Software & Systems

Journal articles №3 2022

1. A rehabilitation simulator for patients with hand mobility problems using virtual reality technologies [№3 за 2022 год]
Authors: Aglyamov F.R. (aglyamov.fox@gmail.com) - Kazan Federal University (Master of Science); Kugurakov V.S. (vladimir.kugurakov@kpfu.ru) - Kazan Federal University, SIM – Laboratory of Simulation Technologies in Biomedicine (Associate Professor, Leading Researcher), Ph.D;
Abstract: A hand is one of the most important parts of the human body; its injuries seriously affect even normal activities. Thus, restoring the hand function and mobility is one of the most complex and important top-ics for normal daily life. The subject of this study is a hardware-software simulator complex to reha-bilitate patients with hand mobility disorders using virtual reality technology. The topic is relevant due to a higher level of patient’s interest and motivation, which can potentially increase the interest and ef-fectiveness of rehabilitation procedures. The authors have analyzed modern motion modeling methods, as well as the use of a virtual reality technology for rehabilitation and tracking changes in motor functions of patients with cognitive prob-lems. The result of the study is a prototype glove and software for collecting information about the finger flexion degree, as well as a set of exercises for a patient and rehabilitation progress recordings for fur-ther analysis. The paper presents a possible architecture option for integrating the reading glove with modern VR systems. Practical relevance relates to the introduction of an experimental method for rehabilitation, the ef-fectiveness of which has been proven theoretically and will probably be effective in practice, which is planned to be proven later. Section 6 outlines further plans for the glove development, as well as the addition of functionality to the rehabilitation application.
Keywords: stroke, task-oriented therapy, exergaming, serious games, glove, hand rehabilitation, vr, virtual reality
Visitors: 4074

2. Using partial parallelization to triangulate 2D domains [№3 за 2022 год]
Authors: Bikbulatov T.Kh. (ch7cly@gmail.com) - Kazan Federal University, Institute of Computational Mathematics and Information Technologies (Undergraduate Student); Tumakov D.N. (dtumakov@kpfu.ru) - Kazan Federal University, Institute of Computational Mathematics and Information Technologies (Associate Professor), Ph.D;
Abstract: Delaunay triangulation of an arbitrary domain is one of the fundamental problems of computational geometry. Classical approaches to Delaunay triangulation produce triangles that have a wide range of angle values. The paper proposes an algorithm for triangulation of complex geometry domains taking into ac-count predetermined parameters: the minimum angle and the maximum side length of the obtained tri-angles. The algorithm consists of three main stages. The first stage takes a set of points that set the fig-ure boundary as input, and forms an initial partition into subdomains from them generating points for further triangulation. Such generation for subdomains is completely independent; therefore, it is most effectively parallelized by the number of logical cores. The figure is then triangulated by the divide-and-conquer algorithm. Here, the highest performance is achieved with the number of threads equal to the number of physical processor cores. At the last stage, the parameters of triangles are refined by a method based on Ruppert’s algorithm. Due to the specifics of the algorithm, the serial code is optimal at this stage. All parallelization is implemented using OpenMP technology in C++. The paper shows numerical results representing the increase in computing performance for a different number of threads depend-ing on the problem dimension.
Keywords: OpenMP, parallelization,, ruppert's algorithm, delaunay triangulation
Visitors: 3699

