Intelligent Computing

No Author(s) Report Title Abstract
1 Luidmila Bilgaeva,
Erzhena Sadykova,
Gregory Badmaev
Associative Search of Indicators for the Evaluation of Integration Processes The article is devoted to the formation of indicators for the evaluation of integration processes using the method of searching for associative rules using binary tables. In the process of searching for rules, calculation of such parameters as support, reliability and utility is carried out. The indicators thus obtained can be used in the prediction task.
2 Aslanbek Murzakhmetov,
Anatolii Fedotov,
Anuar Dyusembaev,
Mikhail Grishko
MODEL OF INNOVATION DIFFUSION IN THE SOCIAL SYSTEM UNDER THE INFLUENCE OF THE MEDIA AND INTERPERSONAL COMMUNICATION The article deals with the diffusion of innovation in a social system, its dynamics in social communities under the influence of the mass media and interpersonal communication; and the process of shaping public opinion. Models of innovations diffusion are analyzed here. As the research results show, the processes of diffusion of various information messages in social systems can determine mass consciousness and, accordingly, mass behavior of people in these social systems.
3 sheheryar Khan,
Guoxia Xu,
Hong Yan
Tensor Learning using N-mode SVD for Dynamic Background Modelling and Subtraction In this paper, we address the problem of modelling dynamic backgrounds in online tensor leaning framework. We use Tucker decomposition to model the spatio-temporal correlation of video background. To facilitate the online execution of foreground detection, we incrementally update the subspace factor matrices and core tensor by using the N-mode SVD. For the upcoming frame, the estimate of new basis matrix is updated, whereas the contents from last observation are removed.
4 Alexander Afanasyev,
Nikolay Voit,
Maria Ukhanova,
Irina Ionova
Treatment of design-engineering workflows in large enterprises The authors presented the analysis of design-engineering workflows in large design and manufacturing enterprise as well as developed a layered structure of similar enterprises' design workflows according to the IBP Rational Unified Process methodology. The problem of the coordination of design-engineering documentation was examined. The author's model of the Petri net modeling model flows of project works in coordination with design-engineering documentation is developed.
5 Alexander Afanasyev,
Nikolay Voit,
Dmitriy Kanev,
Sergey Brigadnov
Development of expert system for the evaluation of student action in virtual worlds and training systems One of the approaches to future engineers' training to develop their applied competences is the use of virtual workplaces. To train a specialist on real equipment is often economically inefficient and involves risks to health, and sometimes it is not possible. However, the task of students' actions assessment in both simultaneous and virtual systems has not yet been solved in its full completeness.
6 Vladimir Voronin,
Oleg Davydov
Local Area Network failures types, consequences and criticality analysis LAN system hierarchical decomposition into basic elements has been carried out. In accordance with the received scheme, a list of equipment to be diagnosed is highlighted. Each unit of LAN equipment has been evaluated for criticality. LAN good technical condition criteria are determined. Failures types, consequences and criticality for possible malfunctions are analyzed. Existing or emerging defects diagnostic indicators are determined.
7 Alexander Afanasyev,
Nikolay Voit,
Andrei Igonin
Analysis and control of dynamic distributed workflows in the design and reengineering of complex automated systems Authors propose a method for analyzing, control and translation distributed workflows based on own RV-, RVTt- grammars. The languages BPMN and BPEL are used by the authors as an example. An estimation of the method effectiveness is presented.
8 Aleksandr Fedorets,
Evgeny Pustovalov,
Evgeny Modin,
Vladimir Tkachev etc.
Regularities in the disordered atomic structure of rapidly quenched amorphous cobalt-based alloys Research presents regularities investigation in the atomic structure of amorphous rapidly quenched Co58Ni10Fe5Si11B16 at.% alloys. The alloys were quenched on a copper wheel with a linear surface velocity from 22 to 38 m/s. We found nonlinear dependence of local atomic ordering from linear velocity of cooling wheel. Average lateral density of ordered atomic clusters of 5 nm size changes from 4% to 8%.
9 Alexy Tarasov ПРОГРАММНАЯ ОБОЛОЧКА ДЛЯ СОЗДАНИЯ ИНТЕЛЛЕКТУАЛЬНЫХ СИСТЕМ В ПРАКТИЧЕСКОЙ И ОБРАЗОВАТЕЛЬНОЙ МЕДИЦИНЕ. Предлагается концепция оболочки для разработки и использования сообщества медицинских интеллектуальных систем, которая позволяет сконцентрировать в одном виртуальном пространстве их информационные и программные ресурсы и обеспечивать доступ к ним пользователей независимо от их географического положения.
10 Alexey Finogeev,
Anton Finogeev
Monitoring of urban transport infrastructure for the intelligent environment "Smart Road" In the article monitoring of urban transport infrastructure on the basis of a distributed network of photo-fixation and video surveillance systems of road accidents is considered. The main goal is to analyze, evaluate and forecast transport situations for preventive response to incidents. Realization of monitoring tasks is offered on the real time Big Data processing, intellectual analysis and deep machine learning. The monitoring system is an integral part of the Smart&Safe City.
11 Vladimir Barakhnin,
Olga Kozhemyakina,
Ilya Pastushkov
The approaches to the construction of a joint classifier of genre types and stylistic colouring of poetic texts We propose the algorithm of automated definition of the genre type and semantic characteristics of poetic texts. We formulated the approaches to the construction of a joint classifier of genre types and styles of poetic texts, based on the definition of interdependence of the type of genre and stylistic colouring of the text. On the basis of these approaches the principles of formation of the training samples for the algorithms for the definition of styles and genre types were analysed.
12 Maksim Kenzin,
Nikolay Maskimkin,
Igor Bychkov
Task allocation and path planning for network of autonomous underwater vehicles Cooperative multi-objective missions for connected heterogeneous groups of autonomous underwater vehicles are highly complex operations and it is an important and challenging problem to effectively route these vehicles in dynamic environment under given communication constraints. We propose a solution for the task allocation and path planning problems based on the evolutionary algorithms that allows one to obtain feasible group routes ensuring well-timed accomplishment of all objectives.
13 Dinar Yakupov,
Igor Yakimov
ASPECTS OF CHOOSING THE METHOD OF FORECASTING THE URBAN ROAD INFRASTRUCTURE CONDITION PERFORMANCE a method for reliability assessment of forecasting the performance of urban road infrastructure condition by the statistic methods and ANNs are proposed.
14 Alexander Bozhenyuk,
Stanislav Belyakov,
Margarita Knyazeva
The Method of Allocation Centers in Second Kind Fuzzy Graphs with the Largest Vitality Degree The problem of optimal allocation of service centers is considered in this paper. It is supposed that the information received from GIS is presented like second kind fuzzy graphs. Method of optimal location as method of finding fuzzy vitality set of second kind fuzzy graph is suggested.This method allows solving not only problem of finding of optimal service centers location but also finding of optimal location k-centers with the greatest degree and selecting of service center numbers.
15 Stanislav Belyakov,
Marina Savelyeva
Geoinformation models in Smart Grid Management This paper investigates the problem of distribution of electricity capacity in the territory covered by a Smart Grid. The purpose of management is loss minimization caused by changes in the state of the outdoor environment. We analyze the issues of cartographical representation of knowledge about the behavior of the outdoor environment and use of this knowledge for planning of electrical supply and decision-making in abnormal situations.
