain methodological effects from the use of this technology in terms of achieving the best result for students to learn the material.
{"title":"Program-Technical Aspects of Creating Training Complexes","authors":"I. V. Manonina, A. S. Adzhemov, V. Shestakov","doi":"10.1109/SYNCHROINFO.2019.8814227","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8814227","url":null,"abstract":"The use of such technology as “electronization” of teaching in the process of learning, which means the extensive use of the capabilities of computing equipment integrated by telecommunications into a network for learning, will allow to obtain methodological effects from the use of this technology in terms of achieving the best result for students to learn the material.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127111502","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 : 2019-07-01DOI: 10.1109/SYNCHROINFO.2019.8814156
R. Bikmukhamedov, A. Nadeev
IoT traffic flows have different from traditional devices statistics and their classification become an important task because of the exponentially growing number of smart devices. Conventional Deep Packet Inspection systems that rely on inspection of open fields in TLS and DNS packets, and the trend of encrypting the open fields makes machine learning based systems the only viable option for future networks. Moreover, computational complexity of models becomes crucial for large-scale operations. In this work, we investigated whether simple models, such as Logistic Regression, SVM with linear kernel, and a Decision Tree, have suitable for real-world deployments performance of multiclass classification of IoT traces, given thoughtful features engineering. We introduced a new flow feature of categorical type that describes a set of TCP-flag fields within a flow. In addition, removal of correlated features and feature space transformation via PCA method showed their usefulness in terms of prediction complexity reduction. In order to account for online classification mode, we limited the maximal number of packets within a flow to 10. Moreover, to estimate the upper-bound performance with given features, we compared the simple algorithms with Random Forest, Gradient Boosting and a feed-forward neural network. We performed 4-fold cross-validation of models by metrics Accuracy and F1-measure. The test results demonstrated that the introduced feature increases F1-measure for logistic regression from 99.1% in the base case to 99.6%, thus closely approaching more computationally expensive models. Overall, the evaluation results demonstrated feasibility of a lightweight model for IoT flow classification task with the suitable for a practical deployment performance.
{"title":"Lightweight Machine Learning Classifiers of IoT Traffic Flows","authors":"R. Bikmukhamedov, A. Nadeev","doi":"10.1109/SYNCHROINFO.2019.8814156","DOIUrl":"https://doi.org/10.1109/SYNCHROINFO.2019.8814156","url":null,"abstract":"IoT traffic flows have different from traditional devices statistics and their classification become an important task because of the exponentially growing number of smart devices. Conventional Deep Packet Inspection systems that rely on inspection of open fields in TLS and DNS packets, and the trend of encrypting the open fields makes machine learning based systems the only viable option for future networks. Moreover, computational complexity of models becomes crucial for large-scale operations. In this work, we investigated whether simple models, such as Logistic Regression, SVM with linear kernel, and a Decision Tree, have suitable for real-world deployments performance of multiclass classification of IoT traces, given thoughtful features engineering. We introduced a new flow feature of categorical type that describes a set of TCP-flag fields within a flow. In addition, removal of correlated features and feature space transformation via PCA method showed their usefulness in terms of prediction complexity reduction. In order to account for online classification mode, we limited the maximal number of packets within a flow to 10. Moreover, to estimate the upper-bound performance with given features, we compared the simple algorithms with Random Forest, Gradient Boosting and a feed-forward neural network. We performed 4-fold cross-validation of models by metrics Accuracy and F1-measure. The test results demonstrated that the introduced feature increases F1-measure for logistic regression from 99.1% in the base case to 99.6%, thus closely approaching more computationally expensive models. Overall, the evaluation results demonstrated feasibility of a lightweight model for IoT flow classification task with the suitable for a practical deployment performance.","PeriodicalId":363848,"journal":{"name":"2019 Systems of Signal Synchronization, Generating and Processing in Telecommunications (SYNCHROINFO)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133615447","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：