3. Solving the problem of electromagnetic wave diffraction on arbitrary shape screens using CUDA [№3 за 2022 год]
Authors: Giniyatova D.Kh. (normaliti@gmail.com) - Kazan Federal University, Institute of Computational Mathematics and Information Technologies (Senior Lecturer); Markina A.G. (m8angelina@gmail.com) - Kazan Federal University, Institute of Computational Mathematics and Information Technologies (Junior Researcher);
Abstract: The paper considers the algorithm for solving the problem of electromagnetic (EM) wave diffraction on flat arbitrary shape screens using the CUDA parallel programming technology. The problem is formulated as an integro-differential equation and solved by the method of moments (Galerkin method). The authors have chosen RWG functions as basis and testing functions. They have developed a simple and fast algorithm for triangulating a domain with an arbitrary boundary to con-struct the corresponding RWG elements on GPU. Numerical results were presented for the diffraction problem on canonical and complex shape screens. The obtained solution is in good agreement with the results of the previous studies. The paper also presents a comparative analysis of the execution time of serial and parallel algo-rithms. It is shown that the use of CUDA technology significantly speeds up the solving of the problem of EM wave diffraction on flat metal arbitrary shape screens.
Keywords: parallel algorithm, rwg functions, method of moments, cuda technology, diffraction problem
Visitors: 3206

4. True and fictitious eigenvalues of the set of Muller boundary integral equations [№3 за 2022 год]
Authors: Ketov I.V. (ivlketov@gmail.com) - Kazan Federal University (Graduate Student); Oktyabrskaya A.O. (alina.oktyabrskaya.21@gmail.com) - Louisiana State University (Postgraduate Student); Spiridonov A.O. (aospiridonov@gmail.com) - Kazan Federal University, Research Laboratory for High Performance Computing, Medical Cybernet-ics, and Machine Vision (Institute of Computational Mathematics and Information Technologies) (Senior Researcher), Ph.D; Karchevskii E.M. (ekarchev70@gmail.com) - Kazan Federal University, Research Laboratory for High Performance Computing, Medical Cybernet-ics, and Machine Vision (Institute of Computational Mathematics and Information Technologies) (Associate Professor, Professor of Applied Mathematics and Artificial Intelligence Department, Principal Researcher of Research Laboratory of High Performance Computing, Medical Cybernetics and Machine Vision), Ph.D;
Abstract: The authors have investigated the spectrum of a nonlinear eigenvalue problem for a system of bounda-ry integral equations theoretically and numerically. In general, eigenvalues of this problem split into two sets. The first set is the set of the true eigenvalues corresponding to the original eigenvalue prob-lem of the Helmholtz operator. The second set is the set of fictitious eigenvalues that correspond to the so-called "turned inside-out" problem. Therefore, it is important to determine the conditions under which the original eigenvalue problem for the Helmholtz operator on a plane and the corresponding problem for the integral operator are spectrally equivalent. The original eigenvalue problem for the Helmholtz operator is reduced to a nonlinear eigenvalue problem for the system of Muller boundary integral equations. The solutions of the original problem and the "turned inside-out" problem are found by the method of separation of variables. The solution of the system of Muller boundary integral equations is based on the Galerkin method. The paper formulates and proves the equivalence theorem for the original eigenvalue problem for the Helmholtz operator and the system of Muller boundary integral equations. It shows that the spec-trum of the nonlinear eigenvalue problem of the system of Muller boundary integral equations contains fictitious eigenvalues in addition to the true eigenvalues. There is a defined area on the complex plane that consists only of fictitious eigenvalues; and it is shown that these fictitious eigenvalues are explicit-ly separated from true eigenvalues. The equivalence theorem provides a theoretical justification for the applicability of the Muller boundary integral equation method. The developed computer programs can be directly used in the modeling microdisk lasers.
Keywords: spectral equivalence, active microcavity, microdisk laser, muller boundary integral equations, eigenvalue problem
Visitors: 2759

