ISSN 1991-2927
 

ACP № 3 (65) 2021

Section: "ARTIFICIAL INTELLIGENCE"

Aleksei Mikhailovich Namestnikov, Doctor of Sciences in Engineering, Associate Professor; graduated from the Radioengineering Faculty of Ulyanovsk State Technical University; Professor of the Department of Information Systems of UlSTU; an author of more than 100 research papers in the field of computer-aided design and intelligent systems. e-mail: nam@ulstu.ruA.M. Namestnikov,

Aleksei Aleksandrovich Filippov, Candidate of Sciences in Engineering; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Associate Professor of the Department of Information Systems of UlSTU; an author of articles in the field of ontology modelling, intelligent storage systems and data processing. e-mail: al.filippov@ulstu.ruA.A. Filippov,

Islam Maratovich Shigabutdinov, Master in Software Engineering; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of articles in the field of text mining. e-mail: isl23@mail.ruI.M. Shigabutdinov

The extraction of terms consisting of several words from texts in natural languages using the syntactic patterns65_12.pdf

Two problems arise when extracting terms consisting of several words using linguistic methods of text analysis: 1. A linguist has no skills in software systems development, however he (she) is required to present his (her) knowledge in the form of software system fragments or constructions in a formal language. 2. Most software developers are not qualified enough in linguistics. This problem creates a semantic gap between the methods of linguistic analysis of texts and their software implementation. The article presents an approach to extract the terms consisting of several words based on syntactic patterns tailored for a linguist. The proposed approach does not require additional skills and usage of various languages to describe syntactic patterns by a linguist.
The prototype of the software system was developed. The software system allows describing syntactic patterns without having knowledge of a formal language. Moreover, as against the analogs the developed system is capable to use syntactic patterns in external systems for text analysis. The server of the prototype has an interface to make the syntactic patterns.

Natural language processing, parse tree, syntactic patterns, terms consisting of several words.

2021_ 3

Sections: Computer-aided engineering

Subjects: Computer-aided engineering, Information systems, Artificial intelligence.



Aleksei Mikhailovich Namestnikov, Doctor of Sciences in Engineering, Associate Professor; graduated from the Radioengineering Faculty of Ulyanovsk State Technical University; Professor of the Department of Information Systems of UlSTU; an author of more than 100 articles in the field of computer-aided design and intelligent systems. e-mail: nam@ulstu.ruA.M.Namestnikov

Ivetta Viacheslavovna Arzamastseva, Candidate of Sciences in Engineering; graduated from the Faculty of Language and Literature of Saratov State University; Associate Professor at the Department of Applied Linguistics of UlSTU; an author of articles and inventions in the field of statistical investigations and mathematical modeling in linguistics. e-mail: lingua@ulstu.ruI.V. Arzamastseva

An ontology approach to the sentiment analysis of software systems64_5.pdf

The article proposes an unorthodox approach to opinion mining for software systems (sentiment analysis) that can be in Russian, English or German languages. The main feature of this approach is an extraction of patterns represented by collocations consisting of one, two or more words and connected by common meaning or grammar. The article gives some examples of patterns in Russian in the area of computer games development. The determining lexical and semantic patterns are included in the ontology of the software system sentiment analysis described formally in the article.

Sentiment analysis, software system, lexical and semantic pattern, ontology, Bayes classificator.

2021_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Vitalii Evgenevich Dementev, Doctor of Sciences in Engineering; graduated from the Faculty of Economics and Mathematics at Ulyanovsk State Technical University; Head of the Department of Telecommunications at UlSTU; an author of monographs, articles, and patents in the field of statistical processing of multidimensional signals and information protection. e-mail: dve@ulntc.ruV.E. Dementev,

Ruslan Anatolevich Savinov, graduated from the Faculty of Machine-Building at Ulyanovsk State Technical University; Leading Software Engineer at Federal Research-and-Production Center Joint Stock Company ‘RPA ‘Mars’; his research interests are in the field of the development of computer-aided recognition systems and the pattern analysis with neural network technologies. e-mail: sarus@list.ruR.A. Savinov,

Marat Nikolaevich Suetin, Postgraduate Student; graduated from the Faculty of Technology and Business at Ulyanovsk State Pedagogical University; Leading Software Engineer at FRPC JSC ‘RPA ‘Mars’, an author of articles in the field of image processing and computer vision. e-mail: source81@gmail.comM.N. Suetin,

Anatolii Gennadievich Podloboshnikov, graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Head of a research-and-development laboratory, Chief Designer at FRPC JSC ‘RPA ‘Mars’; his research interests are in the field of computer-aided recognition and pattern analysis systems development with neural network technologies. e-mail: agpdonet@mail.ruA.G. Podloboshnikov

The system of damage recognition in metal structures64_6.pdf

The article deals with a system developed on the basis of a neural network approach that allows the system to detect the visual defects and damage of infrastructure facilities using photo/video data processing. The photo/video images of structural railroad bridge members were used as training data for the convolutional neural network U-Net. The authors carried out ranging and labeling the photo/video data sets as well as they selected an optimal architecture and hyperparameters for the neural network. The image test sets were used for testing the neural network trained. The findings suggest that the resulting system can detect defects in structural steel members at the level which can be achieved if experts performed the visual inspection

Noninvasive inspection, damage in metal structures, deep convolutional neural network, CNN, bridge structures, cracks, photo image processing.

2021_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Andrei Alekseevich Pertsev, Candidate of Sciences in Engineering; graduated from the Faculty of Mechanics and Mathematics of Ulyanovsk State University; Head of a department of FRPC JSC ‘RPA ‘Mars’; an author of articles in the field of the automated enterprise management system implementation. e-mail: mars@mv.ruA.A. Pertsev,

Aleksandr Nikolaevich Podobrii, Candidate of Sciences in Engineering; graduated from the Faculty of Mechanics and Mathematics of Ulyanovsk State University; Deputy Chief of a department of FRPC JSC ‘RPA ‘Mars’; an author of articles in the field of the automated enterprise management system implementation. e-mail: mars@mv.ruA.N. Podobrii,

Iuliia Aleksandrovna Radionova, Candidate of Sciences in Engineering; graduated from the Faculty of Mechanics and Mathematics of Ulyanovsk State University; Leading Software Engineer at FRPC JSC ‘RPA ‘Mars’; an author of articles in the field of automated workflow systems, intelligent technical documentation storage bases and systems for statistical analysis of supplier appraisal; research interests are in the field of electronic document management, archival depositories, statistical data analysis, decision support systems. e-mail: julia-owl@mail.ruI.A. Radionova

An approach to plan the production resources of a machine-building enterprise using neural networks64_7.pdf

Generally, this is the experience of production workers, economists, designers, etc. that used to get a preliminary assessment of feasibility of hardware manufacturing at an enterprise. For a preliminary assessment, it is enough to understand the complexity of the product and available analogues. At the same time, it is not always possible to calculate an accurate production time for the product due to the lack of a complete set of design and technological documentation.
The article presents an approach to calculating the production time of hardware using neural networks based on existing data for previous periods and types of hardware using. This approach allows estimating the production time without using accurate data on the design and manufacturing technology. The article also describes the structure of neural networks and defines the training sample. Some experiments were conducted based on the sample data, which allowed determining the initial weight coefficients of the neural network. The software implementation is made in the form of an additional module for an interactive web resource and uses T-SQL.

Production plan formation, neural network, small-scale manufacturing, project manufacturing, mechanical engineering, production capacity, operation performance statistics.