16 Maksim Sporyshev Cooperative AUV area coverage with visibility and collision constraints In this paper we consider the problem of autonomous underwater vehicles (AUV) area coverage. Given an area on the plane with static obstacles, find the shortest tour for a group of AUVs such that every point of the area is covered by visibility range of some of the AUVs. Every vehicle is constrained to stay within the area and has limited visibility range.
17 Yuri A. Sukhobok,
Leonid R. Verkhovtsev,
Yulia V. Ponomarchuk
Determination of the soil boundaries from Ground Penetration Data using artificial neuron networks The paper presents a method of automated determination of soil boundaries from the GPR data. For this application, artificial neural networks technique was used to process the traces. Firstly, the baseline theoretical model of data processing was constructed to create the network in the form of a multilayer perceptron. Then, the backpropagation method was used for training ANN.The results were verified by the simulation data, pointing out the applicability of machine learning to the current task
18 Artur Mitsel,
Sergey Kozlov,
Anna German
Dynamic model of rating management of a subject of the Russian Federation The article proposed governance model the probability of default risk of the Russian Federation. This model is based on quality criteria and quadratic linear control law. The model is designed so that its application is possible not only for subjects with already assigned a rating, but also for those of the Russian Federation who do not yet have a rating assigned to one of the leading rating agencies (Standard & Poor's, Fitch Ratings and Moody's).
19 Anton Tolstonogov,
Vladimir Kostenko
Modeling the Transverse AUV Tunnel Thruster in Incoming Water Flow The article presents modeling of transverse tunnel thrusters in incoming water flow. The more accurate numerical simulation of this process using the finite element method is also given. Dependence of generated thrust by the tunnel thruster on the diameter of the tunnel and speed of oncoming flow is shown. General recommendations for designing tunnel thrusters and tuning of the switching threshold for vehicle control by stern thrusters or tunnel thrusters are given.
20 Evgeny Kostyuchenko,
Ivan Botnarenko,
Dariya Ignatieva,
Alexander Shelupanov
User identification by the free-text keystroke dynamics. The article discusses the possibility of user identification based on free-text keystroke dynamics for the Russian language. Article describes software for receiving of free-text keystroke dynamics characteristics and designed database for them storage. The using of a naive Bayesian classifier for the task is described. Preliminary quantitative assessment of the user identification quality. The requirements and material for the future studies was accumulated.
21 Galina Troshina,
Alexander Voevoda
The Steady-State at the Parameters Estimation Algorithm for Dynamic Objects The iterative scheme for the dynamic parameters estimation in the conditions of dynamics noises is offered. It is supposed that there is an opportunity to give the required input signal on an object. The input signal like a meander is used. The dynamic object modeling and recursive least-squares method modeling are executed in the Simulink environment. The parameters estimation results are given. The offered approach allows to specify object parameters that is actually in engineering practice
22 Sergey Rylov,
Igor Pestunov
Nonparametric clustering algorithm for image segmentation combining grid-based approach and mean-shift procedure Nonparametric clustering is attractive because of its ability to discover arbitrary shaped clusters. Grid-based methods are nonparametric and computationally efficient, but their accuracy is limited by the grid structure. A novel clustering algorithm that combines grid-based HCA algorithm with mean-shift procedure for cluster boundaries refinement is proposed. Experiments show significant improvement of clustering accuracy over HCA and withal the algorithm is considerably faster than mean-shift.
23 Mikhail Grishchenko,
Alexander Yakimenko,
Marat Khairetdinov,
Anastasiia Lazareva
Randomization-based enrichment analysis using GPU: the ways of performance improvement In this paper, the permutation test algorithm for randomization-based enrichment analysis is considered. This algorithm are widely used to solve the problem of processing genetic data for the analysis genetic determination of traits. The software tool implementing this algorithm on the GP GPU was developed. Permutation test algorithm was improved for simultaniously testing set of independent gene characterisitcs. The ways of improvement this algorithm performance is investigated.
24 Igor Semaev Experimental Study of DIGIPASS GO3 and the Security of Authentication Based on the analysis of 6-digit one-time passwords (OTP) generated by DIGIPASS GO3 manufactured by VASCO and used for authentication in Norwegian banks we were able to reconstruct the synchronisation system of the token, the OTP generating algorithm and the verification protocol in details essential for an attack. The OTPs are more predictable than expected. A forgery attack is described. The implications for the security of authentication are discussed and open questions are formulated.
25 Александр Ефимов,
Сергей Мамойленко
Стохастическая модель организации функционирования большемасштабных распределенных вычислительных систем Количество вычислительных узлов в современных распределенных вычислительных системах (ВС) достигает сотен тысяч, в перспективных системах этот показатель может достичь нескольких миллионов. В работе на основе методов Теории массового обслуживания, Теории игр и Теории вычислительных систем разработана стохастическая модель децентрализованного управления большемасштабными распределенными ВС.
26 Alexander Borodin,
Alexander Meigal,
Dmitry Korzun,
Yuliya Zavyalova etc.
Assessing and Improving the Treatment Adherence among Hypertensive Outpatients in Smart Spaces based on Continuous Health State Monitoring and Mobile User Engagement Models. Affecting up to 40% of the world's population, arterial hypertension is the most essential preventable risk factor of premature death. Due to the long-term treatment period, the outpatients often give up the treatment. In this paper, we extend the previously proposed smart space-enabled service for hypertension management assistance with the way of assessment of the treatment adherence based on of joint analysis of the health-related parameters and continuously collected mobile analytics data.
27 Dmitriy Mikhajlenko,
Artem Lenskiy
Research of echo state networks topologies and learning algorithms in data prediction tasks. This paper shows using of echo state networks architectures for time series prediction and generation tasks and the influence of learning algorithms on the quality of the output values of the network.
28 Yana Eroshenko fine dust harmfullness level assasment This article describes harmfulness level of fine dust particles smaller than 10 micron. It shows poor development of this problem, thus there is a necessity for further research. Also it tells about a probability of rough estimation of PM10 and PM2.5 particles levels, in case of special hardware absence. And results of computational methods slightly differs from results given from special hardware.
29 Oleg Evsutin,
Roman Meshcheryakov,
Nikolai Yugov,
Viktor Genrikh etc.
An improved algorithm of digital watermarking based on wavelet transform using learning automata In this paper, we present an algorithm for embedding digital watermarks in digital images. Embedding is based on block quantization of DWT coefficients. A distinctive feature of this paper is the use of learning automata for the optimal redistribution of energy in blocks of DWT coefficients during the quantization. The obtained algorithm is highly efficient in terms of the quality criteria for embedding and can be used both for embedding digital watermarks and for arbitrary messages.
