Marina Savelyeva
Southern Federal University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Marina Savelyeva.
Intelligence Systems in Environmental Management | 2017
Alexander V. Bozhenyuk; Stanislav L. Belyakov; Evgeniya Gerasimenko; Marina Savelyeva
In this chapter questions of defining of service centers optimum allocation in transportation network are observed. It is supposed that transportation network is described by a fuzzy graph. In this case a task of definition of optimum allocation of the service centers can be transformed into the task of definition of base fuzzy set, antibase fuzzy set and vitality fuzzy set of fuzzy graph. The method of definition of these sets is considered in this chapter. The numerical example of optimum allocation of the service centers finding in the railway network in the form of the fuzzy graph is considered.
advanced industrial conference on telecommunications | 2016
Stanislav L. Belyakov; Igor Rozenberg; Marina Savelyeva; Marina Belyakova
The paper proposes a method of constructing solutions based on the experience represented by cartographic images — centers and transformations of situations that do not change their meaning. The method is based on the metatransformation of images. The goal of metatransformation is to construct new situations by known precedents. The usage of metatransformations allows to evaluate the semantic proximity of situations and adapt the earlier decisions in a special way. The factors that determine the reliability of the generated solutions are analyzed.
IEEE Conf. on Intelligent Systems (2) | 2015
Marina Savelyeva; Stanislav L. Belyakov
The article presents the problem of supply chain management. One of the main issues in solving such problems is routing. An algorithm to find the shortest path in the temporal dependence and fuzzy-defined parameters of time and distance. Solution is based on the apparatus of graph theory, namely fuzzy temporal graph. This algorithm is a modification of Dijkstra’s algorithm. An illustration of an example of solving the problem of finding an optimal route in fuzzy conditions, as such representation is closest to reality.
international conference on industrial informatics | 2014
Stanislav L. Belyakov; Marina Savelyeva; Jeffrey Yan; Valeriy Vyatkin
This paper presents the ways of constructing routing algorithms in mechanical transport systems based on knowledge. It is assumed that the experts observing system behavior applies his experience by designating subsystems with a specific behavior. To create routing tables, a model of fuzzy temporal hypergraph was used. We consider fixed and dynamic routing, given modifications of Dijkstras algorithm for the case of fuzzy temporal hypergraphs.
computer science on-line conference | 2018
Stanislav L. Belyakov; Marina Savelyeva
This paper presents the problem of controlling the transportation of cargo in the mechanical transport system. The overall efficiency of the system includes the costs of reconfiguration, involving both software and manual changes in the parameters and relationships of equipment components. The decision-making phase about choosing the reconfiguration method is preceded by the analysis of the utility of possible methods. The complexity of the solution of the considered problem consists in the ambiguous estimation of the network state due to the considerable number of parameters and incompleteness of information about their values. Except the status, the reconfiguration effect depends on the dynamics of the input flows and the effect of the external environment on the network after reconfiguration. The way of the solution of the problem, based on the image representation of the reconfiguration experience, is considered. The model of the image representation of knowledge and reasoning on their basis is described. The advantage of model of representation of precedents of reconfiguring by images is analyzed. The example of the image representation of situations reflecting the set of knowledge about the input flow, the degree of congestion of the subnet, and the forecast of the behavior of the reconfigured network is given. The boundaries of application of the proposed method are analyzed.
international symposium on intelligent systems and informatics | 2017
Stanislav L. Belyakov; Marina Savelyeva; Marina Belyakova; Sergey Zubkov
This paper investigates the problem of visual analysis of complex plans, schemes and maps for solving of difficult formalized tasks. It is analyzed the dependence of the level of perception upon the visualization complexity. It is introduced the concept of the utility of the visual image, it is described by the behavior of the empirical utility function. We propose an optimization model of the utility, which is based on picture representation by two components. The first component is a skeleton of workspace. The skeleton includes primitive attributes of map or scheme, which selected from a database corresponding to the users request. The second component is the skeleton environment intended for filling of the skeleton by information details. The environment primitive attributes increase the semantic level of visualization. Selection of the environment primitive attributes is provided by a set of expert rules. The set of rules is divided into classes corresponding to the professional user orientation. It is given the formal statement of the optimization problem of visualization utility. It describes the operation of picture manipulation. Examples are shown of practical applications of visualization for two classes of visual images.
european society for fuzzy logic and technology conference | 2017
Stanislav L. Belyakov; Marina Savelyeva; Dmitry Kiyashko; Anna Lashchenkova
The article deals with the problem of moving flows in mechanical transport systems suitable for prevention or greatly decreasing the probability of emergency situations. The solution is based on minimizing costs during transportation. Routing methods considering the specifics of the MTS are analyzed. It’s developed routing algorithm with protective correction of flows with fuzzy temporal variability of adaptation. The algorithm consists in definition and establishment of high value of transportation cost on the particular segment of network on a fuzzy time interval. Methods for determining the parameters of protective correction of flows are studied. A structural diagram of the MTS, considering the protective correction, is presented. The diagram is implemented by introduction an intelligent module into the structure. Module operation feature is the use of case-based reasoning. The example of the implementation of protective correction of flows is given.
computer science on-line conference | 2017
Stanislav L. Belyakov; Marina Savelyeva
In this paper, we will examine the problem of cost minimizing of the cargo moving in mechanical transport systems. Cost Index includes component, which reflects the loss on disaster recovery. We analyze ways to reduce the possibilities of accident initiation. We also consider the features of the adaptive routing. We define the conditions under which it can be used to manage by the intensity of the flow through separate network segments. We propose adaptive routing algorithm with protective correction of flow. The essence of the algorithm consists in installing high value of the cost of the transfer on separate segments. This value is fixed as a periodic event in the specified time window. We consider the factors that determine the value of protective correction of the parameters. We have identified the problem of finding the best values. We have proposed the mechanical transport system structure, which includes an intelligent module of instruction issue of protective correction. We consider the work principles of intelligent module based on case analysis with a hierarchical storage system of precedents.
Proceedings of the IV International research conference "Information technologies in Science, Management, Social sphere and Medicine"#N#(ITSMSSM 2017) | 2017
Stanislav L. Belyakov; Marina Savelyeva; Marina Belyakova; Sergey Zubkov
The paper is devoted to the development of a method of visualization management of the spatial data on electronic maps. It is assumed that spatial data are obtained from sources that didn’t allow to define fully and consistently all characteristics of objects or events. There are defects of display in the visual analysis of the maps containing cartographic objects with uncertainty. The method of visualization management is proposed, which allows to control the utility of visual representation of the map with defects. The special presentation of the analysis workspace is introduced, the structure of expert rules is described, allowing to realize the selection of information from the geographic information system database to reduce redundancy and ensure the integrity of the picture. The form of the utility function is defined. The restriction of perception is introduced, which is determined by the complexity of the analysis workspace. The complexity measure is the number of cartographic objects. The algorithm of visualization management is given. Keywords— visualization management, spatial data, uncertainty, electronic maps.
Intelligence Systems in Environmental Management | 2017
Alexander V. Bozhenyuk; Stanislav L. Belyakov; Evgeniya Gerasimenko; Marina Savelyeva
The following chapter deals with the problems of the sustainable transportation network from the geographic information systems for intelligent control. For this we developed the dynamic geoinformation model with temporal dependence of the parameters and the procedural model of routing with temporal dependence and fuzzy given distance and time. The tasks of routing problem with fuzzy conditions are described and solved.