2021_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Nadezhda Glebovna Yarushkina, Doctor of Sciences in Engineering, Professor; graduated from Ulyanovsk Polytechnic Institute with the specialty in Electronic Computing Machines; Head of the Department of Information Systems at Ulyanovsk State Technical University; an author of more than 400 papers in the field of soft computing, fuzzy logic, and hybrid systems. e-mail: jng@ulstu.ruN.G. Yarushkina

Vadim Sergeevich Moshkin, graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Associate Professor of the Department of Information Systems of UlSTU; an author of more than 90 papers in the field of data analyzing intelligent systems. e-mail: v.moshkin@ulstu.ruV.S. Moshkin

Andrei Alekseevich Konstantinov, a student in the master’s degree at the Department of Information Systems of Ulyanovsk State Technical University; an author of articles in the field of text mining; the area of his scientific interests relates to the automation of text analysis using machine learning. e-mail: adwaises@mail.ruA.A. Konstantinov

Word2vec and BERT language models used for a sentiment analysis of text posts in social networks61_7.pdf

The paper proposes an original algorithm for the formation of a training sample for a neural network that provides a sentiment analysis of text posts in social networks. A feature of the algorithm is the use of the extended Russian-language semantic thesaurus WordNetAffect and the expert dictionary of author’s symbols for expressing emotions. In addition, the paper describes the application of a neural network based on the LSTM architecture to determine the emotional coloring of text messages on a social network using two text vectorization algorithms “word2vec” and “BERT”. As a result of the experiments, an indicator of the accuracy of determining the emotional coloring of messages of 87% was achieved using lemmatization as a text preprocessing algorithm and the BERT algorithm when converting it into a vector.

Sentiment analysis, BERT, word2vec, neural network, social network.

2020_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Alexander Viacheslavovich Mikheev, graduated from Ulyanovsk State Technical University; Programmer of the Ulyanovsk Regional Center of New Information Technologies at the Ulyanovsk State Technical University; an author of more than 15 research papers, a holder of the certificate of software registration; the area of his scientific interests relates to the machine learning. e-mail: a.miheev@simcase.ruA.V. Mikheev

Kirill Valerevich Sviatov, Candidate of Sciences in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies of UlSTU; an author of more than 40 articles, three monographs, three textbooks; a holder of four certificates of software registration; the area of his scientific interests relates to machine learning and robotics. e-mail: k.svyatov@ulstu.ruK.V. Sviatov

Iurii Aleksandrovich Lapshov, Candidate of Sciences in Engineering; graduated from Ulyanovsk State Technical University; Associate Professor of the Computer Engineering Department at UlSTU; an author of 32 articles, a monograph; a holder of two certificates of software registration; the area of his scientific interests relates to computer-aided design systems, workflow management. e-mail: y.lapshov@ulstu.ruI.A. Lapshov

Vadim Georgievich Tronin, Candidate of Sciences in Engineering; graduated from Ulyanovsk State Technical University; Associate Professor of the Department of Information Systems at UlSTU; an author of more than 50 articles, a textbook; the area of his scientific interests relates to the project management and theory of solving inventive problems. e-mail: v.tronin@ulstu.ruV.G. Tronin

Software for determining features of a mobile robot’s path with the use of neural networks61_8.pdf

The article describes an approach to the implementation of a software package for determining the probability of a collision of a mobile robot with obstacles. This approach is based on a neural network model with attention. Key feature is the method of the training dataset generation: the labeling of obstacles and the values of the probability of collision with them is performed not in manual mode, but using a deterministic algorithm that uses the result of semantic segmentation using another pre-trained neural network. This method allows to use a poorly detailed description of the external environment for training convolutional neural networks with attention on the example of recognizing obstacles when a mobile robot moves in simulation mode. At the same time, low detail allows to reduce the time-consuming process of manual data labeling due to automatically generated sampling in the NVIDIA Isaac environment, and the attention mechanism allows to increase the interpretability of the analysis results.

Artificial intelligence, neural networks, machine learning, computer vision, attention networks, robotics.

2020_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Anton Alekseevich Romanov, Candidate of Sciences in Engineering; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University (UlSTU); Associate Professor of the Department of Information Systems at UlSTU; an author of articles in the field of intelligent systems for data storage and processing. e-mail: romanov73@gmail.comA. A. Romanov

Aleksei Aleksandrovich Filippov, Candidate of Sciences in Engineering; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Associate Professor of the Department of Information Systems at UlSTU; an author of articles in the field of ontological modeling, intelligent systems for data storage and processing. e-mail: al.filippov@ulstu.ruA. A. Filippov

Nadezhda Glebovna Yarushkina, Doctor of Sciences in Engineering, Professor; graduated from Ulyanovsk Polytechnic Institute; Interim Rector of Ulyanovsk State Technical University, Head of the Department of Information Systems at UlSTU; an author of more than 300 scientific papers in the field of soft computing, fuzzy logic, and hybrid systems. e-mail: jng@ulstu.ruN. G. Yarushkina

Vladimir Anatolyevich Maklaev, Candidate of Sciences in Engineering; graduated from Radioengineering Faculty of Ulyanovsk Polytechnic Institute; Director General of Federal Research-and-Production Center Joint-Stock Company ‘Research-and-Production Association ‘Mars’. The area of scientific interests relates to the computer- aided design systems. e-mail: mars@mv.ruV. A. Maklaev

The decision support module of information environment for technological support of production60_7.pdf

Making management decisions requires a specialist to have extensive knowledge of the problem area and the current state of the organization. There is a need for timely and urgent management decision support in the activity of any large organization. The decision support module (DSM) was created to solve that kind of problem in the task of balancing production capacities. The main task of the DSM is a linguistic summarization of the state of the main production indicators and the formation of recommendations that allow the decision-maker to develop a specific strategy for balancing production capacities. The DSM functionality is based on the knowledge base in the form of ontology with the set of expert SWRL-rules. This article describes methods for modeling and forecasting the dynamics of the main production indicators based on type- 2 fuzzy sets, and the approach to summarizing the time series of production indicators and forming recommendations for optimizing production based on knowledge engineering methods.

Data-driven decision making, type-2 fuzzy sets, time series forecasting, ontology, inference.

2020_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Viacheslav Andreevich Sergeev, Doctor of Sciences in Engineering, Professor; graduatedfromthe Faculty of Physics of Gorky State University n.a. Lobahevsky; Director of the Ulyanovsk Branch of the Kotel’nikov Institute of Radio- Engineering and Electronics of the Russian Academy of Sciences; Head of the Department of Radioengineering, Opto- and Nanoelectronics of Ulyanovsk State Technical University (UlSTU); an author of monographs, papers, and inventions in the field of modeling and researching semiconductor devices and integrated circuits characteristics and measuring its thermal parameters. e-mail: sva@ulstu.ruV. A. Sergeev

Mikhail Iurevich Leontev, completed postgraduate studies at the Faculty of Mathematics, Information, and Aviation Technologies at Ulyanovsk State University; Junior Research Associate of the Scientific and Research Institute of Technology n.a. S.P. Kapitsa; Leading Engineer of the Ulyanovsk Branch of the Kotel’nikov Institute of Radio-Engineering and Electronics of RAS; an author of eight articles, a certificate of registration for computer program. The area of his research interests relates to learning and robotics. e-mail: ulstaer@gmail.comM. I. Leontev

Victoriia Iurevna Islenteva, a student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of two articles. The area of her research interests relates to machine learning. e-mail: viksaskin@yandex.ruV. I. Islenteva

Sergei Vladimirovich Sukhov, Candidate of Sciences in Physics and Mathematics; graduated from the Ulyanovsk Branch of Lomonosov Moscow State University; Senior Staff Scientist at the Ulyanovsk Branch of the Kotel’nikov Institute of Radio-Engineering and Electronics of RAS; Associate Professor at the Department of Applied Mathematics and Informatics of UlSTU; an author of a monograph, 90 articles, two patents for inventions in the field of optics, computational neuroscience, and machine learning. e-mail: ssukhov@ulireran.ruS. V. Sukhov

Evaluation of generative approaches to knowledge sharing in neural networks60_8.pdf

The ability to interact and share knowledge among artificial neural networks (ANNs) is critical for further development of the artificial intelligence. One of the methods of knowledge sharing among ANNs may rely on the generation of training data using auxiliary generative models, which have recently become widespread. To make such methods more efficient, it is necessary to further improve the quality of artificial training data developed by generative models. The article proposes and tests several methods of enhancing characteristics of one of the classes of generative models, viz. variational autoencoders (VAE). It was improved both the VAE training procedure and changes in the model architecture. The improving methods of the quality of generated training data have been analyzed in terms of the efficiency of knowledge sharing among ANNs. To test the process of knowledge sharing among ANNs, the public training data sets have been used.