30 George Volosnyh,
Nina Kazachek,
Gennady Kalach
Improving the executive level dynamics of the mobile robot based on fuzzy logic technology Improving the executive level dynamics of the mobile robot based on fuzzy logic technology
31 Anastasia Iskhakova,
Roman Meshcheryakov
Automatic search of the malicious messages in the Internet of things systems on the example of an intelligent detection of the unnatural agents requests The article considers one of the actual threats of the Internet of things related to the transmission of malicious or incorrect electronic messages between agents. Methods of the transmitted data automatic verification and filtering by some set of features in Internet systems of things are analyzed. Authors propose an approach to the intelligent detection of unnatural requests between agents, which could minimize the likelihood of the implementation of threats.
32 Alisa Fedorchenko Modelling of imitative behavior and vicarious learning in swarm robotics The general principles of interaction in groups of robots on the basis of models of social behavior are discussed. A new method for implementing an organization in groups of robots based on social behavior is proposed. Mechanisms of imitative behavior and vicarious learning are considered.
33 Olga Smirnova,
Leonid Sharnin
Automated recognition of cancer tumors in the human brain using magnetic resonance imaging and neural networks People all over the world suffer from cancer. A wide popularity is gained by scanning the human brain with MRI. Using the information obtained and analyzing the images, we define the zones that are investigated using mathematical methods for determining objects. In the images identified during the MRI examination, we determine the boundaries of education, studying in which zone it is located. Automatic detection of tumors helps to detect all potential formations.
34 Valentin Golodov,
Anna Zavei-Boroda,
Sergei Ivanov,
Kseniya Nikolskaya
Development of a deep learning neural network for human movements analysis The article deals with the recognition of the sensor/intuit subtype according to the empirical typology of K.G.Jung. A video fragment with the recording of human movements is used as the input data. Preliminary processing includes algorithms for processing the frames of the video fragment for selecting the skeleton of the image and then using it as input data to an artificial neural network of deep learning. The topology of the neural network is supposed.
35 Dmitry Bogomolov,
Anton Morozov,
Aksinya Sokolova
Development and analysis of the informational monitoring system on road surfacing condition with using mobile devices. The research is dedicated to the creation of information system for road pavement condition monitoring and the development of software to work with this system using mobile devices.
36 Denis Pechenkin,
Ivan Shcherbatov,
Oleg Protalinskiy
Risk assessment for poorly formalized technological process Management of technological process in real time is associated with the emergence of risks related not only with the technical component work of a hazardous production facility, but also inaccurate or untimely assessments pre-emergency or emergency situations on the part of staff. We substantiate the expediency of fuzzy logic application for risk assessment of technological processes and control these risks.
37 Irina Timina,
Eugene Egov,
Nadezhda Yarushkina,
Dmitry Yashin
The use of the aggregator for choosing the method of forecasting time series In this paper, we propose an approach to optimizing the solution of the problem of forecasting time series. Optimization of the solution consists in using an aggregator to select the forecasting methods that will give the best forecast. When choosing methods, the time series features are taken into account. The aggregator uses methods of machine learning to select methods. The aggregator is built into the information system "Combination of fuzzy and exponential models".
38 Egor Pugin,
Arkady Zhiznyakov
Image segmentation using fuzzy pixel representation In our paper we propose a novel approach to image processing based on fuzzy sets, that suggest a transition to fuzzy image representation with fuzzy pixels on the earliest stages of processing.
39 Roman Senchenko,
Nina Krapukhina
Multi-agent simulation modelling with intellectual agents for city traffic control This work suggests an approach to developing a traffic control system based on a multi-agent model of a road network. The intellectual agents flow in simulation model is adjusted in real time mode based on the data from standard video systems. The agents in the model describe their intellectual cooperation, and reflects the dynamics and system qualities of the real traffic flows. The regulation decisions are made as a result of the series of calculation experiments in real time mode.
40 Yana Smekhun,
Irina Artemieva
Modeling of communicative interaction Human language is extremely complex system.
41 Tatyana Afanasieva,
Aleksey Sapunkov
Software of Time Series Forecasting based on Combinations of Fuzzy and Statistical Models The developed software is a web application with open access and is aimed on forecasting of time series stored in database. We proposed approach of time series forecasting, combined ARIMA models with fuzzy techniques: three fuzzy time series models, fuzzy transformation (F-transform) and ACL-scale. Applications of a proposed web service have demonstrated efficiency in practical time series predictions with suitable accuracy.
42 Valery Ovcharuk,
Maksim Kutsenko
Features of spectral analysis methods application for solving problems of acoustic emission signals processing The article describes main problems of the acoustic-emission method of nondestructive testing. A comparative evaluation of the efficiency of acoustic emission signals parameters is carried out. This work is underlined inadequacy of spectral analysis methods in a narrow frequency band. As an example, the results of spectral analysis of acoustic emission signals are given. On the base of this, the necessity of using spectral analysis to increase the reliability of the results is substantiated.
43 Ivan Khramoin,
Margarita Kamenskaya,
Ilya Tikhomirov,
Natalya Toganova
Sentiment Analysis of Innovations in Russian Media The paper presents the sentiment analysis based algorithm for evaluation of public's attitude to innovations. Domain-depended corpus for training algorithm was created. More than 200 000 articles from Russian mass media devoted to innovations were analyzed. Results of analysis represented as set of histogram. Conclusions and future work are given.
44 Maksim Kutsenko Wavelet analysis efficiency in acoustic emission measurement systems This paper is devoted to comparative evaluation of the efficiency of wavelet transformation and traditional methods in relation to problems of acoustic emission signals identification.
45 Yuliya Leonova,
Anatolii Fedotov,
Olga Fedotova
THEMATIC CLASSIFICATION OF THE THESIS ABSTRACTS In this paper the method of thematic classification of the thesis abstracts. It uses specially constructed proximity measure documents, taking into account the specificity of the subject area. The values of the weighting coefficients in the formula for calculating the proximity of the proposed measures are defined a posteriori reliability of the corresponding scale data.
46 Vladimir Bukhtoyarov,
Vadim Tynchenko,
Eduard Petrovskyi,
Natalya Bukhtoyarovs
Neural network diagnostic system for some types of oil and natural gas industry equipment Neural network diagnostic system for some types of oil and natural gas industry equipment is developed. Basic scheme of such a system is suposed. Basic input data types and data sources fo neural network diagnostics are explored. Parameters and results of statistical numerical experiments are discussed.
47 Yulia Shichkina,
Mikhail Kupriyanov,
Mohammed Al-Mardi
The construction of the parallel algorithm execution schedule taking into account the interprocessor data transfer The method of constructing a schedule for parallel algorithm execution is considered in the article. The method is based on an information graph. As a result of the interchange of operations between computing nodes, it is possible to achieve a reduction in the execution time of the algorithm by reducing the time spent on transferring data between nodes and reducing node downtime.
48 Yaroslav Fedulov,
Vadim Borisov,
Alexander Fedulov
Fuzzy model and method of rating university evaluation This paper presents a method for constructing a fuzzy evaluation model, considering the compatibility of the indicators and the possibility of both direct and inverse inference.
49 Nikolai Gorlov,
Evgeniya Kitova
Computer Processing of Results of Reflectometric Measurements The report proposes the algorithms for processing the results of the pulse-sensing telecommunications optical fiber in order to obtain reliable measuring information about losses and back reflection. The proposed software allows automatic searching of local inhomogeneities in optical fiber, the identification of the reflectograms, comparative analysis and reporting.