5. Structuring natural text entities using neural networks for generating 3D-scenes [№3 за 2022 год]
Authors: Kozar B.A. (bogdan.kozar.itis@gmail.com) - Kazan Federal University (Engineer); Kugurakova V.V. (vlada.kugurakova@gmail.com) - Kazan Federal University (Associate Professor), Ph.D; Sakhibgareeva G.F. (gulnara.sahibgareeva42@gmail.com) - Kazan Federal University (Assistant);
Abstract: The subject of this study is the automation using neural networks of the process of assembling three-dimensional scene, which can be used both to generate three-dimensional scenes or locations in com-puter games from a textual description, and to prepare sequences of three-dimensional synthetic data. This topic is relevant for developing three-dimensional graphics including interactive projects – games, simula-tors, AR/VR applications. After analyzing and comparing the results obtained in a number of well-known completed projects, the authors determine technologies and software libraries, which allow effectively achieving the de-sired goal - to provide fast assembly of three-dimensional scenes filled with objects according to the text description. Thanks to synthesis of the best solutions, it was possible to create an optimal concept that allows achieving quick and qualitative result with the right rules of building geometrical relations between scene objects. There is a formed list of requirements to the designed tool and its architecture. Input data for using this tool is a text in natural language; output data is a scene with objects corre-sponding to the description used. The main result achieved is a finished software tool for Unreal Engine developed on the basis of the nlp-ue4 neural network and the set of tensorflow, nltk, pandas, gensim, h5py libraries. The readiness of the tool is evaluated as a prototype solution, which can be integrated into the drafting stage of interac-tive projects with three-dimensional graphics. To evaluate the created tool effectiveness objectively, the authors have conducted the experiments that proved that its use even in the current version significantly reduces development time and does not require a user to have skills in programming or creating three-dimensional graphics. There is also a discussion about the research development prospects.
Keywords: computer graphics, unreal engine, neural network, nlp, automation, level design, procedural generation, render, 3d modeling, computer games
Visitors: 4300

6. A filtration model and parallel computing of the blood flow characteristics in the circulatory system in case of an occluding circular clot [№3 за 2022 год]
Authors: Konyukhov V.M. (vladimir.konyukhov@kpfu.ru) - Kazan Federal University (Professor), Ph.D; Khramchenkov M.G. (mkhramch@gmail.com) - Kazan Federal University (Professor), Ph.D; Konyukhov I.V. (i.konyukhov@innopolis.ru) - Innopolis University (Associate Professor), Ph.D;
Abstract: The authors have mathematically described the blood flow in the circulatory system based on the gen-eral filtration equations at the presence of an occluding circular porous clot located on the vessel wall, taking into account clot destruction under the action of hydrodynamic forces. The change in the inter-nal forces occurring in the clot material leads to forming an inhomogeneous permeability distribution, which is a function of spatial coordinates and time. Under the assumption of a symmetric toroidal shape of the thrombus, the paper considers a flat two-dimensional problem in the cross section of the vessel and a clot. The authors have developed finite-difference schemes and iterative algorithms using parallel com-puting technologies to solve corresponding two-dimensional problem in a blood vessel and a blood clot with heterogeneous permeability. They have also carried out parallelization at the visualization of the hydrodynamic characteristics of the flows. The software package with the implemented numerical and algorithmical models enables computational experiments with simultaneous visualization of their re-sults. There is the analysis of the influence of the shape and the structure of a clot formed at the blood vessel wall on the main hydrodynamic characteristics determining the probability of a clot breakage from the wall. It is shown that the most dangerous are the blood clots which boundary forms an acute angle with the vessel wall. This is caused by to two factors: the occurrence of the rotary moment of the forces tending to the break of the blood clot front edge down the vessel wall, as well as by the action of a local pressure gradient at the clot base, which significantly exceeds the pressure gradient in the vessel outside the blood clot. At the same time, the clot permeability affects the total pressure drop and the maximal pressure gradient magnitude, but it practically does not change the direction of the fluid flow in the blood vessel.
Keywords: occluding circular clot, circulatory system, parallel computing, numerical algorithms, filtration model
Visitors: 3566

