Software & Systems

Articles of journal № 3 at 2017 year.

Order result by: Public date | Title | Authors |

21. Method of frequency-morphological classification of texts [№3 за 2017 год]
Authors: A.А. Osochkin, Fomin V.V., А.V. Flegontov
Visitors: 11006
Appearing of centralized data storages and information accumulation as structured tables or semistructured texts is a result of growing attention to data analysis techniques. The analysis of similar data in the long term allows obtaining important information, which can become a basis for making right management decisions or predicting further development of events in many fields. One of the important directions of such analysis is automatic classification of collected data in electronic form. Its simplified model is reduced to reading, text processing and assigning a topic to a document from a given list of topics. Foreign papers more and more often are devoted to medical data classification for further disease progression forecast on the basis of statistics or diagnosis based on medical history. The main difficulty in classification are natural language texts. They are difficult to classify due to linguistic features of language and support by a part of classification methods of exclusively numerical data. The paper studies scientific activity in the field of NLP based on the annual publication of scientific papers in this field. It also offers the method of Russian-language texts classification that integrates the algorithms of frequency, morphological and intellectual analysis. The paper presents the results of some experiments on the identification method of classification with high classification accuracy. The classification was carried out according to functional, literary, and authorial styles.

22. Review of simulation modeling tools for robot groups with social organization elements [№3 за 2017 год]
Authors: M.A. Rovbo, E.E. Ovsyannikova , A.A. Chumachenko
Visitors: 9081
The paper discusses mechanisms that are important for a proper simulation of artificial agents’ group, especially mobile robots, which are organized into a system with the elements of a social structure. The authors provide an overview of simulation tools based on these requirements to determine advantages and disadvantages of existing systems for modeling, simulating and researching such systems. They identify key instruments for a simulation of artificial groups with social structures. The review focuses on simulation tools for biological systems (in particular, ants since they are a good example of a social group), agent-based modeling and robot-specialized simulation tools. The paper emphasizes the level of support of various social mechanisms in simulation tools, as well as their capability to model a large number of agents (in particular, cluster computing support) and the ability to simulate user-provided models and implementations of different aspects of a social group. It was found out that, although there are many general modeling and simulation tools, there is very little support and ready-to-use implementations of even widely used mechanisms, such as pheromones, which are provided by systems to build and research a group of robotic agents with a social structure. On the other hand, the tools that aim at simulating systems with social behavior elements, such as ant modeling systems, are not very scalable or limited in aspects they can simulate. There are no mechanisms to expand them for further research. Based on the review, the paper has detected a lack of a comprehensive simulation system that specifically aims at the research of artificial agent groups with social structure elements. It has also formulated a set of requirements for such a system.

23. Optimization of the problem of conflict detection with dangerous aircraft movement areas to execute on Intel Xeon Phi [№3 за 2017 год]
Author: Rybakov, A.A.
Visitors: 4011
An aircraft generates a wake vortex during its flight. This wake might be dangerous for other air traffic participants, especially in zones with a large number of aircrafts. So, the problem of vortex wake modeling and conflicts detection is very important and in demand. The article considers a vortex wake as a set of dangerous zones in separate traffic segments. A dangerous zone of separate traffic segment is a pencil of spheres – a set of spheres with centers on this segment. Next, we consider the direct mathematical method of detecting an intersection of a line and a pencil of spheres. The line is an immediate trajectory of own aircraft, while a pencil of spheres forms the whole dangerous flight zone. Since the number of traffic segments in a dangerous zone is large enough, it is appropriate to use accelerators in such calculations. The paper considers using Intel Xeon Phi coprocessors for this task and applying some manual sourcecode optimization to enforce execution code vectorization. This approach leads to five-time acceleration of calculation for 107 traffic segments in a dangerous zone.

24. Analysis of modern methods for vlsi project testing and verification [№3 за 2017 год]
Author: Slinkin D.I.
Visitors: 6941
VLSI development companies are keeping selected design flows and a testing process is a part of them. It is considered that from 60 % to 80 % of development teams’ efforts are spent on VLSI project verification and debugging. Debugging of register-transfer level (RTL) models is an important phase. There is no universal way to solve this problem. The article is devoted to the analysis of foreign and domestic publications on industrial VLSI project debugging. There are four main methodologies that are being considered: formal verification, simulation testing, using of hardware accelerators, prototyping based on programmable logic integrated circuits (FPGAs). For each of these methodologies there is information on an error detection method, existing software and hardware debugging tools. The paper analyzes some of their features, such as labor consumption, requirements for qualification and size of verification group, the cost of necessary tools and the availability of metrics to evaluate the test coverage. There are names of some industrial VLSI projects that used these methodologies, such as microprocessors, high-performance network switches, graphics processors. The paper mentions the tools used by the developers. Special attention is paid to debugging FPGA projects. The following approaches are considered: using the built-in logic analyzer, external control and measuring equipment and their combination. Finally, based on the practical experience the paper shows that four VLSI project debugging and verifying methodologies have different applications. It mentions the types of VLSI, which use one of these methodologies. Their advantages and disadvantages are briefly summarized.