50 Evgeny Lipachev,
Alexander Elizarov,
Shamil Khaydarov
Semantic representation of digital libraries using ontologies for describing scientific documents We present a system of services for the automatic processing of collections of scientific documents that are part of digital libraries. These services are based on ontologies describing scientific documents, as well as methods for the semantic analysis of mathematical documents. These services automatically check documents for compliance with the rules, convert to established formats and form metadata.
51 Alexander Zuenko МATRIX-LIKE STRUCTURES IN SOLUTION OF CONSTRAINT SATISFACTION PROBLEMS The paper presents two types of matrix-like structures, the C-systems and the D-systems, which are proposed to be used in representation and handling the constraints over finite domains. The modifications of the well known constraints propagation algorithms have been developed by the author. The proposed approach allows representing the n-ary relations in a compressed form, and accelerating searching the solution by means of analyzing the specific features of the constraints matrices.
52 Aleksey Senkov,
Mikhael Margolin
Modeling of fuzzy business processes in solving operational planning tasks The article proposes a new approach to modeling fuzzy business processes, that combines the advantages of existing ones and expanding their capabilities by simultaneously assessing the characteristics of the business process results, the reliability of these results, and assessing the time during which they were obtained.
53 Alexander Evsyukov Infographic and geoinformation modeling in OLAP-technology for web-applications The article is devoted to developing the infographic and geoinformation modeling technologies for the multidimensional data representation in web-applications. Methods for presenting the analytical processing results determine the cognitive effectiveness of OLAP. The article considers methods of automatic generation of infograms for the analysis of multidimensional data. Using the infographic modeling tools in web applications allows to expand the target audience, increase interest in content.
54 Alan Savushkin,
Igor Ivanov,
Gennady Kalach
The use of convolutional neural networks in the tasks of computer vision of an unmanned aerial vehicle The use of convolutional neural networks in the tasks of computer vision of an unmanned aerial vehicle
55 Dmitriy Pesterev,
Liudmila Massel
TRANSFORMATION OF COGNITIVE MODELS INTO KNOWLEDGE BASE OF PRODUCTION EXPERT SYSTEM Cognitive modeling is one of the types of semantic modeling used to energy security study. The automation of the process of cognitive models analyzing is considered. To solve this problem, the author suggests using the capabilities of product expert systems. The author proposed an algorithm for transforming cognitive models into a knowledge base of a product expert system, taking into account the peculiarities of cognitive models and improving the method and tool used for cognitive modeling.
56 Alexander Shukhman,
Irina Bolodurina,
Petr Polezhaev,
Yury Ushakov etc.
Ant colony optimization algorithm for building virtual machine images in cloud systems The paper describes the development of an efficient algorithm for building virtual machine images in a cloud educational resource datacenter providing remote shared access for educational institutions to software. In this paper the problem of time optimization for building VM images with limited server disk capacity is formalized. This problem is reduced to the Steiner problem for directed graphs. We have developed the efficient algorithm for building VM images based on ant colony optimization.
57 Gaskova Daria,
Massel Aleksei
Intelligent system for risk of cybersecurity violations identification in energy facility The article describes risk-based approach using for analysis threats and risk assessment of cybersecurity violations in energy facilities. Risk-based approach considers harm by damage or destruction of object using quantitative and qualitative parameters based on probability of damage or destruction of object leading to cascading failure. The proposed approach can be implemented to development system information-analytical system used for monitoring of cybersecurity violations in energy sector.
58 Nikolay Kamenov,
Nina Krapukhina
A method for predicting vehicles movement based on road scene reconstruction in real time The proposed method allows predicting vehicles movement in order to increase the reaction time of the driver and prevent collisions on the roads. The algorithm dynamically reconstructs the road scene around the vehicle in consideration based on information from the on-board video camera. A dynamic model traces and places all detected moving objects on a two-dimensional virtual map. After analyzing the movement of each object, the algorithm predicts their possible behavior.
59 Oleg S. Amosov,
Yuriy S. Ivanov,
Sergey V. Zhiganov
Semantic video segmentation with using ensemble of particular classifiers and a deep neural network for systems of detecting abnormal situations A new approach based on the use of a deep neural network and an ensemble of particular classifiers is proposed. This approach is based on use of the novel block of fuzzy generalization for combines classes of objects into semantic groups, each of which corresponds to one or more particular classifiers. As result of processing, the sequence of frames is converted into the annotation of the event occurring in the video for a certain time interval.
60 Andrew Lewis,
Muhammad Newton,
Jan Hettenhausen,
Abdul Sattar
Constraint Guided Interactive Multi-objective Optimisation Kangaroo is a constraint-based local search system, that uses stochastic local search to find solutions for constrained optimisation problems. It allows declarative problem description and specification of search algorithms. This paper describes the integration of a novel, web-based interactive optimisation interface. This displays evolving solutions, and guides the optimisation process using dynamic constraints, supporting more effective and efficient exploration of challenging search spaces.
61 Chernysheva Tatiana,
Zakharova Alexandra,
Telipenko Elena,
Molnina Elene etc.
DSS choice of rational QUANTITY nanostructured powder-modifier for welding stainless steels The possibilities of using nanomaterials and nanocoatings for machine building are considered. The review of software for the engineering calculations of welding processes and heat treatment is reviewed. A decision support system for choosing a rational amount of nanostructured modifier powders for welding corrosion-resistant steels is proposed.
62 Olga A. Nikolaychuk,
Alexandr I. Pavlov,
Alexandr B. Stolbov
Web-oriented software system for agent-based modeling driven by declarative specification of implementation process The article discusses information models for describing the typical elements and software tools used for development of agent-based simulation models, including the inference and the simulation engine. Step-by-step specification formation method of the agent model driven by the domain ontology is proposed. A web-oriented software system was developed to approbate the method. It is provided implementation of that specification based on an extensible toolkit, for example Jess and Madkit
63 Vasilii Galperov,
Ludmila Massel
Development of multi-agent systems using Joiner-Networks: The proposed approach and its application in the energy sector On the one hand, one of the important aspects of the Smart Grid conception is the usability of the multi-agent technologies,on the other we have only few numbers of practical approaches to the multi-agent system realization in the energy sector.
64 Andey Gavrilov,
Alexandr Maliavko,
Alexandr Yakimenko
Key-Threshold based Spiking Neural Network In paper a novel model of Key-Threshold based Spiking Neural Network is proposed. This neural network consists of quasi-neurons oriented to recognize a key - spikes distributed in time (sequence of spikes) or in space (in synapses). Every neuron aims to recognize key (template of spikes) stored in its memory and to react by output spike at succesfully detection. Software implementation of this model is suggested. Possible methods of learning, implementation and usage of this model are discussed.
65 Dmitry Rizvanov,
Nafissa Yussupova
About the Development of a Software Prototype for Information Support of Decision-Making in Resource Management in Complex Systems Information support for decision-making in complex systems operating under uncertainty and resource constraints is designed to improve the efficiency of management activities and the quality of decisions made. The developed software prototype for information support of decision making in resource management is based on application of intelligent technologies and multi-agent approach. The results of suggested approach application in different subject domains are given.