Generative networks, variational autoencoders, neural networks, machine learning, image classification, knowledge sharing.

2020_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Roman Nikolaevich Ermakov, Candidate of Science in Biology; graduated from the Bonch-Bruevich Saint-Petersburg State University of Telecommunications; Leading Engineer of JSC “Research Institute “Masshtab”; an author of articles in the field of mathematical modeling, expert systems, and control systems. e-mail: romul151925@mail.ru.R. Ermakov

Detection Of Network Protocols With Application Of Machine Learning Methods And Fuzzy Logic Algorithms In Traffic Analysis Systems 57_7.pdf

The article deals with a new effective approach to analyzing the network traffic in order to determine the protocol of information exchange. A brief description of the structure of the algorithm for classifying network packets by belonging to one of the known network protocols (TLS v1, TLS v1.2, HTTP, SSH v2, DNS, DHCP v6, etc.) is given. To define the protocol, the principle of high-speed one-packet classification is used, which consists in analyzing the information transmitted in each particular packet. Elements of behavioral analysis are used, namely, the transition states of information exchange protocols are classified, which allows to achieve a higher level of accuracy of classification and a higher degree of generalization in new test samples. Fuzzy logic algorithms and neural networks are used. The test results of the constructed software module capable of identifying network protocols for information exchange are demonstrated.

Network packet classification, artificial neural networks, logistic regression, network traffic analysis, in-depth packet analysis.

2019_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Pavel Vladimirovich Dudarin, graduated from Ulyanovsk State University; Postgraduate Student at the Department of Information Systems of Ulyanovsk State Technical University; an author of scientific papers in the field of data processing by means of neural networks. e-mail: p.dudarin@ulstu.ru.P. Dudarin,

Vadim Georgievich Tronin, Candidate of Science in Engineering; Associate Professor at the Department of Information Systems of UlSTU; an author of scientific papers in the field of economics, finance and information technologies. e-mail: v.tronin@ulstu.ru.V. Tronin,

Kirill Valerevich Sviatov, Candidate of Science in Engineering; graduated from UlSTU; Dean of the Faculty Information Systems and Technologies of UlSTU; an author of scientific papers in the field of automation of management processes. e-mail: k.svyatov@ulstu.ru.K. Sviatov,

Vladimir Aleksandrovich Belov, graduated from UlSTU with a bachelor degree in Software Engineering; Master Student at the Department of Information Systems of UlSTU; an author of an article in the field of computer operation monitoring. e-mail: v.belov@ulstu.ru.V. Belov,

Roman Azatovich Shakurov, graduated from UlSTU with a bachelor degree in Software Engineering; Master Student at the Department of Information Systems of UlSTU; an author of articles in the field of computer operation monitoring and developing of system for determining the winner in cyber security competitions. e-mail: r.shakurov@ulstu.ru.R. Shakurov

An Approach To Labor Intensity Evaluation In Software Development Process Based On Neural Networks 57_8.pdf

Software development process is actively studied by experts from different spheres of science and different viewpoints. However, the degree of success of projects in the development of software intensive systems (Software Intensive Systems, SIS) has changed insignificantly, remaining at the level of 50% inconsistency with the initial requirements (finance, time and functionality) for medium-sized projects. The annual financial losses in the world because of the total failures are counted by hundreds of billions of dollars. Its high complexity leads to constant mistakes in labor intensity evaluation, and even new agile development paradigm does not solve this problem. This paper shows that retrospective labor intensity estimation could be approximated by a function, implemented by neural network, with some amount of code complexity metrics as arguments. Also there is a described an approach of neural network training and data collection, which allows to automate a process of retrospective labor intensity evaluation in agile software developing process. Experiments performed on the real life software project show the effectiveness of proposed technique.

Software developing process, neural network, data augmentation, Halstead metrics, Cyclomatic metric.

2019_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Nikolai Veniaminovich Maksimov, Moscow Engineering Physics Institute, Doctor of Science in Engineering, Professor; graduated from Moscow Engineering Physics Institute; Professor of the System Analysis Department at Moscow Engineering Physics Institute; an author of more than 120 scientific papers, textbooks and manuals; research interests are in the field of modeling and development of documentary information retrieval systems and databases, linguistic support of documentary information retrieval systems and knowledge management systems; man-machine information systems, interfaces based on cognitive and behavioral models. [e-mail: nv-maks@yandex.ru]N. Maksimov,

Valerii Igorevich Shirokov, JSC IC ASE, graduated from Nizhny Novgorod State University n.a. R.E. Alekseev; Leading Engineer of JSC IC ASE; a student in the master’s degree at the National Research Nuclear University MEPhI; research interests are in the field of databases, automated design and calculation of electrical networks. [e-mail: v.shirokov@ase-ec.ru]V. Shirokov,

Alexander Iurevich Shamanin, JSC IC ASE, graduated from Nizhny Novgorod State University n.a. R.E. Alekseev; an expert of JSC IC "ASE"; research interests are in the field of systems engineering, systems modeling, ontology, semantic and syntactic analysis of textual information. [e-mail: al.shamanin@ase-ec.ru]A. Shamanin

An Approach to the Development of Ontology for Electric-Power Engineering Domain Based on Standards ISO 15926, IEC 61970 56_7.pdf

The article deals with an approach to the development of ontology in the field of electric power industry using up-to-date international standards. Currently, when designing electrical installations, designers are faced with unreliable information from several sources as well as search complexity and heterogeneity of information. The requirements for the ontology of the subject area in the field of electric power industry are given, and the ISO 15926 and IEC 61970 standards are compared. It is concluded that the classes in the CIM model are complete for the operational stage. Publications on this topic are reviewed. The procedure for constructing an ontology prototype is carried out using the DOT-15926 program in terms of transformer parameters and the ISO 15926 standard methodology. This prototype was used to transfer from the E3.Series design system to the ETAP calculation complex. Data transfer was carried out in a file form with the conversion in the DOT-15926 program.

ISO 15926, IEC 61970, CIM, domain ontology, electric power engineering.

2019_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Irina Aleksandrovna Moshkina, Ulyanovsk State Technical University, Candidate of Science in Engineering; Associate Professor at the Department of Information Systems of Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of articles in the field of intellectual analysis of time series. [e-mail: timina_i@mail.ru]I. Moshkina,

Evgenii Nikolaevich Egov, Ulyanovsk State Technical University, graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Assistant at the Department of Information Systems at Ulyanovsk State Technical University; at author of articles in the field of data mining. [e-mail: e.egov@ulstu.ru]E. Egov

Project State Forecasting on Time Series of Metrics and on Detected Anomalies 56_8.pdf

The article deals with an example of the anomalies detection when analyzing the time series of metrics that characterize the project activity to adjust the project state forecasting. Project activity metrics are analyzed. A forecasting algorithm based on fuzzy tendency of time series metrics is developed and implemented. Authors suggest a procedure for detecting the time series anomaly based on entropy. A formula for computing the entropy measure for a fuzzy time series is proposed. The algorithm allows to take into account the dependence of the predicted values on the entropy measures. For forecasting, a hypothesis is used, which is formed for a given period on the basis of a trend. The results of the application of the proposed approach for forecasting the state of the project "FreeNAS9" are given.

Time series, software metrics, entropy, forecasting.

