ДМДмитрий Михайлович Мурин

Дмитрий Михайлович Мурин

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Дмитрий Михайлович Мурин has a total of 18 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • UAV Detection Using Neural Networks

    by M. D. Averina, O. A. Levanova, D. V. Grushevskaya, K. A. Kukharev, D. M. Murin, M. A. Kalinin

    The availability of unmanned aerial vehicles (UAVs) has led to a significant increase in the number of offenses involving their use. This makes the develop

  • Joint Simplification of Various Types of Spatial Objects While Preserving Topological Relations

    by O. P. Yakimova, D. M. Murin, V. G. Gorshkov

    Cartographic generalization includes the selection of objects and phenomena, as well as their simplification (generalization), to be shown in the map while


  • Open Access

    UAV detection using neural networks

    by Мария Дмитриевна Аверина, Ольга Александровна Леванова, Darya V. Grushevskaya, Kirill A. Kukharev, Дмитрий Михайлович Мурин, Максим Александрович Калинин, Дарья Грушевская

    The availability of unmanned aerial vehicles (UAVs) has led to a significant increase in the number of offenses involving their use. This makes the development of UAV detection systems relevant. Solutions based on deep neural networks show the best results in detecting UAVs on video. This article presents a study of various neural network detectors and focuses on identifying objects as small as possible, up to the size of $4\times4$ and even $3\times3$ pixels. The work investigates architectures SSD (VGG16) and YOLOv3 and it's modifications. Precision and recall metrics are calculated separately for different intervals of the object areas. The best result have been shown by YOLOv3 model with bbox parameters chosen as the result of object sizes clustering. Small ($3\times3$ px) drones have been successfully identified with 76% precision and a very small recall of 26%. For objects between 10 and 20 pixels in area, the recall is 64% with an accuracy of 75%. For objects with an area more than 20px the recall is about 90%, the precision is 89%, and the F1 score is 90%. These results show that it is possible to recognize even $4\times4$ pixel drones, which can be used in video surveillance systems.


  • Open Access

    Joint simplification of various types spatial objects while preserving topological relationships

    by Olga P. Yakimova, Дмитрий Михайлович Мурин, Владислав Геннадьевич Горшков

    Cartographic generalization includes the process of graphically reducing information from reality or larger scaled maps to display only the information that is necessary at a specific scale. After generalization, maps can show the main things and essential characteristics. The scale, use and theme of maps, geographical features of cartographic regions and graphic dimensions of symbols are the main factors affecting cartographic generalization. Geometric simplification is one of the core components of cartographic generalization. The topological relations of spatial features also play an important role in spatial data organization, queries, updates, and quality control. Various map transformations can change the relationships between features, especially since it is common practice to simplify each type of spatial feature independently (first administrative boundaries, then road network, settlements, hydrographic network, etc.). In order to detect the spatial conflicts a refined description of topological relationships is needed. Considering coverings and mesh structures allows us to reduce the more general problem of topological conflict correction to the problem of resolving topological conflicts within a single mesh cell. In this paper, a new simplification algorithm is proposed. Its peculiarity is the joint simplification of a set of spatial objects of different types while preserving their topological relations. The proposed algorithm has a single parameter — the minimum map detail size (usually it is equal to one millimeter in the target map scale). The first step of the algorithm is the construction of a special mesh data structure. On its basis for each spatial object a sequence of cells is formed, to which points of this object belong. If a cell contains points of only one object, its geometric simplification is performed within the bounding cell using the sleeve-fitting algorithm. If a cell contains points of several objects, geometric simplification is performed using a special topology-preserving procedure.

  • Research of Models of Topological Relations of Spatial Features

    by V. G. Gorshkov, D. M. Murin, O. P. Yakimova

    In map production it is necessary to keep the spatial relationships between map features. Generalization is simplification performed on geographical data w


  • Open Access

    The Statistical Analysis of the Security for a Wireless Communication System with a Beaulieu-Xie Shadowed Fading Model Channel

    by Алексей Сергеевич Гвоздарев, Татьяна Константиновна Артёмова, Павел Евгеньевич Патралов, Дмитрий Михайлович Мурин

    В работе рассмотрена задача анализа безопасного сеанса на физическом уровне беспроводной системы связи в условиях многолучевого канала распространения сигнала и наличия канала утечки информации. Для обобщения эффектов распространения была выбрана модель канала Beaulieu-Xie с затенениями. Для описания безопасности процесса передачи информации использовалась такая метрика, как вероятность прерывания безопасного сеанса связи. В рамках исследования было получено аналитическое выражение вероятности прерывания связи. Проведён анализ её поведения в зависимости от характеристик канала и системы связи: среднего значения отношения сигнал-шум в основном канале и канале утечки, эффективного значение показателя потерь на пути распространения сигнала, относительного расстояния между законным приемником и прослушивающим приёмником и пороговой пропускной способности, нормированной на пропускную способность гладкого гауссова канала. Рассмотрены совокупности параметров, которые покрывают важные сценарии функционирования беспроводных систем связи. К ним относятся как глубокие замирания (отвечающие гиперрэлеевскому сценарию), так и малые замирания. Учитываются условия наличия существенной по величине компоненты прямой видимости и значительного количества многопутевых кластеров, затенения доминантной компоненты и многопутевость волн, а также всевозможные промежуточные варианты. Обнаружено, что величина энергетического потенциала, необходимого для гарантированной безопасной связи с заданной скоростью, определяется в первую очередь мощностью многопутевых компонент, а также наличие неснижаемой вероятности прерывания безопасного сеанса связи с ростом для каналов с сильным общим затенением компонент сигнала, что с практической точки зрения важно учитывать при предъявлении требований к величинам отношения сигнал/шум и скорости передачи данных в прямом канале, обеспечивающим желаемую степень безопасности беспроводного сеанса связи.