66 Alexandra Zakharova,
Olga Kolegova,
Elena Telipenko,
Tatiana Chernysheva etc.
The model of estimating the strategic development of a company on the base of expert knowledge The paper considers the problem of expert knowledge formalization under the integrated assessment of the enterprise development strategy implementation. The authors suggest an integrated model, which allows obtaining a generalized estimator of the measure of company's achievement of the established strategic benchmarks. An example of the practical application of this model is given on the example of one of the state passenger transport enterprises.
67 Igor Bychkov,
Artem Davydov,
Nadezhda Nagul,
Sergey Ul'yanov
Hybrid Control Approach to Multi-AUV System in a Surveillance Mission Surveillance missions for multiple autonomous underwater vehicle (AUV) system suggest the use of different modes of operation including organizing and keeping a predefined formation, avoiding obstacles, reaching static and tracking dynamic targets. While exploiting a leader-follower strategy to formation control and the vector Lyapunov function method to controller design, we use discrete-event approach and supervisory control theory to switch between operational modes.
68 Evgeny Pustovoy,
Olesya Pystovaya
Management of neural networks Management of neural networks using the spatial matrix of coefficients
69 Evgeni Trifonov Exact PDE Solutions via Symbolic Calculations Algorithms for searching exact PDE solutions are provided. Their realisation using computer algebra systems is discussed.
70 Anatolii Shoberg,
Kirill Shoberg
Variants of block frequency transform for image retrieval An accelerated growth of digital media collections has established the need for development of tools for efficient access and retrieval of visual information. The paper presents different variants of block frequency transform to form an array of features for a quick search. Our approach is to perform block frequency transform with elements of invariance for certain rotation angles. The execution time does not increase. The proposed algorithms can be successfully used in computer vision.
71 Anastasia Mochalova,
Mochalov Vladimir
Evaluation of the similarity coefficient of the ontosemantic graphs and its application for the problem of question-answering search The paper proposes an algorithm for the operation of the natural language question answering system based on construction of supposed answers and comparison of the corresponding ontosemantic graphs with the ontosemantic graphs constructed on the interrogative sentence that is submitted to the system input. An algorithm for calculating the similarity coefficient of ontosemantic graphs is proposed. Examples illustrating the operation of the described algorithms are given through the paper.
72 Alina Kim,
Olga Lukovenkova,
Yuriy Marapulets,
Alexandr Tristanov
Sparse approximation methods and their parallel implementation The article is devoted to a new approach in the analysis of geoacoustic pulses. The authors proposed a mathematical model based on a sparse representation of the signal. An adaptive matching pursuit method has been developed to identify model parameters. A parallel implementation of this algorithm is proposed on the CUDA platform. This allows real-time processing and modeling of signals.
73 Pavel Nikolaev Adaptive intelligent environment based on neural networks This paper describes the concept of adaptive system of intelligent environment for smart homes and intelligent buildings. This intelligent system is based on artificial neural networks. Artificial neural network is one of the methods of artificial intelligence and machine learning. A key feature of the proposed system is the recognition of human behavior. Depending on this, the intelligent system can select and activate the most optimal operating modes of the environment.
Gennady Kalach,
Aleksandr Morozov
Computation of noise characteristics of the Low-cost MEMS IMU based on Node.js technology. I'm creating the web-application based on Node.js which will evaluate the noise components of the sensor.
75 Roman Alekhin,
Pavel Varshavsky,
Alexander Eremeev,
Anton Kozhevnikov
APPLICATION OF THE CASE-BASED REASONING APPROACH FOR IDENTIFICATION OF ACOUSTIC-EMISSION CONTROL SIGNALS OF COMPLEX TECHNICAL OBJECTS The work is devoted to the problem of developing a case-based reasoning module, capable of performing identification and filtration of data, obtained during acoustic emission control of complex technical objects. The application of case-based reasoning approach for identifying and filtering noise (non-standard, distorted) signals is considered. The parametric case representation is proposed to solve this problem.
76 Kseniya Korshunova A Convolutional Fuzzy Neural Network for image classification A model of Convolutional Fuzzy Neural Network for classification of real world objects and scenes in images is proposed. The Convolutional Fuzzy Neural Network consists of convolutional, pooling and fully-connected layers and a Fuzzy Self Organization Layer. The model combines the power of convolutional neural networks and fuzzy logic and is capable of handling uncertainty and impreciseness in the input pattern representation.
77 Ivan Bagaev,
Ilya Kanishchev
Probabilistic modeling of heavy-tailed distributions Modern probabilistic programming allows to solve different tasks through Bayesian Inference. One of this tasks is approximation of parameters of probability distributions. In this article we explain our approach for estimation difference of two sample groups distributions each of them is heavy-tailed. This task is common for marketing research, for example, A/B testing. We use PyMC3, Python probabilistic programming framework.
Synthesis of a filter that forms a random process of irregular sea waves The report examines the features of the well-known sea-wave excitation spectrum. The limitations of approximations of this spectrum were shown. These limitations allow to simulate irregular sea waves in the time domain. The approximation, which is devoid of these shortcomings is suggested.
79 Boris Paluch,
Valery Kemaykin
Development principles of knowledge database of intelligent system for estimation of dynamical interaction of orbital systems with space debris In the paper, a principles underlying the construction of an intelligent information system estimated results of the dynamic interaction of orbital systems with space debris is presented. It describes the knowledge database model based on these principles which is the synthesis of theoretical and practical information in the field of estimating the high-speed interaction of objects.
80 Larisa Rybak,
Sergey Khalapyan,
Elena Gaponenko,
Anton Glushchenko
Intelligent computing based on neural network model in problems of kinematics and control of parallel robot The article considers the problem of control of a parallel robot and determining the position of the output link when moving the drive links. As in the control process information is available on the previous position of the output link, can be defined some neighborhood in which to search for the current position. It is shown that the supply of such information to the input of a neural network model, which solves a problem of kinematics, allows substantially increasing its adequacy.
81 Sergey Bobkov Microprocessors KOMDIV for high-performance embedded systems The problems of creating of high-performance embedded computing systems based on microprocessors KOMDIV is considered. Processor performance is dependent upon three characteristics: clock cycle, clock cycles per instruction, and instruction count. These characteristics for microprocessors KOMDIV are optimized using parameter performance/power consumption and requirements of embedded systems.
82 Maxim Denisenkov,
Vadim Borisov
Modeling the behavior of intelligent agents based on adaptive fuzzy situational networks The paper represents adaptive fuzzy situational networks and their features for formalized description and modeling of behavior and interaction of intelligent agents in multi-agent systems. Simulating method of individual and collective behavior of intelligent agents are proposed (for the following types of interactions: conflict, competition, coalition, autonomy.
83 Elizarov Alexander,
Kirillovich Alexander,
Lipachev Evgeny,
Olga Nevzorova
Semantic search in Digital Mathematical Library This paper presents semantic search methods for mathematical scholar papers. We discuss semantic search methods for mathematical formulas and also methods, based on the logical structure of mathematical documents. New mathematical search methods have been developed and tested on Lobachevskii DML.