2019_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence, Information systems.



Eduard Dmitrievich Pavlygin, Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’, Candidate of Science in Engineering; graduated from the Radioengineering Faculty of Ulyanovsk Polytechnic Institute; First Deputy of Director General in Scientific Affairs and Innovations of Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’; an author of articles in the field of statistical methods of signal processing. [e-mail: mars@mv.ru]E. Pavlygin,

Anatolii Gennadievich Podloboshnikov, Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’, graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Head of the Research Laboratory and Chief Designer at FRPC JSC ‘RPA ‘Mars’; research interests are in the field of special-purpose information system. e-mail: mars@mv.ruA. Podloboshnikov,

Ruslan Anatolevich Savinov, Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’, graduated from the Machine-building Faculty of UlSTU; Software Engineer at FRPC JSC ‘RPA ‘Mars’. research interests are in the field of special-purpose information system. [e-mail: mars@mv.ru]R. Savinov,

Nadezhda Glebovna Yarushkina, Ulyanovsk State Technical University, Doctor of Science in Engineering, Professor; graduated from Ulyanovsk Polytechnic Institute; First Vice-Rector, Vice-Rector in Scientific Affairs in UlSTU, Head of the Department of Information Systems at UlSTU; an author of more than 300 publications in the field of soft computing, fuzzy logic, and hybrid systems. [e-mail: jng@ulstu.ru]N. Yarushkina,

Aleksei Mikhailovich Namestnikov, Ulyanovsk State Technical University, Doctor of Science in Engineering, Associate Professor; graduated from the Radioengineering Faculty of UlSTU; an author of more than 80 publications in the field of computer-aided design and intelligent systems.[e-mail: nam@ulstu.ru]A. Namestnikov,

Aleksei Aleksandrovich Filippov, Ulyanovsk State Technical University, Candidate in Science in Engineering; graduated from the Faculty of Information Systems and Technologies of UlSTU; Associate Professor at the Department of Information Systems of UlSTU; an author of articles in the field of ontological modelling and building of computer-aided systems for knowledge processing. [e-mail: al.filippov@ulstu.ru]A. Filippov,

Anton Alekseevich Romanov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from the Faculty of Information Systems and Technologies of UlSTU; Associate Professor at the Department of Information Systems of UlSTU;an author of articles in the field of systems for data storage and processing, and time series mining. [e-mail:romanov73@gmail.com]A. Romanov,

Vadim Sergeevich Moshkin, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from the Faculty of information systems and Technologies at UlSTU; Associate Professor of Information Systems at UlSTU; an author of more than 70 articles in the field of data mining systems. [e-mail: postforvadim@ya.ru]V. Moshkin,

Gleb Iurevich Guskov, Ulyanovsk State Technical University, graduated from the Faculty of information Systems and Technologies of UlSTU; Senior Lecturer at the Department of Information Systems of UlSTU; an author of publications in the field of ontological engineering and data mining systems. [e-mail: g.guskov@ulstu.ru]G. Guskov,

Maria Sergeevna Grigoricheva, Ulyanovsk State Technical University, Postgraduate Student at the Department of Information Systems of UlSTU; graduated from the Faculty of Information Systems and Technologies of UlSTU; Assistant Lecturer at the Department of Information Systems of UlSTU; an author of publications in the field of data mining. [e-mail:gms4295@mail.ru]M. Grigoricheva

Development of a Software Package for Data Mining of Social Media56_3.pdf

The article presents the results of work on a software package for data mining of social media. The architecture of the software package is described. Listed the main subsystems of the software package and third-party software systems used in the development of a software package. The organization of the data storage subsystem of the software package is considered, the data model of this subsystem is described. The approach to organizing the ontology repository of a software package based on a graph database is described, and the ontology translation method in the OWL / XML format into a graph database fragment is presented. The organization of the data search subsystem is considered, the method of extending the search query using ontology for accounting for the features of the subject area in the search process is described. Also presented is a method of formatting a search query to highlight the important elements of the query to improve the quality of the search. The organization of the social portrait building subsystem of the user of the social network VKontakte is described, the method of determining the categories of interests of the user is considered.

Social media, ontological analysis, natural language processing, data mining, software package.

2019_ 2

Sections: Information systems

Subjects: Information systems, Artificial intelligence.



Ivan Iurevich Davydov, Ulyanovsk State Technical University, graduated with a Master degree from Ulyanovsk State Technical University in Telecommunication Technologies and Communication Systems; a postgraduate student of the Department of Telecommunications of Ulyanovsk State Technical University; an author of articles in the field of error-proof coding and information security. [e-mail: 1Davydov2i@gmail.com]I. Davydov,

Denis Aleksandrovich Kozlov, Ulyanovsk Transport (Aviation) Security Center, graduated from the Ulyanovsk Institute of Civil Aviation; Head of Ulyanovsk Transport (Aviation) Security Center; a postgraduate student of the Department of Aviation Security Assurance at the Ulyanovsk Institute of Civil Aviation named after Chief Air Marshal B.P. Bugaev; an author of articles in the field of aviation security. [e-mail: peccab@mail.ru]D. Kozlov,

Sergei Valentinovich Shakhtanov, Nizhny Novgorod State University of Engineering and Economics, Cgraduated from the Leningrad Higher Military Engineering School of Communications; Senior Lecturer of the Department of Infocommunication Technologies and Communication Systems at the Nizhny Novgorod State University of Engineering and Economics; an author of publications in the field of error-proof coding and information protection. [e-mail: r155p@bk.ru]S. Shakhtanov,

Mariia Iurevna Shibaeva, Nizhny Novgorod State University of Engineering and Economics, graduated from the Faculty of Information Technologies and Communication Systems at the Nizhny Novgorod State University of Engineering and Economics; Master’s Degree Student of the Department of Infocommunication Technologies and Communication Systems at the Nizhny Novgorod State University of Engineering and Economics; an author of publications in the field of error-proof coding and information protection. [e-mail: shibaevamarya@yandex.ru]M. Shibaeva

Permutation Decoding in the System of Combinations Code Designs in the Evaluation of Biometric Data 56_10.pdf

State-of-the-art telecommunication systems and means of data protection against natural and anthropogenic interference in the form of redundant codes are increasingly used in various applications related to the processing of biometric data. A large volume of publications in this subject area is devoted to codes with a low density of parity checks, polar codes, turbocodes with iterative data transformations that implement the algorithm of "belief propagation". These code constructions provide the required probabilistic characteristics but the procedure of decoding such codes takes long time intervals, which is unacceptable in terms of the duration of the cycle of biometric data management in systems critical to time delays. The paper proposes to use the principle of permutation decoding (PD), which is applied to systematic block codes. This method allows to fully use the corrective capabilities of redundant codes but in the classical interpretation requires cumbersome matrix calculations, which does not allow to use the positive properties of the method for error correction. The complexity of the computational process is excessively high. Therefore, to reduce the negative effect in the PD system, it is proposed to use the cognitive principle of data processing at the channel level, which significantly reduces the complexity of the decoder implementation and ensures the use of PD in the control systems of biometric data of subjects, for example, in the automation of transport security processes. Special attention is paid to the combination of codes in the format of cascade coding. For the first time, a description of such a scheme is given for polar codes and nonbinary Reed-Solomon (RS) codes.

Soft symbol solution, permutation decoding, cognitive map decoder, concatenated code.

2019_ 2

Sections: Mathematical modeling

Subjects: Mathematical modeling, Artificial intelligence.