7. Remote control of a robotic device using virtual reality [№3 за 2022 год]
Authors: Kugurakova V.V. (vlada.kugurakova@gmail.com) - Kazan Federal University (Associate Professor), Ph.D; Khafizov M.R. (mrimsh@mrimsh.ru) - Kazan Federal University (Senior Lecturer); Kadyrov S.A. (kadyrovsamat16@gmail.com) - Kazan Federal University (Graduate Student); Zykov E.Yu. (Evgeniy.Zykov@kpfu.ru) - Kazan Federal University (Associate Professor), Ph.D;
Abstract: The subject of this paper is the possibility of remote control of a robotic device using the virtual reality technology. This concept is being developed in order to create a more native way to control a device remotely, as well as a more convenient image transmission for an operator, which is especially relevant in extreme situations. The paper presents the analysis of intelligent control system technologies and the examples of im-plementing virtual reality technologies in tele-robotics. This helped to highlight the overall structure of the remote control system and to show the main implementation problems of this project. This analysis has become a base for development and implementation of a universal hardware and software telecon-trol platform on the Unity platform. The paper presents the application architecture and considers the requirements initially imposed on it in order to bypass the wireless channel limitations in the task of the real-time robot control using VR headsets. There is an implemented control system for selecting the direction of moving a robotic unit using one of the VR controllers. The paper considers implemented algorithms for obtaining high-quality stereoscopic vision in virtual reality devices, as well as the technique for synchronizing the re-mote rotation of a stereo pair. Moreover, there is a description of a command transmission system. The experiments of the implemented system were conducted in order to verify if it meets the neces-sary requirements to obtain the proper quality. The authors have measured the response time of the system and minimized the delay in the communication channel. The developed software for robotic unit telecontrol using a virtual reality headset provides the pos-sibility of stable telecontrol of remote robotic equipment.
Keywords: virtual reality, telecontrol, robotics, cybersickness
Visitors: 4608

8. Applying CUDA technology for training the Kohonen neural network [№3 за 2022 год]
Authors: Latypova D.S. (dina.latypova23@gmail.com) - Kazan Federal University, Institute of Computational Mathematics and Information Technology (Postgraduate Student); Tumakov D.N. (dtumakov@kpfu.ru) - Kazan Federal University, Institute of Computational Mathematics and Information Technologies (Associate Professor), Ph.D;
Abstract: The paper presents clustering of the data from in the training samples of the MNIST and Fashion MNIST databases. For clustering, the authors use a Kohonen neural network with a Euclidean metric for estimating distances. The optimal number of clusters (no more than 50) is determined for each handwritten digit (MNIST) and type of clothing (Fashion MNIST). Neural network training is parallelized on a NVidia graphics device using CUDA technology. There are the results for each digit illustrating the comparison of the processor and GPU operating time. For both the digits and clothing types, there is a conclusion about a 17-fold acceleration on an entry-level gaming laptop. Test samples of the same databases are used to verify the cluster construction correct-ness. For both sequential and parallel learning, it is concluded that the vectors from the test sample be-long to the correct cluster with a probability of more than 90 % in the case of handwritten digits. In ad-dition, there are calculated F-measures for each digit and type of clothing to evaluate clusters. It is shown that sequential and parallel clustering give similar results. The best values of the F-measure are obtained for the digits 0 and 1 (F-mean is 0.974), while the worst value is obtained for the digit 9 (F-mean is 0.903). For the Fashion MNIST data, the best value for the F-measure was obtained for trousers (F-average value is 0.96), and the worst value was for a shirt (F-average value is 0.34). De-spite the large variations for the F-metric values of the considered two databases, the differences in the clustering results are minimal. Thus, the maximum difference of the F-measure is about 0.01 for the MNIST and about 0.04 for the Fashion MNIST.
Keywords: mnist, cuda, parallelization, clusterization, kohonen neural network
Visitors: 4686