84 Mikhail Khachumov,
Vyacheslav Khachumov
The problem of target capturing by a group of unmanned flight vehicles under wind disturbances We consider the game-theoretic pursuit-evasion problem, where a group of pursuers is required to capture a moving target under wind loads. As participants of the game, we assume the unmanned flight vehicles, which mathematical models are determined by transfer functions. Behavioral strategies of all participants of the antagonistic game for a case when the speed of the evader is higher than the speed of the pursuers are suggested. Situations with different outcomes are modelled.
85 Boris Palukh,
Alexander Vetrov
Diagnostics and state analysis of multiple-stage production in terms of evolution management The scheme of effective management of multiple-stage production evolution based on adaptive processes is regarded. Model of process management architecture is described as multi-agent system where agents interact with each other and with center. It is proposed here to set a task on identification of current problems related to improvement of agents performance and of production system in general.
86 Sergey Sai Method protecting of transmission digital images from modifications In this paper, we propose an original method of protect digital images from modifications. The method is based on the algorithm of segmentation fine details in normalized colorimetric CIELAB system and calculating their level (FDL). To check the authenticity of the image is enough to compare the FDL values of the original and received images. Gives examples of image authentication results after modifications.
87 Aleksei Massel Intelligent computing for justification and strategic decisions support in Russia energy sector The application of intelligent computing for justification and strategic decisions support in Russia energy sector is considered in this article. First of all, it includes the use of ontological, cognitive, event and probabilistic modeling. The main tools to support intelligent computing are Intelligent IT- environment and Situation Polygon. Proposed approach provides integration of intelligent computing tools and support of two-level technology of Russia energy security research.
88 Elena Telipenko,
Alexandra Zakharova,
Tatyana Chernysheva,
Svetlana Sopova
Software for bankruptcy risk assessment of the enterprise The article presents the results of developing an intellectual information system for assessing the risk of bankruptcy of an enterprise based on the synthesis of fuzzy logic and neural network technologies. The composition and structure of the information system, as well as the features of working with the program are presented. The system allows for a current assessment of the risk of bankruptcy and provides an opportunity to see how it changes when one or more indicators change their value.
89 Albert Ashrafzianov,
Mikhail Shleymovich
Vehicles detection on images in on-board systems This paper describes the problem of detecting a vehicle on the image in real time. Images are obtained with the moving image sensor mounted inside a moving car. A class of existing methods of detecting objects of interest are described, we also give a their characteristic in relation to this problem. To detect objects of interest we consider the approaches based on key point of wavelet transform, the modified method of Viola-Jones, optical flow. Computation experiments are presented.
90 Molnina Elena,
Zakharova Alexandra,
Chernysheva Tatiana,
Telipenko Elena etc.
Information support of a complex system to form IT competences The integrated system of development of information and communication competences of students trained. The necessity to involve the Institute into the process of development of information and communication competences of prospective students is reasoned. The algorithms of information system and the structure of the Portal «Computer-assisted IT-University» are worked out to develop graded competences.
91 Roman Fedorov,
Igor Bychkov,
Gennadiy Ruzhnikov,
Yuri Avramenko
Object identification on raster images by user query Currently, most software systems designed to identify objects on raster images are focused on identifying a rigid class of objects. Often for real-world tasks, the capabilities of software systems are not enough. One of the ways to solve the problem is to perform identification in accordance with the user query. The development and implementation of the method for identifying objects on raster images based on the user's knowledge is proposed.
92 Alexandr Osipov,
Veronika Trushina
METHOD FOR MODELING THE ADIABATIC BURNING TEMPERATURE OF CHEMICAL SUBSTANCES USING DESCRIPTORS OF GRAPHS OF STRUCTURAL FORMULAS A mathematical method for modeling the adiabatic burning temperature depending on the molecular fuel structure is considered. The method was tested on experimental data in comparison with other methods
93 Vladimir Kuzmin,
Liudmila Massel
Situation calculus application in tasks of intelligent decision-making support The basic concepts of situational calculus are considered. The architecture of the intelligent decision support system (Situation polygon) for strategy development in the energy sector is presented. It is based on the use of situational management concept and semantic modeling. The possibility of applying situational calculus is illustrated on the example one of the main components of the Situation Polygon - Contingency management language (CML).
94 Alexander Bahrushin,
Galina Bahrushina,
Ruslan Bazhenov
Robust blind image watermarking based on a new modulation mode of low frequency DCT coefficientst blind image watermarking based on a new modulation mode of low frequency DCT coefficients Abstract—A blind watermarking scheme based on DCT is presented in this report. To promote robustness of the scheme to different attacks while maintaining high visual quality of image it was proposed to use a new modulation mode of low frequency DCT coefficients. This mode allows to embed every bit of watermark only to one DCT coefficient. Simulation results show that the scheme is highly robust against different attacks and especially against JPEG compression even at low quality factors.
95 Andrey Klimenko,
Igor Nadezhdin,
Flavio Manenti,
Alexey Goryunov
Dynamic Hybrid Simulation of Uranyl Nitrate Crystallization Process The paper addresses the dynamic modeling of the uranyl nitrate crystallization process by means of a hybrid technique. The paper is the subject of the present state of the art in the renewal of the nuclear fuel. А novel mathematical model of the uranyl nitrate crystallization process is proposed describing the heat and mass transfer phenomena. Sensitivity analyses are provided for the prediction of the main outlet parameters of the crystallization process.
96 Konstantin Aksyonov,
Anna Antonova
Analysis of the Electric Arc Furnace Workshop Logistic Processes Using Multi-Agent Simulation The article presents analysis of the logistic processes using simulation. The aim is to find the best values of the shop output characteristics depending on the method of grouping the melts. Agents in the model are used to implement the logic to process the orders for production, determine the orders route, and adjust the experiment. The following recommendations have been found. It is necessary to group the melts in groups with 40 melts with identical routes before feeding into the shop.
97 Dinar Miftakhutdinov,
Ildus Rizaev,
Michael Shleymovich
METHOD OF AUTOMATIC DETECTION OF NEW MOTIONLESS OBJECTS ON THE BASIS OF COMPARISON OF IMAGES OF THE AREA The basic principles of an algorithm of Detection of objects in the onboard systems of unmanned aerial vehicles using information about changes in the image of the terrain is considered in the paper. The possibility of obtaining additional information about the objects determines the prospects of the technology for allocating changes for use in high-resolution aviation surveillance systems.
98 Yuri Vasin Models, methods, algorithms and IT-technologies for processing of spatially distributed data in GIS The paper presents the author's mathematical description models, methods, algorithms and intellectual GIS technologies for processing, analysis and recognition of Earth remote sensing data, thematic information and hyperspectral data. We discuss the organization of storage of spatially distributed data in the environment of the GIS for different hardware and software platforms (Windows and Android) in the local and client-server variants.
99 Elza Takhavova,
Galina Kostjukhina
Neural Networks for the Moving Objects Control The article deals with methods for training the neural network model developed to control a robot moving. The developed software for neural network training is described. Results of comparative analysis the back propagation method and genetic algorithm method used to train the neural network are described.