Marina Viltalevna Samoilenko, Moscow Aeronautical Institute of National Research University, Candidate of Science in Engineering, Associate Professor; graduated from Moscow Aeronautical Institute and Moscow Institute of Physics and Technologies; Associate Professor at Moscow Aeronautical Institute of National Research University; an author of monographs, articles, and inventions; scientific interests are in the field of signal and image processing. [e-mail: Samoi.Mar@mail.ru]M. Samoilenko

Matrix-Iterative Method of the Blurred Images Restoration 56_11.pdf

A new method of the picture-original restoration from the blurred image is proposed. This method is based on the matrixiterative method developed by the author for solving the simultaneous linear algebraic equations. When implementing the image-restoration method, the author uses a prior information specified. It is assumed that the intensity of minimum background values of this image as well as the point spread function are known. The task of image restoration is resulted in the solution of an underdetermined system of linear algebraic equations. A pseudoinverse technique of its matrix is a known solution of the simultaneous linear algebraic equations. The well-known image restoration method based on this solution is also given. The author compares the image restoration by the use of this well-known method and a new matrix-iterative method based on computer simulating. It is shown that the matrixiterative method provides almost exact restoration under certain conditions. Such condition is a low occupation level of an image being filled up with objects if there is a high occupation level of an image being filled up with background values. The additive noise impact and an expected uncertainty were not considered.

Simultaneous linear algebraic equations, matrix-iterative method, image restoration, point spread function, pseudoinverse technique.

2019_ 2

Sections: Mathematical modeling

Subjects: Mathematical modeling, Artificial intelligence.



Valerii Vladimirovich Kozhevnikov, Scientific Research Technological Institute of Ulyanovsk State University, Candidate of Science in Engineering; graduated from the Pushkin Higher Command School of Radioelectronics; Senior Researcher at the Scientific Research Technological Institute of Ulyanovsk State University; an author of articles in the field of microelectronic system design theory.[e-mail: vvk28061955@mail.ru]V. Kozhevnikov

The Method of Mathematical Modeling of Cognitive Digital Automata 56_12.pdf

An approach to solving the problem of mathematical modeling of cognitive digital automata (CDA) is proposed. The task of formalizing the concept of the cognitive nature of the CDA mathematical model comes to the fore. The cognitiveness (cognition) of the mathematical model is determined by the possibility of learning and generating solutions that are not provided for in the learning process. A special feature of CDA is that the description of the neural network (NN) structure is used as a structural circuit of the automata, and the logical function "NOT-AND-OR" is used as the model of the neuron. In the case of the feedbacks formation from the output to the inputs of the neurons, the model of the neuron is a binary trigger with a logical function "NOT-AND-OR" at the input. As a tool for constructing a mathematical model of CDA, a mathematical apparatus of Petri nets (PNs) is proposed: marked graphs, inhibitory PNs and PNs with programmable logic. The mathematical model is builton the basis of the representation of the CDA in the form of the state equation of the PNs from the class of Murat equations (matrix equations) or a system of linear algebraic equations. The task of formalizing the concept of cognitiveness (cognition) is solved as a result of the logic synthesis (learning) of the initial structural circuit of CDA or the formation of the formula (network algorithm) of CDA. At the same time, the possibility of forming a formula (network algorithm) of CDA depends on the critical mass (quality) of training sets and training algorithms. Hence, the task of generating the minimum set of training sets for a given CDA function or experimentally determined function takes on particular importance. Forecasting or generation of solutions, in turn, is performed on the basis of the mathematical model of CDA obtained in the learning process.

intellectual control system, cognitive digital automata, artificial intelligence, neural networks, machine learning, cognition, Petri nets, equation of states, mathematical modeling, synthesis, generation, analysis, logic.

2019_ 2

Sections: Mathematical modeling

Subjects: Mathematical modeling, Artificial intelligence.



Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. Tupolev-KAI, Candidate of Science in Engineering; graduated from the Faculty of Physics and Mathematics of the Elabuga State Pedagogical Institute; Associate Professor of the Information Security Systems Department of the Kazan National Research Technical University named after A.N. Tupolev-KAI; an author of scientific works in the field of mathematical modeling, data analysis and development of intelligent decision support systems. [e-mail: Kat_726@mail.ru]A. Katasev

Neuro-fuzzy Model and Software Complex for Automation of Forming Fuzzy Rules for Objects State Assessing 55_3.pdf

This article deals with the task of objects state assessing in uncertainty. To solve it, the need to use of fuzzy knowledge bases and fuzzy inference algorithms as part of fuzzy expert systems is being actualized. As a tool for a knowledge base formation, a neuro-fuzzy model is proposed. The proposed type of fuzzy rules and the logical inference algorithm on the rules for object state assessing are described. A structure of a fuzzy neural network consisting of six layers is proposed, each of which implements a corresponding stage of the logical inference algorithm. As a result of learning a fuzzy neural network, a system of fuzzy rules is formed, which make up the knowledge base for object state assessing. On the basis of the proposed neuro-fuzzy model, a software complex was implemented for automating the processes of forming fuzzy rules. The main components of the software complex are the knowledge base generation module and the fuzzy inference module. As an approbation of the neuro-fuzzy model, the formation of fuzzy rules for water lines state assessing at the pumping stations in reservoir pressure maintenance systems has been carried out. The results of the testing confirmed the high efficiency of the neuro-fuzzy model and the possibility of its practical use for the formation of fuzzy rules in various subject areas.

Neuro-fuzzy model, fuzzy neural network, fuzzy rules formation, knowledge base, object state assessment, decision-making support.

2019_ 1

Sections: Information systems

Subjects: Information systems, Artificial intelligence.



Aleksandr Viacheslavovich Mikheev, Ulyanovsk Regional Center of New Information Technologies of Ulyanovsk State Technical University, graduated from Ulyanovsk State Technical University; Software Engineer at the Ulyanovsk Regional Center of New Information Technologies of Ulyanovsk State Technical University; his research interests include machine learning. [e-mail: a.miheev@simcase.ru]A. Mikheev,

Kirill Valerevich Sviatov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies at UlSTU; an author of 40 articles, 3 monographs, 1 textbook, and 4 State Registration Certificate of the Computer Program; his research interests are in the field of machine learning and robotics. [e-mail: k.svyatov@ulstu.ru]K. Sviatov,

Daniil Pavlovich Kanin, Ulyanovsk State Technical University, a student of the Faculty of Information Systems and Technologies of the Computer Science Department at Ulyanovsk State Technical University, a winner of robotics competitions; his research interests are in the field of machine learning. [e-mail: dan-kan@mail.ru]D. Kanin,

Sergei Vladimirovich Sukhov, Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Candidate at Science in Physics and Mathematics; graduated from the Ulyanovsk Branch of Lomonosov Moscow State University; Senior Researcher at the Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences; an author of one monograph, 70 articles, and 2 patents for inventions; his research interests are in the field of optics, computational neurobiology, machine learning [e-mail: ssukhov@knights.ucf.edu]S. Sukhov,

Vadim Georgievich Tronin, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Associated Professor at the Department of Information Systems of UlSTU; an author of 50 articles, 1 textbook; his research interests are in the field of project management and theory of inventive problem-solving. [e-mail: v.tronin@ulstu.ru]V. Tronin

The Scene Segmentation in the Tasks for Self-driving Vehicle Navigation By Using Neural Network Models With Attention 55_5.pdf

The article deals with the designing process of software module for the road signs recognition. This module is designated for the use in the automated control system of self-driving vehicles and is being developed at Ulyanovsk State Technical University.The creation of the training dataset sufficient to train neural network models is one of the major tasks to be solved when creating computer vision systems for self-driving vehicles. In this case, the preparation of a large sample in the semantic scene segmentation task may require considerable efforts for “manual” labeling. Authors describe a convolutional network model with a soft attention mechanism. This network is trained in the classification task with the possibility of extracting an attention mask from the internal network state, which can be used for the semantic image segmentation. This approach allows to reduce data-labeling costs significantly.

Artificial intelligence, neural networks, machine learning, computer vision, attention networks.

2019_ 1

Sections: Information systems

Subjects: Information systems, Artificial intelligence.