9. A method for simplifying task tracking in video game development projects [№3 за 2022 год]
Authors: Sharaeva R.A. (r.sharaeva3496@gmail.com) - Kazan Federal University, Institute of Information Technology and Intelligent Systems, Department of Software Engineering (Junior Researcher); Kugurakova V.V. (vlada.kugurakova@gmail.com) - Kazan Federal University (Associate Professor), Ph.D; Selezneva N.E. (nataliseleznewa306@gmail.com) - Kazan Federal University, Institute of Information Technology and Intelligent Systems, Department of Software Engineering (Postgraduate Student);
Abstract: Computer game development differs from “traditional” IT project development mainly due to the high degree of process creativity, which should be taken into account when applying software engineering methods. The research topic is studying the specifics of project management process automation and devel-oping a tool embodying the methods and recommendations formed for the game industry. The authors have analyzed topical scientific sources to set the goal and objectives correctly. As a result, they have highlighted a number of functions necessary for team task trackers that are: assigning a role or a task to an employee, creating dependent tasks, Gantt chart, giving access to information about related tasks to an employee, distributing links and documents, creating reusable templates. Based on the extensive research results, the paper presents a methodology that simplifies the work of the project manager in terms of task management. The approach includes creation of the following features: executors automatically receive tasks according to their field of concern; automatic creation of duplicates and configuration of task dependencies; automatic transfer of artifacts to dependent tasks; generating a project template according to a brief. The work is interesting for the field of interac-tive project development with a prevailing game-dev component. In order to check the result effectiveness, the generated practical approaches were integrated into the LeanTime system. The proposed approach has shown the reduction of time for management tasks by more than 20%; in case of need for many new templates the reduction can even exceed 40%. The designed web-tool can then be integrated as an automation tool not only in the development processes of gamedev projects, but in general for any highly specialized IT development areas.
Keywords: automation, task tracker, gamedev, it development, software engineering
Visitors: 4145

10. Forecasting based on the second generation artificial neural network for decision support in especially significant situations [№3 за 2022 год]
Authors: E.V. Palchevsky (teelxp@inbox.ru) - Financial University under the Government of the Russian Federation; Antonov V.V. (antonov.v@bashkortostan.ru) - Ufa State Aviation Technical University, Faculty of IRT (Professor), Ph.D; Enikeev R.R. (enikeevRR@mail.ru) - Ufa State Aviation Technical University, Faculty of IRT (Associate Professor), Ph.D;
Abstract: Nowadays, specialized system models implemented on the basis of decision support in exceptional (emergency) situations (states) using machine learning, artificial intelligence (including using neural networks) to reproduce, predict and prevent (or minimize risk) consequences) in exceptional situations are useful and becoming increasingly popular. Floods also fall under such exceptional situations and states. Therefore, there arises the problem of early forecasting of an exceptional situation using the ex-ample of rising water levels at stationary hydrological posts in order to prevent (or minimize the risk) the transition of the system under consideration into an exceptional state (emergency situation). To solve this problem, the authors propose a decision support system for early forecasting water rise levels. It is based on a neural network (intelligent) analysis of retrospective data (code of a station-ary hydrological station / automatic station, date, water level at a stationary hydrological station / au-tomatic station, atmospheric pressure, wind speed, snow cover thickness, amount of precipitation, time and air temperature) in order to calculate the values of water levels for 5 days in advance. The artificial neural network itself is based on the freely distributed TensorFlow machine learning software library; a modified backpropagation method is used as training. Its main difference is the addition of an artificial neural network (ANN) learning rate increase factor. An analysis of the effectiveness of the proposed solution in the framework of forecasting the flood situation has shown high accuracy in calculating the forecast values of water levels: the difference be-tween the real and predicted values is 2.10 %. This will allow specialized services to carry out special-ized anti-flood measures in advance (5 days in advance). Thus, information support during special situations is an absolute (not relative) indicator of data quality that allows developing and making decisions in the framework of predicting possible critical situations and preventing the transfer of the state of the territory management system to critical situa-tions.
Keywords: forecasting, data intelligent analysis, neural network analysis, retrospective data, forecasting water levels
Visitors: 3813

| 1 | 2 | 3 | Next → ►