100 Nina Kazachek,
Vasiliy Berdnikov,
Valeriy Lokhin
Increasing the Reserves of Automatic Control System Stability by Using of Fuzzy Controllers The paper discusses the problem of increasing the reserves of automatic control system stability by using fuzzy controllers. The exact stability regions have been developed on the plane of the plant parameters, by using the methods of numerical integration of the control systems equations. Their dependence from the parameters of the fuzzy controller is shown. The approaches to fuzzy controller synthesis, that guarantee the required quality, are proposed.
101 Maria Mikheyenkova,
Victor Finn
Cognitive sociology from the knowledge discovery point of view The means of cognitive heuristics formalization that realize the inductive strategies of empirical sociological research are presented in the work. The generation of hypotheses on behavior determinants, empirical regularities detection in expanding empirical data and studying the social individuals' cognitive effects are considered to be the knowledge discovery in cognitive sociology. The JSM Method of automated support of scientific research is proved to be the knowledge discovery instrument.
102 Mikhail Medvedev,
Mikhail Shleymovich,
Stella Lyasheva
Image analysis based on salient points of wavelet transform In the article the task of image analysis based on salient points of wavelet transform is considered. Salient points retrieval based on energy estimation of wavelet transform is described. Salient points description based on local binary patterns are proposed.
103 Vadim Uvarov,
Alexander Popov,
Tatyana Gultyaeva
Classifying incomplete sequences using derivatives of likelihood function with respect to HMM parameters This paper deals with the problem of classifying incomplete multidimensional sequences using hidden Markov models (HMMs). We propose a modification to the formulas for calculating first derivatives of likelihood function with respect to HMM parameters which extends them to the case of incomplete sequences. We study how classification of sequences in space of the first-derivatives using support vector machines helps to fight the data loss occurred at the HMM training stage.
104 Michael ZABEZHAILO,
Victor FINN
Intelligent Data Analysis and Machine Learning: are they really equivalent concepts? Modern Artificial Intelligence (AI) technologies are discussed. Intelligent Data Analysis (IDA - data analysis by reasoning systems) is in focus. We compare effectiveness of classical Machine Learning (ML) and IDA in knowledge discovery problems (extraction of stable empirical dependencies from open collections of experimental data). We'll demonstrate (by examples of applications of JSM-method of automated support for scientific research) that IDA is more general concept than classical ML.
105 Dmitry Kugaevsky Optimization of road network capacity This article discusses the problem of increasing the throughput of the urban network via simulation modeling
106 Vitaly Fralenko,
Maria Shustova,
Mikhail Khachumov,
Vyacheslav Khachumov
Isolation and tracking of transplanted mesenchymal stem cells on MRI images The problems of automatic isolation and tracking of mesenchymal stem cells transplanted into the brain of experimental animals are considered. The experiments were performed on a series of images of the observed MRI cut. The task of tracking is solved by constructing shells for the sets of stem cells allocated to the sequence of images. Trajectories connecting the corresponding central points of shells are carried out using special parametric Bézier curves.
107 Alexander Emelyanov,
Maxim Dli
The decision-making in real-time of airport services based on simulation modeling and fuzzy logic Decision making by the aircrafts services of the international airport, which provides for intensive traffic of aircraft and their ground handling, becomes a very topical issue. A large accumulation of aircraft on the platform-field creates equally complex difficulties in comparison with aircraft take-offs and landings. Solving such problems with the use of queuing theory gives little. This article deals with complex ''fuzzy methods'' based on simulation modeling and and fuzzy algorithms.
108 Aleksandr Panov,
Gleb Kiselev
Planning and goalsetting in sign based world model Planning and goalsetting in sign based world model
109 Evgeny Kuleshov,
Konstantin Petrov,
Tatiana Kirillova
Testing a statistical hypothesis of the probability distribution function of a random signal A goodness-of-fit test of empirical and hypothetical distribution functions constructed as a sequence of bilateral tests. It is shown that the central element of the sequence is the unbiased locally most powerful test. A probability distribution free algorithm for computing the significance level is presented. The quality of the new goodness-of-fit test was evaluated with a numerical simulation.
110 Evgeniy Shelenok,
Eugenie Eremin
Research of Operating Modes of the Combined Control System for Manipulator with Input Constraints Article deals with the problem of research the different operating modes of the decentralized control system for two degrees of freedom robotic manipulator which have an input saturations. With help of numerical experiments, a sufficiently high quality of the control system operation under various periodic modes of the manipulator operation is illustrated.
111 Evgeniy Shelenok,
Eugenie Eremin
Synthesis of the Decentralized Control System for Robot-Manipulator With Input Saturations It is discussed the problem of synthesis of the decentralized adaptive-periodic control system for two degrees of freedom robotic manipulator which have an input limitations. The solution of the problem is based on the use of hyperstability criterion, L-dissipativity conditions and dynamic filter-corrector.
112 Daria Chernomorets,
Vladimir Mikhelev,
Andrey Chernomorets
Multiscale approach of retinal blood vessels segmentation based on vessels segmentation with different scales In this work, we developed retinal blood vessels segmentation approach using contrast limited adaptive histogram equalization, morphological filtering, k-means clustering, matched filtering for thin and thick vessels selection. We also applied matched filtering for thin vessels selection using the kernels which were built in order to determine the existence of line segments with different length and orientation. Our approach has shown promising results.
113 Andrey Parasich,
Igor Kaftannikov,
Victor Parasich,
Irina Parasich
Predicting sales prices of the houses using regression methods of machine learning In this article we will describe our solution for ''House Prices: Advanced Regression Techniques'' machine learning competition, which was held on Kaggle platform. The competitor's goal was to predict house's sale price by their attributes like house area, year of building, etc. In our solution, we use classic machine learning algorithms, and our original methods, which will be described here. At the end of the competition, we took 18th place among 2124 participants from whole world (top 1%).
114 Anna Mikheeva Studying the global geotectonic structures of the South-Eastern Asia by means of the GIS-ENDDB Various endogenous (occurring in the bowels of the Earth) and exogenous (for example, impact effects) geological processes characterize the modern geodynamic situation. To solve problems focused on the investigation of cause-effect relationships of processes influencing regional geodynamics, the GIS-ENDDB (Earth's Natural Disasters Database) is developed. The new global geodynamics structures was found by means of the tools and methods of this GIS.
115 Yury Brodsky Model Synthesis and Model-oriented Programming:A new technology for high performance agent-based modeling A new approach proposed to the description, design and implementation for computer simulations of complex multi-component systems, – the model synthesis and model-oriented programming. The central concept of this approach is the concept of the model-component. The models-components family is closed under uniting components into the complex, and the simulation computations organization is an invariant for any member of the family. This fact allows solving the synthesis problem for a simulation model of any complexity. A special declarative language LCCD (language of components and complexes descriptions) proposed for describing the models-components and building models-complexes from them. The model-oriented programming system proposed is focused on parallel and distributed computing.
116 Sergey Sheptunov,
Anna Pogodina
Mechatronics in biology Application of mechatronics in biology and human reproduction
117 Sergey Sheptunov,
Anatoly Evstrapov
Micro- and nanotechology application at devices of molecular diagnostics for medical and biological research The current state and prospects for the use of microfluidic devices in the detection of nucleic acids at biological and medical research are discussed in the article. The main trends in the development of analytical instruments base a microfluidic platform are indicated. The most usually used technologies for the formation of micro- and nanoscale functional structures in microfluidic devices are noted. Popular materials used for the mass production of devices are highlighted.
