{"title":"Evolutionary-simulation algorithm implementation for logistic processes optimization","authors":"K. Aksyonov, A. Antonova, I. V. Vershinina","doi":"10.1109/SSDSE.2017.8071956","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071956","url":null,"abstract":"This paper deals with implementation of an evolutionary-simulation algorithm in the metallurgical enterprise information system. The algorithm is based on a multi-agent genetic optimization method proposed by authors in the previous work. In this method, the genetic algorithm is used for search of the effective solution, and multi-agent simulation is used to evaluate the fitness function of a particular solution. The evolutionary-simulation algorithm has been implemented on Java in the optimization module of the metallurgical enterprise information system. The algorithm has been tested in logistic processes optimization for the production of metallurgical products. During algorithm testing, recommendations have been obtained for the user to setting up the parameters of the algorithm. To achieve the rapid convergence of the algorithm, while maintaining the accuracy of the result, it is necessary to use the number of chromosomes in the generation of at least 6 chromosomes and stop the algorithm when changing at least 10 generations.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126542176","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":"Neural network solution of the inverse anomalous diffusion problem","authors":"V. A. Dedok","doi":"10.1109/SSDSE.2017.8071972","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071972","url":null,"abstract":"This paper presents a new method of using artificial neural network (ANN) to solve the inverse problem of anomalous diffusion theory. The main goal is to estimate the unknown coefficients of anomalous diffusion equation using a Multilayer Perceptron Artificial Neural Network model. This report demonstrates that this model is a powerful instrument for recovering of Hurst exponent.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134603672","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":"Cartesian decomposition in data analysis","authors":"P. Emelyanov, D. Ponomaryov","doi":"10.1109/SSDSE.2017.8071964","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071964","url":null,"abstract":"We consider the Cartesian decomposition of relational data sets, i.e. the problem of finding two or several data sets such that their unordered Cartesian product equals the source set. In terms of relational databases, this means reversing the SQL CROSS JOIN operator. We describe a polytime algorithm for computing a Cartesian decomposition based on factorization of boolean polynomials. We provide an implementation of the algorithm in Transact SQL and discuss some generalizations of the Cartesian decomposition.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125926117","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":"On the possibilities of the discriminant analysis for the arterial hypertension diagnosis: Evaluation of the short-term heart rate variability feature combinations","authors":"Kublanov Vladimir, D. Anton, H. Gamboa","doi":"10.1109/SSDSE.2017.8071968","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071968","url":null,"abstract":"This paper discusses the possibilities of the Linear and Quadratic Discriminant analysis for diagnosing arterial hypertension patients. For this purpose, electrocardiogram was recorded while performing the tilt testing in two distinct groups: 30 healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. Further analysis includes the extraction of 64 features, obtained by statistical, geometric, spectral (Fourier and wavelet) and nonlinear methods. In order to find the best feature combination, a Semi-optimal search of the non-correlated features space is proposed. All calculations were performed in the in-house software written on Python. The results suggest that a 4-features combination of statistical, spectral and nonlinear features provide the most robust classifiers.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126475645","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}
R. Gazizov, T. T. Gazizov, A. Belousov, T. Gazizov
{"title":"Optimization of ultrashort pulse duration with usage of genetic algorithms by criteria of peak voltage maximization in PCB bus","authors":"R. Gazizov, T. T. Gazizov, A. Belousov, T. Gazizov","doi":"10.1109/SSDSE.2017.8071967","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071967","url":null,"abstract":"Importance of the genetic algorithms (GA) usage in the investigation of an ultrashort pulse peak voltage in multiconductor structures of printed circuit boards (PCB) is highlighted. Trapezoidal ultrashort pulse propagation along the conductors of a real PCB multiconductor bus was simulated. Using GA an optimization of the whole ultrashort pulse duration and separately of the rise, top and fall durations was made by a criterion of the peak voltage maximization in the PCB bus. A voltage maximum which is revealed with the whole ultrashort pulse duration variation by 16% exceeds the steady state level when the whole duration is near 0.13 ns. A voltage maximum exceeding the steady state level by 36% is revealed and localized by using the variation of ultrashort rise, top and fall durations. The maximum crosstalk value of 24% of the steady state level is observed for this case. For the last voltage and crosstalk maximums, the whole ultrashort pulse duration is near 1 ns. A good replicability of results is shown.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131357258","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":"Multicriteria optimization of multiconductor modal filters by genetic algorithms","authors":"A. Belousov, T. T. Gazizov, T. Gazizov","doi":"10.1109/SSDSE.2017.8071966","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071966","url":null,"abstract":"Multicriteria optimization by genetic algorithms is considered. We optimize novel devices for the protection against ultrashort pulses referred to as multiconductor modal filters (MF) by means of the decomposition of the pulses into a sequence of smaller pulses. A multicriteria objective function with amplitude and time criteria is formulated. Five amplitude criteria are proposed for the critical systems, as well as range-time and interval-time criteria. To test the theory, four-criterion optimization of four parameters for a three-conductor microstrip MF has been performed. The results have shown the importance of optimization of multiconductor MF with the simultaneous use of several criteria: the three-conductor microstrip MF with attenuation factor of 21.4 times for ultrashort pulse with the duration of less than 0.6 ns/m is obtained.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123224374","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":"Assessment of personal environments in social networks","authors":"A. Kolonin","doi":"10.1109/SSDSE.2017.8071965","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071965","url":null,"abstract":"The paper justifies importance of study of personal social environments in social networks, suggests practical metrics for its assessment, describes web application developed for this purpose and evaluates its practical applicability in different social networks.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124959132","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":"Steganography in social networks","authors":"I. Nechta","doi":"10.1109/SSDSE.2017.8071959","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071959","url":null,"abstract":"In this paper we propose a new method for hidden messages transmission in social networks, on the example of the network “Vkontakte”. It was proposed to use a graph structure of user's friends to embed a secret message. It was tested for robustness of this method to a statistical stegoanalysis. It was shown the necessity of adding redundancy to secret messages for preventing successful steganalysis.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115246026","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}
S. Alyamkin, Nikita A. Nikolenko, Evgeny Nikolaevich Pavlovskiy, V. Dyubanov
{"title":"FRiS-censoring of reference sample in face recognition task by deep neural networks","authors":"S. Alyamkin, Nikita A. Nikolenko, Evgeny Nikolaevich Pavlovskiy, V. Dyubanov","doi":"10.1109/SSDSE.2017.8071961","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071961","url":null,"abstract":"To increase face recognition quality in video surveillance system an approach of censoring incoming photos based on FRiS function is presented.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123104580","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":"A tool for effective extraction of synsets and semantic relations from BabelNet","authors":"Dmitry Ustalov, Alexander Panchenko","doi":"10.1109/SSDSE.2017.8071954","DOIUrl":"https://doi.org/10.1109/SSDSE.2017.8071954","url":null,"abstract":"Evaluation experiments in natural language processing often involve construction of samples from large lexical semantic resources, such as WordNet, Wiktionary, and OmegaWiki for evaluation and training purposes. The two most recurrent tasks are extraction of synsets and semantic relations between words. BabelNet is a resource which combines and interlinks all main lexical resources providing a unified assess to them. In this paper, we present BabelNet Extract, an open source tool which helps in addressing these two recurrent extraction tasks effectively in a parallelized manner from the large-scale multilingual BabelNet semantic network. The tool extracts individual word senses and the synsets they form as well as the semantic relations established between the synsets. We show its architecture, describe the output format, and discuss the use cases of the tool.","PeriodicalId":216748,"journal":{"name":"2017 Siberian Symposium on Data Science and Engineering (SSDSE)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132178027","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}