Aleksei Mikhailovich Namestnikov, Ulyanovsk State Technical University, Doctor of Science in Engineering; principal lecturer; graduated from the Faculty of Radioengineering at Ulyanovsk State Technical University; Professor of the Department of Information Systems at UlSTU; an author of more than 80 scientific papers in the field of automated design and intelligent systems. [e-mail: nam@ulstu.ru]A. Namestnikov,

Petr Ivanovich Sosnin, Ulyanovsk State Technical University, Honored Worker of the Higher School of the Russian Federation, Doctor of Engineering, Professor; graduated from the Radioengineering Faculty of Ulyanovsk Polytechnic Institute; Head of the Department of Computer Science at Ulyanovsk State Technical University; an author of numerous works in the field of conceptual design of computer-aided systems. [e-mail: sosnin@ulstu.ru.]P. Sosnin,

Method for Conceptual Indexing of Project Diagrams in Electronic Archives 54_6.pdf

The objective of the research is the development of a method for conceptual indexing of semistructured project diagrams. The proposed method of conceptual indexing is based on the use of the special type of ontologies - the ontology of project diagrams. This ontology includes semantic description of project diagram notations and design patterns used in the software system development. Intelligent design systems that allow to perform more efficiently tasks of structuring the large electronic archives including project diagrams of software and hardware systems have been developed.

Uml, ontology, project diagram, uml, conceptual indexing.

2018_ 4

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Aleksandr Viacheslavovich Mikheev, Ulyanovsk State Technical University, graduated from Ulyanovsk State Technical University; Software Engineer of Ulyanovsk Regional Center for New Information Technologies at Ulyanovsk State Technical University; his research interests include machine learning. [e-mail: a.miheev@simcase.ru]A. Mikheev,

Kirill Valerevich Sviatov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University;an author of 40 articles, three monographs, one textbook, and four certificates of registration of computer software programs; his research interests include machine learning and robotics. [e-mail: k.svyatov@ulstu.ru]K. Sviatov,

Sergei Vladimirovich Sukhov, Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences, Candidate of Science in Physics and Mathematics; graduated from the Ulyanovsk Branch of Lomonosov Moscow State University; Senior Staff Scientist at the Ulyanovsk Branch of the Kotel’nikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences; an author of one monograph, 70 articles, two patents of inventions in the field of optics, computational neurobiology, machine learning. [e-mail: ssukhov@knights.ucf.edu]S. Sukhov,

Daniil Pavlovich Kanin, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: dan-kan@mail.ru]D. Kanin,

Iakov Andreevich Akimov, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: yasha.akimov.73@gmail.com]I. Akimov,

Pavel Mikhailovich Volkov, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Winner of robotics competitions; his research interests include machine learning. [e-mail: p.vollkkoff@yandex.ru]P. Volkov

Changing the Lighting in the Scenes By Using Neural Networks Cascades 54_7.pdf

The article describes the process of creating the artificial illumination of surfaces taking into account shadows on convex and concave surfaces using machine learning algorithms and methods of working with three-dimensional objects.Despite the variety of applications for photo processing (LightRoom, Photoshop, Snapchat, Instagram etc.), there is a problem associated with the correct modeling of lighting on surfaces, due to the peculiarity of the photo format. First, the photo is a two-dimensional object and contains only indirect information about three-dimensional objects depicted on it. Secondly, the photoimage captures a certain state of objects with a certain set of properties, which are not enough for modeling shadows and lighting. The missing information is difficult to recreate by classical algorithms or heuristics because of the large number of parameters for recognition of objects in the photo and their possible combinations. However, machine learning algorithms are able to approximate very complex functional relationships based on training samples. This article describes the solution to the problem of modeling artificial lighting and shadows in photography using several neural networks trained on synthetic data.

Artificial intelligence, neural networks, machine learning, computer vision.

2018_ 4

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Vladislav Sergeevich Poletaev, Ulyanovsk State University, graduated from Ulyanovsk State University; a degree-seeking student of the Department of Telecommunication Technologies and Networks at Ulyanovsk State University; an author of several articles in the field of forecasting of information security threats based on the method of Internet Forums’ data analysis. [e-mail: vladis173@mail.ru]V. Poletaev

Fuzzy Inference About Information Security Threats Based on Data Analysis From Hacker Forums 54_8.pdf

This article describes an approach to solving the problem of forecasting the risk of new threats to information security by fuzzy inference based on the analysis of text message flow from hacker forums.The method of determining the information security threats is considered. A model of the online forum database based on the analysis of the existing software platforms for the implementation of the Internet forums is created. The online-forum message structure is presented. Empirical rules for the hacker forum functioning and rules of fuzzy system outputs of the fuzzy inference about possible information security threats are formulated. The statistical performances of several hacker forums and an example of fuzzy inference about the risk of information security threats are provided.

Threat forecasting, fuzzy inference, information security, message flow, model of forum.

2018_ 4

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Kirill Valerevich Sviatov, Ulyanovsk State Technical University, Candidate of Science in Engineering; graduated from Ulyanovsk State Technical University; Dean of the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of articles, monographs, textbooks, and certifications of software registration in the field of machine learning and robotic engineering. [e-mail: k.svyatov@ulstu.ru]K. Sviatov,

Aleksandr Viacheslavovich Mikheev, Ulyanovsk Regional Center of New Information Technologies at UlSTU, graduated from Ulyanovsk State Technical University; software engineer of the Ulyanovsk Regional Center of New Information Technologies at UlSTU; interested in the field of machine learning. [e-mail: a.miheev@simcase.ru]A. Mikheev,

Maksim Andreevich Shliamov, Ulyanovsk State Technical University, Student of the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; interested in the field of machine learning. [e-mail: m.shlyamov@simcase.ru]M. Shliamov

Software Package for Visual Monitoring of the Cargo Transportation 53_7.pdf

The article considers the process of designing and implementing a software package to check the completeness of trucks loading when passing checkpoints using technical vision algorithms and machine learning methods. Load completeness checking is used in the governmental supervision of the Russian roads operation as well as checking the cargo transportation volume by private companies when executing orders under the agreements for cargo transportation services. The article deals with the problem of supervising the volume of transported cargo in open-top trucks with bulk non-metallic materials (sand, gravel, coal). Currently, the problem of road-freight transport weight-checking is solved in most cases by the use of weighing units. Also, there are solutions when ultrasonic distance sensors are used that generate a signal corresponding to the shape of the vehicle when driving under several sensors. However, these solutions are quite expensive to install, they do not consider the difference between signals when various vehicle types or models are used on one route. In addition, the weight does not always reflect the completeness of the load body because some materials weigh much more than payload at low volume. And under different weather conditions (e.g. high humidity), the mass of certain goods can vary significantly within 15 percent. At the same time, the transportation efficiency is estimated based on the minimum possible number of passes for the export of cargo of the given volume. The vision systems allow to solve the problem on checking the transported bulk cargo volume. The article focuses on the development description of such a system.

Computer-aided design, artificial intelligence, neural networks, machine learning, computer vision.

2018_ 3

Sections: Information systems

Subjects: Information systems, Artificial intelligence.


Ilia Vladimirovich Zhuikov, Volga State University of Technology, Postgraduate Student; graduated from the Department of Applied Mathematics and Information Technologies of Volga State University of Technology; an author of articles in the field of intelligent test systems. [e-mail: zhuikill@yandex.ru]I. Zhuikov,

Igor Nikolaevich Nekhaev, Volga State University of Technology, Candidate of Science in Engineering, Associate Professor of the Department of Applied Mathematics and Information Technologies of Volga State University of Technology, Head of the e-Learning Center of Volga State University of Technology; an author of scientific papers in the field of soft computing, fuzzy logic, and e-learning. [e-mail: nehaevin@volgatech.net]I. Nekhaev

Application of Lp-structures When Constructing the Intelligent Test System 53_8.pdf

Tasks of competence level are complex tasks for solving which is not enough only knowledge, so learning and testing systems should be able to simulate structures of gradually complicating tasks. In some cases, these structures can be modeled using mathematical lattices describing the structure of cases with additional attitude of complication. This article describes a model of the lattice of non-complication of cases for the subject domain. A method for specifying and constructing such lattice using finite LP-structures and applying operations of transitive closure on the lattice of clarification of case situations is proposed. In conclusion, the example of using this approach to construct intelligent test system of the ability to perform solve tasks of comparing numbers from the domain of arithmetic of natural numbers is considered. It is shown that this approach could be used for further analyzing the results of solutions and to construct a more pragmatic lattice of complication of cases and test tasks.