118 Sergey Sheptunov,
Eduard Kim
Surgical aspects of the need for mechatronics in medicine Consideration of basic surgical aspects, required application of mechatronic technologies
119 Sergey Sheptunov,
Eduard Kim
Mechatronics in liver surgery Application of mechatronic devices and engineering technologies in surgery of the liver and other organs
120 Sergey Sheptunov,
Irina Avdunina
mechatronic technologies for rehabilitation and resuscitation Application of mechatronic technologies in the process of rehabilitation and resuscitation, for stabilization of incurable patients
121 Sergey Sheptunov,
Mikhail Kulikov,
Vitaly Inozemtsev,
Mikhail Krukovich
The conception of surface quality formation for metal detail's shaping through layered growing The article describes the feasibility to use an anodic machining for improving the surface quality of parts are produced by direct laser sintering from metal powders.
122 Sergey Sheptunov,
Dmitry Pushkar,
Konstantin Kolontarev
Significance of the -2proPSA index and the prostate health index in patients with prostate cancer: a literature review and data of the Russian prospective study The current literature review provides an analysis of fundamental studies on the -2proPSA index and prostate health index PHI and determination of their role in patients with prostate cancer.
123 Alexander Eremeev,
Sergey Ivliev,
Vladimir Vagin
Using NoSQL databases and machine learning for realization intellegent decision system for complex vision patalogies One of the most important fileds of decision system development is processing medical data for helping experts to make desicion in case of complex pathologies. In generally, system for storing data and decision module is main parts of these systems, what's why is very important to create systems, which can handle medical and expert information, which can be presented in various types and forms. One of the decision in this case it's combining methods of machine learning and NoSQL databases.
124 Olga Kupriyanova,
En Un Chye
Development and research of models of data transmission systems with adaptation to communication channel status and implementation of ''deferred precision'' principle This work studies one of the methods of adapting data transmission. The basis for the suggested adaptive system is status assessment of the data transmission channel, according to which selection is done of transmitted data width and parameters of error correcting code. The simulation modeling results show the accuracy of the suggested solution and allow assess the main parameters of the data transmission systems with such adaptive method.
125 Dmitry Pashchenko,
Dmitriy Artamonov,
Dmitriy Trokoz
Recursively controlled automata Abstract machines are widely used for creating models of control systems, solving verification tasks, designing of the grammatical recognizers. Deterministic finite automata are the special class representing the abstract machines with a finite number of states.
126 Konstantin Yakovlev,
Bokovoy Andrey
An Empirical Evaluation of Grid-based Path Planning Algorithms on Widely Used in Robotics Raspberry Pi Platform We compare three widely used grid-based path planning algorithms in terms of runtime performance on a desktop personal computer and on the Raspberry Pi 2 embedded computer widely used in modern robotics. Two principal questions are targeted: first) to what extent modern embedded computers are slower than conventional desktops when solving path finding problems on grids; second) how well the former scale up to larger problems.
127 Илья Владимирович,
Алексей Викторович,
Ольга Викторовна
Adaptive Compression of Telemetry Data This paper proposes a method for compressing the telemetry data that implements adaptation by the compression algorithm. It is offered five performance criteria that can be applied to select approximately optimal compression algorithm. It is shown that the application of the proposed criteria allows, with a sufficiently high level of reliability, to select the most effective compression algorithm for a known statistical data type with relatively low computational costs.
128 Georgy Burdo Principles of Creating Hybrid Integrated Automated Systems of Technological Process Design and Control Relevance of information integration of automated systems of technological process design and control in multiproduct manufacture is shown. The research is conducted on the basis of system theory framework and product life cycle methodology. The hierarchy of the systems examined is shown. The principles of creating integrated systems and their subsystems are grounded. The technique of decision making in hybrid systems is suggested.
129 Roman Solodukha,
Igor Atlasov
Modification of RS-steganalysis to Attacks Based on Known Stego-program The modification of RS-steganalysis for BMP stego-images is offered. It is based on applying the method to a various size group of pixels. The traces of LSB embedding called trasological statistics of stego-program are accumulated. The modification gives more accurate results at based on the known program steganalytic attack.
130 Nicolay Kosykh,
Sergey Savin
Expert System for Computer-aided Medical Image Analysis Method of computer-aided analysis of planar osteoscintigramms studied the skeleton of patients with metastases to the skeleton. There is a direct relationship between the levels of accumulation of the radiopharmaceutical in areas of the skeleton without metastatic lesion and bone metastases occurring in these zones. Consider methodological approaches to expert system building for the analysis skeleton planar scintigramms, as well as results of conducting calculations.
131 Gennady Bronfeld Methodological analysis of the notions «information» and «knowledge» on the basis of the modern structural ideas Analyzes changes in the understanding of the notions of "information" and "knowledge" from the the standpoint of the development of science and theory of cognition on the basis of the changes of the perspectives on the structure of information and knowledge. The new four-level structure of knowledge permits to, mathematically imagine in a new way the components of knowledge and newly reconsider the problematics of knowledge and information.
132 Alexander Fridman,
Boris Kulik
Logic-Probabilistic Analysis of Information with Uncertainties Besides using logic-probabilistic analysis for probabilistic estimation itself, it is often necessary to consider uncertain or underdetermined information of a different nature expressed in the following forms: interval estimates, lists of possible options, hypothetical or possibilistic statements, etc. This article discusses methods of logic and logic-probabilistic analysis of uncertain data and knowledge by means of n-tuple algebra the authors have developed earlier.
133 Sergey Chernyshev Algorithm of restore shape of the object from the reflected UWB signal Algorithm of reconstructing the shape of the object from the reflected UWB signal based on the mentioned reflections developed. This algorithm uses a discrete model of the object and allows to determine the wave reflection coefficients of local inhomogeneities which completely determine the shape of the object.
134 Victor Kasyanov,
Timur Zolotuhin
A System for Visualization of Big Attributed Hierarchical Graphs Information visualization is a process of transformation of large and complex abstract forms of information into visual form, strengthening cognitive abilities of users and allowing them to take the most optimal decisions. A graph is an abstract structure that is widely used to model complex information for its visualization. In the paper, we consider a system aimed at supporting of visualization of big amounts of complex information on the base of attributed hierarchical graphs.
135 Gennady Vinogradov,
Nadezhda Kirsanova
Modeling of subjective choice in an uncertain and poorly structured environment The paper considers a relevant problem of creating a strategy (model)of economic and social system development, which uses its members' information interaction mechanisms.
136 Valeria Gribova,
Margaret Petryaeva,
Dmitry Okun,
Alexey Tarasov,
George Ostrovsky,
Dmitry Krasnov
Software toolkit for creating intelligent systems in practical and educational medicine The article considers a specialized cloud toolkit for development of medical expert systems and computer simulators. A special feature of the toolkit is usage of specialized ontologies for formation of knowledge bases and databases for diagnosis and treatment of diseases that do not depend on the area of medicine, and which can be reused for different types of intelligent systems (expert systems and simulators).