25. Anaphor resolution system development based on machine learning methods [№3 за 2017 год]
Authors: A.V. Sokolov, Batura T.V.
Visitors: 8596
The paper proposes and implements a method for the anaphora resolution of third person pronouns in Russian texts. The problem of finding the true pairs “anaphor-antecedent” is considered as a binary classification problem. Initially, the authors perform morphological and syntactic analysis of the text. The morphological analyzer used the pymorphy2 library. The parsing has been performed using MaltParser. The algorithm of anaphora resolution itself consists of three stages. First stage includes searching for all pronouns, then there is a compilation of many potential antecedents, and finally the most suitable candidate is selected. The component of creating a set of candidates for antecedents is based on using distance, morphological and syntactic filters. Classification uses the Random Forest algorithm. The anaphoric classifier takes into account 78 different features. The authors performed a series of experiments in order to prove the effectiveness of the proposed method. They showed that that the quality of the analyzer improves if we do not take into account the morphological case. It can also be noted that the number of trees taken for calculation has a lesser effect on the final result when taking a feature set without cases. The paper considers the main difficulties in developing the anaphora resolution systems. First, the search for anaphoric relations is in the semantic domain, and therefore it is difficult to formalize. Second, there are some features of the Russian language, such as developed morphology, morphological and syntactic ambiguities, which adversely affect the result.

26. Development of a pattern recognition system for a mobile robot [№3 за 2017 год]
Authors: Ulyanov, S.V., A.G. Reshetnikov, K.V. Koshelev
Visitors: 9621
The main development source of robotic systems and artificial intelligence systems is improvement of computer technology, devices and sensors that allow obtaining information about the environment. This process is inextricably linked with the development of software on-board processors, which are used in autonomous robot managing. The article gives a brief description of a module of a developed image recognition system for an autonomous robot, which is based on a stereo vision technology. Nowadays, more and more articles mention the systems consisting of combinations of several video cameras, laser radars, ther-mal imagers and other sources of information about the environment. Equipment of this class became widespread when creating au-topilots for vehicles, security control systems, unmanned aerial reconnaissance, various household robots. Stereo vision allows ob-taining data on image depth, the distance to objects. It also provides an opportunity to build a three-dimensional picture of the sur-rounding world. The paper describes the configuration of the equipment used (a pair of cameras fixed on a common base): a stereopair calibrating process, the calibration pattern on the image was searched using the ROS framework. Images obtained from cameras are subjected to rectification (a transformation when both images are projected onto a plane parallel to the line that connects the optical centers of the cameras). The article considers the fundamentals of projective transformations and epipolar geometry. The paper presents the idea that un-derlies the construction of depth and displacement maps. As a result, it presents a recognition software module developed using the Python programming language.

27. Нybrid cognitive fuzzy control systems for an autonomous robot based on neurointerface and soft computing [№3 за 2017 год]
Authors: Ulyanov, S.V., A.G. Reshetnikov, A.A. Mamaeva
Visitors: 7216
The article discusses the possibility of applying neurointerface together with different types of regulators via the typical example of controlling an autonomous vehicle. There is an assessment of application possibilities of intelligent computing methods and means to improve the control system performance reliability. The aim of this work is to show experimentally the possibilities of cognitive interface effective application (“brain-computer-actuating device”) on the example of motor vehicle driving (a mobile robot). The paper also reveals modern management technologies application and shows the role and the necessity of intelligent computing in the operating “brain-computer” interface in order to improve the reliability and robustness of the control system. In particular, the paper considers the possibility of controlling the movement of the object (forward, backward, left, right, bypass obstacles) with the help of a cognitive helmet using a standard command recognition block and different types of control systems, including knowledge base optimizer based on soft computing.

28. A framework for analysis and forecasting of time series in the development of proactive decision support system components [№3 за 2017 год]
Authors: M.V. Shcherbakov, K.S. Zadiran, A.V. Golubev, Al-Gunaid Mohammed Amin
Visitors: 7881
The article describes the developed framework for automation research on software design for decision support proactive systems. In particular, it considers the problem of analysis and forecasting time series to form automation components in predicting various processes. In practice, there are various data analysis libraries (R, Python) used for prototyping the component uses. The main problem is a lack (or insufficiency) of implementation of analysis methods, i.e. the sequence of actions during analysis. In addition, there is a number of limiting factors that affect the efficiency of analysis and forecasting components design: (i) time-consuming routine operations during time series manual analysis; (ii) developer’s insufficient qualifications as a deterrent in implementing proactive system components; (iii) a frequent need in the analysis of a large number of similar data. The proposed software solution (a software in Python) automates the process of time series analysis and generate a LaTeX report. Formation is automatic in accordance with CRISP-DM methodology. The report provides a comprehensive analysis of time series in accordance with published and accepted methods. All functions of the framework can be attributed to one of the following groups: data loading and the internal data frame; descriptive time series analysis with visualization; prediction and report making. The paper shows an example of using a framework to solve the problem of proactive management decisions making support in energy management systems (forecasting of electricity consumption).

29. A software suite to determine the parameters of three-phase alternating current electric arcs burning in a horizontal surface [№3 за 2017 год]
Authors: I.M. Yachikov, E.M. Kostyleva
Visitors: 8800
The metallurgical industry uses a lot of equipment with electrical arcs as the sources of thermal energy. They burn in the direction of the horizontal heat-absorbing surface. Knowing electromagnetic forces affecting the arcs, their location and behavior is significant when designing new furnaces and automating their operation. The literature review shows that many issues connected with electrical arcs of three-phase alternating current are underserved due to technical complexity, high cost and often impossible on industrial or pilot plants. A possible method of research is the development of appropriate mathematical models, their implementation as applied software and further computer modeling. The paper shows mathematical models and developed software, which includes modules for determining the magnetic field intensity, electromagnetic forces, arc and heat flow forms, near three arcs of three-phase alternating current burning in the direction of a horizontal surface. The result of the created software complex is calculation and representation of vector fields including magnetic field strength and average-integral electromagnetic forces, as well as visualization of the average form of electric arc column axis by the period and the heat flux distribution on a horizontal heat-absorbing surface.

◄ ← Preview | 1 | 2 | 3