Lp-структура, competency-based approach, intelligent test system, lattice of complication of cases, lp-structure.

2018_ 3

Sections: Information systems

Subjects: Information systems, Mathematical modeling, Artificial intelligence.


Gennadii Pavlovich Vinogradov, Tver State Technical University, Doctor of Engineering; graduated from Kalinin Polytechnic Institute; Professor of the Department of Informatics and Applied Mathematics of Tver State Technical University; an author of more than 200 scientific papers in the field of decision making theory, fuzzy logic, and hybrid systems. [e-mail: wgp272ng@mail.ru]G. Vinogradov

The Model for Decision Making Process in Situations With Incomplete and Fuzzy Information 52_12.pdf

It is shown that an agent when making decisions uses three sets of alternatives: control, structural, and identification. This presupposes the existence of three virtual parties involved in the selection of appropriate alternatives. Rules for the selection of alternatives depending on the subject's understanding of the situation and structure their interests are shaped by compromise. The work seeks to investigate the causes of discrepancies between actual and "optimal" choice. To this end, we propose a formal scheme included in the choice model of the stages of cognition and behavior associated with the choice. The proposed approach is based on a formalization of the ideas of Miller, and Pribram Galanter and uses the ideas of subjectively rational choice developed based on the theory of fuzzy sets. Subjectively rational choice assumes that the motivation of the choice is determined by both external and internal factors. Internal factors reflect the interests of the subject determined by its needs and ethical system to which it adheres. Evaluation of satisfaction with the current situation purposeful state entity, as shown, can lead to changes in the structure of interests of the subject, and it can choose.

Reflexive governance, decision-making model, a compromise.

2018_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Sergei Vasilevich Voronov, Ulyanovsk State Technical University, Candidate of Engineering; graduated from the Faculty of Radioengineering of Ulyanovsk State Technical University; Associate Professor of the Radioengineering Department of UlSTU; an author of articles, monographs in the field of digital signal and image processing and computer vision. [e-mail: valmedia@yandex.ru]S. Voronov,

Rinat Nailevich Mukhometzianov, University of Waterloo, Canada, Postgraduate Student at the University of Waterloo, Canada; graduated from the Faculty of Radioengineering of Ulyanovsk State Technical University; an author of articles in the field of computer vision. [e-mail: mukhometzyanov@mail.ru]R. Mukhometzianov,

Ilia Vasilevich Voronov, Ulyanovsk State Technical University, Postgraduate Student at Ulyanovsk State Technical University; graduated from the Faculty of Radioengineering of Ulyanovsk State Technical University; an author of articles in the field of digital signal and image processing. [e-mail: ilvo1987@gmail.com]I. Voronov,

Vadim Andreevich Shramov, Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’, Postgraduate Student at Ulyanovsk State Technical University; graduated from the Faculty of Radioengineering of Ulyanovsk State Technical University; Research-Engineer at FRPC JSC ‘RPA ‘Mars’. [e-mail: vadim_shramov@mail.ru]V. Shramov

Trafic Sign Detection and Recognition in Real Time on Mobile Devices 52_13.pdf

An automatic traffic sign recognition system localizes road signs from images captured by an onboard camera of a vehicle and determine what road signs depicted. Such systems may support the driver on the road, be part of the self-driving cars or advanced driver assistance systems. This paper proposes an approach for solving traffic sign recognition problem using deep learning methods adopted to mobile devices with low power consumption. The approach consists of two consecutive stages: detection of a traffic sign and recognition of a class of the detected sign. Data for analysis were taken from three open sets of images. In order to analyze the effectiveness of the solution obtained, the results achieved were compared with the results of well-known approaches to object detection based on the use of deep convolutional neural networks. The results showed that the proposed algorithm provides the best recognition quality for all used data sets, as well as the highest recognition rate.

Deep learning, viola-jones detector, convolutional neural networks, traffic sign recognition, object detection.

2018_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence.


Amir Muratovich Akhmetvaleev, Kazan National Research Technical University named after A.N. Tupolev-KAI, Postgraduate Student of Kazan National Research Technical University named after A.N. Tupolev-KAI; graduated from the Faculty of Technical Cybernetics and Informatics of the Kazan State Technical University named after A.N. Tupolev-KAI; an author of scientific works in the field of mathematical modelling, data analysis and machine learning methods. [e-mail: amir.akhmetvaleev@gmail.com]A. Akhmetvaleev,

Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. Tupolev-KAI, Candidate of Engineering; graduated from the Faculty of Physics and Mathematics of Elabuga State Pedagogical Institute; Associate Professor of the Information Security Systems Department of Kazan National Research Technical University named after A.N. Tupolev-KAI; an author of scientific works in the field of mathematical modelling, data analysis and development of intelligent decision support systems. [e-mail: Kat_726@mail.ru]A. Katasev

Instrumental Software Complex for Automation to Determine the Functional State of Intoxication of a Person 52_14.pdf

This article actualizes the need to determine the functional state of a person. Its decision is based on the application of the pupillometry method, which allows to determine the state of a person by his pupillary reaction to light changes. In order to automate the processes of determining the functional state of a person, an instrumental program complex is developed, based on the use of the neural network model. Its structure, composition and characteristics of components are described. The functioning of the program complex is considered on the example of the modules of neural network model construction, estimation of its accuracy on the basis of bootstrapping method, structural optimization of the model, and determining the functional state of a person. A number of researches and experiments were conducted on the basis of the program complex. The results of the influence of the number of stages of bootstrapping on the accuracy of the neural network model, the results of reduction of neural networks, the comparison of the accuracy of the model with the accuracy of other classification methods are presented. The results of the research showed the effectiveness of the neural network model and the possibility of its practical use to determine the functional state of the person in various subject areas.

Human functional state, papillomometry, neural network model, genetic algorithm, bootstrapping.

2018_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence, Information systems.


Petr Ivanovich Sosnin, Honored Worker of Higher School of the Russian Federation, Doctor of Engineering, Professor; graduated from the Radioengineering Faculty of Ulyanovsk Polytechnic Institute; Head of the Department of Computer Science at Ulyanovsk State Technical University; an author of numerous works in the field of conceptual design of computer-aided systems, [e-mail: sosnin@ulstu.ru]P. Sosnin,

Anna Aleksandrovna Pushkareva, Ulyanovsk State Technical University, Postgraduate Student at the Department of Computer Science of Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies; interested in the field of applied linguistics. [e-mail: a.push1206@gmail.com]A. Pushkareva,

Andrei Alekseevich Vasilev, Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’, Postgraduate Student of Ulyanovsk State Technical University; graduated from the Power Faculty of Ulyanovsk State Technical University; Head of Research Department at Federal Research-and-Production Center Joint Stock Company ‘Research-and-Production Association ‘Mars’; interested in the field of CAD-systems. [e-mail: mars@mv.ru]A. Vasilev

The Complex of Ontological Support for Processes of Solving New Design Tasks in Development of Systems With Software 000_11.pdf

The article presents a method of ontological support increasing efficiency of project thinking, when in the development of a software intensive system, the designer discovers the need to solve a new design task. Support is provided in the conditions of application of the version of the project thinking, in the processes of which the means of question-answer and case-oriented approaches are included, which ensure the constructive formation of the project task tree. The components of the tree register not only the texts of task statements but also the question-answer reasoning of the processes of solving each task. The proposed method of ontological support is aimed at the search for design errors, their correction and prevention, as well as on the extraction of useful questions and support of understanding processes in the design process in real time. In addition, it allows you to identify in the texts the cause-effect relationship and the «part-whole» relationship. The basis of the proposed method is the use of question-answer and precedent-oriented approaches to work with the project task, the formulation of which is built in the process of its conceptual solution.

