+7 (495) 987 43 74
Join us -              
Рус   |   Eng


  

“Journal of Applied Informatics” is a peer-reviewed science journal with international representation of editorial board and authors, covering a significant part of Russian IT-area. The topics of the publications are connected to the aspects of theory and application of computer modeling and information technologies in various professional areas. The journal is indexed by Russian Science Citation Index on Web of Science platform.

More
In accordance with the decision of the Higher Attestation Commission of the Ministry of Education and Science of Russian Federation, journal is included in the «List of Leading Peer-Reviewed Scientific Journals and Publications authorized to publish main dissertation results»

Fuzzy case models for project management using a multi-ontology approach

The author: Chernovalova M.
The article identifies the features of innovative projects that should be taken into account when building models of information processes in decision support systems (DSS) for project management. It is shown that, in terms of taking into account these features, methods for forming knowledge in the form of ontologies and the use of information analysis procedures based on precedent methods seem to be promising. The limitations of existing precedent methods, including those involving the formation of a knowledge base in the form of ontologies for their use in project management, are revealed. Development trends in methods for representing knowledge in the form of ontologies and their use within the framework of precedent approaches are substantiated. The trends are as follows: providing the ability to use several independent ontologies for different subject areas; taking into account the differences of the analyzed projects and creating conditions for the adaptation of ontologies when the indicators of the external and internal environments of the project change. A DSS structure for project management is proposed, which provides the use of several subject and functional ontologies and a developed fuzzy logic algorithm for adapting earlier rational decisions to the current situation. Software tools implementing the proposed models and procedures are described, as well as the results of their application to decision support in managing a project to develop an innovative asynchronous electric motor. It is shown that the proposed approach allows the description of the current situation in a linguistic form. At the same time, in contrast to the known variants of precedent methods based on the use of ontological models, the described algorithm for deriving solutions allows taking into account the characteristics of the analyzed situations related to various subject and functional areas. This allows you to develop recommendations for the allocation of resources for the implementation of design work based on the analysis of positive experience in the implementation of projects of various sizes.

Models and methods of reinforcement learning in the structure of adaptive web-based information systems

The author: Shpolyanskaya I. Y.
Widespread use of web-based systems in business, marketing, e-learning, etc. makes it necessary to take into account and analyze the information needs of the user in order to optimize interaction with him. One of the main problems of creating adaptive web-based systems is the task of classifying information resources (pages) of the portal describing the offered product or service, for the subsequent formation of the user profile and personalized recommendations of services. Data mining and machine learning methods can be used to solve this problem. The article presents a new approach to creating adaptive web-based information systems using the reinforcement learning algorithms to classify information resources and to form personalized recommendations to users based on their preferences. An adaptive approach is proposed and justified, based on the use of Reinforcement Learning procedures, which allows you to automatically find the most effective strategies for the correct classification of the site's resources and the formation of user groups with the same type of requests and preferences. The proposed scheme allows you to create procedures for evaluating and ranking information resources of the system based on the analysis of user behavior on the site online. The reinforcement learning algorithms used make it possible to evaluate the relevance of each page of the site to the requests and preferences of the users from different categories in order to optimize the structure and content of the site, as well as to build an effective system of recommendations in accordance with the user's interests to be able to choose the most suitable products or services.

Preliminary assessment of the pragmatic value of information in the classifiсation problem based on deep neural networks

A method is proposed for preliminary assessment of the pragmatic value of information in the problem of classifying the state of an object based on deep recurrent networks of long short-term memory. The purpose of the study is to develop a method for predicting the state of a controlled object while minimizing the number of used prognostic parameters through a preliminary assessment of the pragmatic value of information. This is an especially urgent task under conditions of processing big data, characterized not only by significant volumes of incoming information, but also by information rate and multiformatness. The generation of big data is now happening in almost all areas of activity due to the widespread introduction of the Internet of Things in them. The method is implemented by a two-level scheme for processing input information. At the first level, a Random Forest machine learning algorithm is used, which has significantly fewer adjustable parameters than a recurrent neural network used at the second level for the final and more accurate classification of the state of the controlled object or process. The choice of Random Forest is due to its ability to assess the importance of variables in regression and classification problems. This is used in determining the pragmatic value of the input information at the first level of the data processing scheme. For this purpose, a parameter is selected that reflects the specified value in some sense, and based on the ranking of the input variables by the level of importance, they are selected to form training datasets for the recurrent network. The algorithm of the proposed data processing method with a preliminary assessment of the pragmatic value of information is implemented in a program in the MatLAB language, and it has shown its efficiency in an experiment on model data.