  • Open Access

    Research of Models of Topological Relations of Spatial Objects

    by Владислав Геннадьевич Горшков, Dmitriy M. Murin, Olga P. Yakimova

    In map production it is necessary to keep the spatial relationships between map objects. Generalization is the simplification performed on geographical data when decreasing its representation scale. It is a common practice to simplify each type of spatial objects independently (administrative boundaries first, then road network, hydrographic network, etc.). During the process some spatial conflicts, which require manual correction, arise inevitably. The generalization automation still remains an open issue for data producers and users. Many researchers are working to achieve a higher level of automation. In order to detect the spatial conflicts a refined description of spatial relationships is needed.The paper analyzes models of describing topological relationships of spatial objects: the nine intersections model, the topological chain model and the E-WID model. Each considered model allows to take into account some relations between objects, but does not allow to transfer them exactly. As a result, the task of developing a model of relations preserving topology is relevant. We have proposed an improved model of nine intersections, which takes into account the topological conflict that occurs when a point object is located next to a simplified line. Line simplification is one of the most requested actions in map production and generalization. When the mesh covered the map inside the cell there can be points, line segments and polygonal topological objects, which, if the cell is rather small, are polyline objects. Thus, the issue of simplification of topological objects within a cell is reduced to the issue of simplification of linear objects (polylines). The developed algorithm is planned to be used to solve the problem of consistent generalization of spatial data. The ideas outlined in this article will form the basis of a new index of spatial data that preserves their topological relationships.


  • Open Access

    On the Issue of Using “Useful” Tasks for Proof of Works in Blockchain

    by Dmitry M. Murin, N. Knyazev Vladimir

    К вопросу использования «полезных» задач для обеспечения работой блокчейн систем


  • Open Access

    Question Answering System for Applicant Support by Using Modern Messengers

    by Дмитрий Русланович Филонов, Dmitry Ju. Chalyy, Дмитрий Михайлович Мурин, Валерий Георгиевич Дурнев, Валерий Анатольевич Соколов, Дмитрий Юрьевич Чалый

    There is an increasing interest to the instant messaging applications, messengers. These applications allow us to interact with other users and include a functionality that can help us to implement bots that automate various business processes or provide information services. In this paper, we consider a specialized question answering system that uses today’s messaging services infrastructure to support university applicants. We gathered a corpus of applicants questions throughout two years and developed an information retrieval model that helps us to find similar questions in the corpus. Applicants can type their questions using a natural language without any formal requirements to phrase construction or using special templates. If the system is unable to find a relevant answer, the user can directly address the question to representatives of the university. The system was implemented with the use of modern cloud services that are provided by Amazon. We used serverless computations and NoSQL data bases, so we had to develop an architecture of the system in that way. Since the system contains sensitive personal data and provide personalized service, we must focus our attention on security. We proposed the means that must improve the safety of the system, more specifically, authentification process that can be used without the explicit use of personal data, however, this is a future work. At present we test our system and evaluate its quality of information retrieval.

  • Open Access

    On Some Approaches to the Solution of the Problem «Useful Proof-of-work for Blockchains»

    by Валерий Георгиевич Дурнев, Дмитрий Михайлович Мурин, Валерий Анатольевич Соколов, Dmitry Ju. Chalyy, Дмитрий Юрьевич Чалый

    The blockchain technology is based on the ”Proof-of-work” principles. The essence of this principle is that some event (for example the bill-to-bill money transaction) becomes significant after the confirmation by a certain computer work. So, a demand arose for such computational problems to work on, and we will spend on it about the whole blockchain system computing capacity. Now the main kind of such a problem is a hash-puzzle – the problem to find a bit string with a hash that satisfies some conditions. The important hash-puzzle weakness is the lack of the useful application outside of the blockchain technology. In this work, we offer some approaches to ”Useful Proof-of-work for blockchains” problem, namely, consider some practical variants of the NP-complete problems that could be solved with the help of SAT or LLL-solvers as the Proof-of-Work computational problems. The use of the FPTproblems requires special study. The offered approach allows to provide the following characteristics of the proof-of-work computational problems: usefulness, problems complexity management (through the dimension change, choosing problems of certain kind, the indication of necessary solution precision), mass character. Herewith we admit that not every solved problem can be useful but we consider the opportunity to solve some practical problems with the help of the blockchain technology. Among other things it is also possible to compare the virtual crypto-currency value (through the energy costs spent) and the effective result of the practical problems solution. The most complicated points of the described approach are the realization of the events-problems (providing the computer work for these events) relations and the realization of the problems complexity analysis system. This issue should be viewed as the study program because of many technical details that must be worked out further.