Conceptual design, lexical control, ontology, precedent, project thinking, semantics.

2017_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence, Information systems.


Amir Muratovich Akhmetvaleev, Kazan National Research Technical University named after A.N. Tupolev, Akhmetvaleev, graduated from the Faculty of Technical Cybernetics and Informatics of Kazan National Research Technical University named after A.N. Tupolev; Postgraduate student of Kazan National Research Technical University named after A.N. Tupolev; an author of scientific works in the field of mathematical modelling, data analysis and machine learning methods. [e-mail: amir.akhmetvaleev@gmail.com]A. Akhmetvaleev,

Aleksei Sergeevich Katasev, Kazan National Research Technical University named after A.N. Tupolev, Candidate of Engineering; graduated from the Faculty of Physics and Mathematics of Elabuga State Pedagogical Institute; Associate Professor at the Department of Information Security Systems of Kazan National Research Technical University named after A.N. Tupolev; an author of scientific works in the field of mathematical modelling, data analysis and development of intelligent decision support systems. [e-mail: Kat_726@mail.ru]A. Katasev

Neuro Network Model and Software Package for Human Functional State Determining 000_12.pdf

The article considers the problem of determining the functional state of intoxication of a person. For its solution, the authors propose a method based on the analysis of data pupillograms - time series characterizing the dynamics of changing the size of the pupils of the person on light-pulse exposure. As a tool for data mining and model building in order to determine the functional state of the person the authors propose to use the mathematical apparatus of artificial neural network - single layer perceptron. The original neural network model is proposed, and its adequacy is evaluated. In order to improve the efficiency of its practical use, a method of reduction of a neural network structure based on genetic algorithm is being developed. The proposed method is a two-stage genetic optimization that allows to determine the significant input features for a neural network on a given input feature space in order to optimize the structure of neurons in the hidden layer. The results of the experiments on the basis of the developed program complex have shown high efficiency of determination of the person functional state based on the reduced neural network model. The model can be effectively used in intelligent surveillance systems in public safety systems, as well as in medical diagnostics as a tool for contactless determination of the functional state of intoxication of a person.

Neural network model, determination of the functional state, genetic algorithm, pupillometry, evaluation of data quality, data cleaning.

2017_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence, Information systems.


Grigorii Aleksandrovich Blagodatskii, Kalashnikov Izhevsk State Technical University, Candidate of Engineering; Associate Professor at the Department of Information Systems of Kalashnikov Izhevsk State Technical University; an author of articles and monographs in the field of automation and optimization of business processes of enterprises and certificates of registration of databases and computer programs. [e-mail: blagodatsky@gmail.com]G. Blagodatskii,

Maksim Mikhailovich Gorokhov, Kalashnikov Izhevsk State Technical University, Doctor of Physics and Mathematics; Professor; Head of the Department of Information Systems of Kalashnikov Izhevsk State Technical University; an author of articles and monographs in the field of development and design of software and hardware tools for various purposes as well as the certificates of registration of databases and computer programs. [e-mail: insys2005@mail.ru]M. Gorokhov,

Denis Alekseevich Perevedentcev, Kalashnikov Izhevsk State Technical University, Postgraduate Student at the Department of Information Systems of Kalashnikov Izhevsk State Technical University; an author of articles and monographs in the field of design and development of expert systems for supporting the processes of management of research and innovation projects as well as the certificate of registration of databases and computer programs. [e-mail: perevedencew@mail.ru]D. Perevedentcev

Modelling the System of Fuzzy Logical Inference for Evaluating Science-intensive Projects 000_11.pdf

In order to determine the innovative potential and prospects of science-intensive projects, it is required to account for a large number of parameters that covers the whole interaction system of the specific time with the environment. The purpose of the study is developing models, methods, algorithms and software for processes aimed at improving the efficiency of management of research and innovation projects. Today, fuzzy inference is widely used in modeling systems characterized by predominantly qualitative parameters. In order to solve the problem, a fuzzy logic system based on the Mamdani algorithm was developed. With the use of factor analysis, eight factors from the total set of projects’ parameters were identified. In the estimates of the factors of the project state, several ranges of values were revealed and the respective linguistic variables were implemented. The result of the application of author’s algorithms is a system of fuzzy inference built in the Matlab FUZZY environment. The system describes the commercial appeal, level of completion and prospects of knowledge-intensive projects. On the basis of the calculated characteristics of the project, the algorithm of evaluation of science projects was developed. The algorithm of solving the problem of multi-objective optimization for selecting projects from the database was presented.

Fuzzy inference, high-tech projects, complex systems, effective evaluation, algorithm of evaluation, selection algorithm.

2017_ 2

Sections: Artificial intelligence

Subjects: Artificial intelligence, Information systems.


Pavel Vladimirovich Dudarin, Ulyanovsk State Technical University, Postgraduate Student at the Department of Information Systems of Ulyanovsk State Technical University (UlSTU); graduated from the Ulyanovsk State Technical University; an author of papers in the field of text clustering. [e-mail: PDudarin@ibs.ru]P. Dudarin,

Aleksandr Petrovich Pinkov, Ulyanovsk State Technical University, Candidate of Economics, graduated from Ulyanovsk branch of Kuibyshev Planning Institute; Acting Rector of Ulyanovsk State Technical University, an author of more than 50 papers, a monograph, and articles in the field of economics, planning, marketing, production engineering, higher education organization, and corporate training. [e-mail: rector@ulstu.ru]A. Pinkov,

Nadezhda Glebovna Yarushkina, Ulyanovsk State Technical University, Doctor of Engineering, Professor; First Vice-Rector - Vice-Rector for Scientific Affairs of Ulyanovsk State Technical University; Head of the Department of Information Systems of UlSTU; graduated from Ulyanovsk Polytechnic Institute; an author of more than 300 papers in the field of soft computing, fuzzy logic, and hybrid systems. [e-mail: jng@ulstu.ru]N. Yarushkina

Methodology and the Algorithm for Clustering Economic Analytics Object 000_12.pdf

The purpose of the study, the results of which are described in the article, consist in developing new and modified methods and algorithms for solving the problem of clustering objects of economic analytics. The use of known algorithms for clustering formulations of economic indicators in order to determine the similarity of objects is complicated by the fact that the formulation of indicators are very short and the traditional indicators of terms occurrence (frequency) are inadequate. In addition, widespread occurrence of interviews and various forms of questionnaires in economic analysis implies the use of linguistic estimates. For example, "customer satisfaction level" indicator is difficult to quantify, so, instead of conventional points, fuzzy values such as “high”, “medium”, “low” are often used. As a result, it becomes feasible to use a fuzzy variant of the k-means method - the method of fuzzy k-means. Typically, the number of indicators in economic analysis is quite big, which makes it advisable to modify the algorithm on the basis of parallel execution. The study addresses the following issues: the k-means method is modified, it is adapted to the characteristics of the economic analytics objects; the methodology of data preprocessing for clustering is developed; new versions of clustering objects of economic analytics are developed, and experimental research of the effectiveness of the developed methods for large volumes of data is carried out.

Fcm-алгоритм, clustering, method of k-means, economic analysis, big data, fcm-algorithm, parallelization.

2017_ 1

Sections: Artificial intelligence

Subjects: Artificial intelligence.


© FRPC JSC 'RPA 'Mars', 2009-2021 The web-site runs on Joomla!