Tools for automated collection and analysis of sociological information on the territorial identity of city residents

The paper proposes an algorithm for automated search and initial analysis of sociological information aimed at studying the territorial identity of city area residents using Internet sources. Communities of social networks, e.g. VKontakte, are considered as the main data source, and websites of topographic objects found in the territories under study are used as auxiliary information sources. It is demonstrated that, in terms of information support, public pages and groups with open or restricted access walls have the greatest potential. The developed algorithm implies selecting relevant groups, finding content concerning area issues, and determining the indices of community activity in discussing territorial problems. The required information is retrieved through the interaction with a social network server with the use of the official Application Programming Interface (API). To identify communities and posts, it is proposed to apply methods of morphological analysis of textual information. The software implementation of the algorithm is described in Python 3.8.5, including original functions for the acquisition of data on communities by their identification numbers, for the formation of a set of urbanonyms for a specified area, and some other ones. The developed program has been used to analyze territorial groups in three areas of Moscow; the results of the analysis enable us to estimate the degree of the territorial identity of their residents. The analysis of the error in the results of automated data collection and processing shows good agreement of these results with manually obtained ones, i.e. the error is 2.6% in the identification of relevant groups and about 3% in the identification of posts on area issues. Therewith, a much higher speed of response and lower labor effort required to perform routine operations allow the algorithm and the implementing computer program to be viewed as an effective tool for sociological research based on data from social networks.

Tools of organizational change management using swarm intelligence methods

In the context of the coronavirus pandemic, the importance of disposable tableware and packaging for food has sharply increased. On the one hand, this contributed to an increase in demand for such products, and on the other hand, it strengthened the already intense competition in this market. As a result, manufacturers of disposable tableware faced the vital challenge of finding ways to maintain and expand their customer base. Today, a promising way to solve it is the development and implementation of various product and technological innovations. However, the implementation of such projects is a rather complex process, since it includes not only the creation or modification of production technologies and manufactured products but organizational changes related to all business processes of the enterprise. Practice shows that the human factor plays a special role in carrying out such organizational changes, while the greatest threat to the project is not mistakes in planning and implementation of changes but the resistance of employees. One of the ways to prevent or reduce it is to create a dedicated change support team that is distinguished by its initiative. However, in practice, it is rather difficult to identify such employees who not only want to participate in the implementation of changes but have sufficient knowledge, skills, experience to carry them out. To solve this problem, it was suggested employee behavior modeling, aimed at optimizing the team composition based on a study of various characteristics. The artificial bee colony algorithm modified by the introduction of fuzzy elements (to set the initial search positions) was used for its practical implementation.

A method and a model framework for planning R&D changes in manufacturing enterprises

This paper presents a method and a model framework for R&D changes planning in manufacturing enterprises, implementing digital transformation projects. The relevance of development of such method is evident because of growing number of factors, influencing the decision-making process and simultaneously the complexity of such influence estimation increases. Classical changes planning methods in such cases do not ensure required level of estimation objectivity and credibility. The objects of research are industrial enterprises, actively engaged in research, design and engineering. The subject of research are methods and models for R&D process changes planning in context of digital transformation endeavors, being implemented in the companies. The research objective is to develop a R&D process planning method, enabling to account for corporate changes, related to digital transformation processes. The proposed method is based on the analysis of the discrepancies between the actual enterprise architecture and the target one and search for possible solution to rectify these discrepancies. For quantitative estimation of the changes, an integral indicator "stakeholder satisfaction level" is proposed. This indicator is calculated using a set of models (a model framework), those preparation and application sequence is defined by the considered method. The paper describes the concept of the method, the problems, being solved within each stage, tools used and final outcomes. The example of planning R&D changes in manufacturing enterprise illustrates the method in work and provides for better understanding of the concepts, presented in the paper.

Algorithmic and information support of innovative project management in conditions of uncertainty

The article presents the features of innovative projects of industrial enterprises that complicate the process of their management. The main groups of mathematical methods used to manage innovative projects are identified. The possible directions of further developing mathematical methods in the field of managing the complex innovative projects at industrial enterprises are determined. Algorithms of accounting the influence of uncertainty factors on the duration and costs that associate with implementing the innovation project works are presented. A distinctive feature of these algorithms is the usage of fuzzy production rules. These rules formulate recommendations for managing these projects based on the distribution of resources available in the organization depending on the results of each stage. It allows minimizing the execution time, both individual stages, and the entire innovation project as a whole. The variant of information support formation is offered that is presented in the form of a physical model of the database. This model allows storing all the information available in the industrial organization that necessary to manage these projects. A distinctive feature of this database is the ability to store information on the impact of uncertainties on the implementation effectiveness in a formalized form. This information is necessary for the implementing the developed algorithms.

Assessing the crypto resistance to the destructive effect of "viewing transmitted data" in the case of quantum computers

In this paper, we evaluate the crypto resistance of known cryptographic methods and methods based on the use of noise-like signals, similar in properties to "limited" white noise and used to spread spectrum of transmitted messages, to the destructive effect of "viewing transmitted data" (decipher), based on the search of code structures (brute force), in the case of quantum computers. It’s established that the required value of the number of code structures (key space), taking into account the constantly improving and developing computing power of quantum computers, for the next few years should be considered a value of 1032 of the number of code structures (key space) and higher, providing crypto resistance for a minimum of 3 years. It’s shown that the Grover algorithm is similar to the destructive effect of "viewing transmitted data" (decipher), based on a complete search of all code structures (brute force) using modern super- computers. It’s established that well-known symmetric cryptographic methods can potentially be used in the post-quantum era and methods based on noise-like signals potentially, provided they are detected and aware of the methods underlying them (without knowledge of the key), cannot be applied in the post-quantum era. According to the authors, a promising approach in the post-quantum era for information security issues is the use of chaotic signals.