Abstract: This paper describes a method of forecasting the guaranteed operating time using the quantile zones. There are presented an equations and graphics for calculations of the guaranteed time operating error.

Key words: Reliability, guaranteed time, parameters’ drifts, quasi-deterministic, quantile zones.

ACM Classification Keywords: B.8.1 Hardware - Performance and Reliability - Reliability, Testing, and Fault- Tolerance

Link:

RESEARCH OF ACCURACY OF GUARANTEED OPERAYTING TIME PREDICTION BY FRACTILE ZONES METHOD

Leonid Nedostup, Myroslav Kiselychnyk, Pavlo Zayarnyuk

http://foibg.com/ibs_isc/ibs-27/ibs-27-p23.pdf

Abstract: An analysis of the basic system for the synthesis of formulas of algebra algorithms was conducted The need for a construction of an expanded system for computer synthesis that would allow simplifying the notation of algebra formulas was demonstrated. Basing on functional criterion purpose a three-level model of decomposition was created. The model is recorded with the help of formulas of algebra algorithms. An implementation of the created model was made in the MS Visual Studio 2010 platform in C# programming language and samples are presented.

Keywords: Algebra, algorithm, model, formula, subsystem, operations: formatting editor

ACM Classification Keywords: F.2 Analysis of algorithms and problem complexity

Link:

SYSTEM MODIFICATION MODEL CREATING SYNTHESIS FOR ALGORITHM FORMULAS

Magdalena Niziołek, Volodymyr Ovsyak

http://foibg.com/ibs_isc/ibs-27/ibs-27-p22.pdf

Abstract: The paper highlighted the problems of selection methods for the preparation of the "raw" data for subsequent processing in the systems of intelligent information analysis. Each application domain contains a lot of different types of identification characteristics. Most algorithms are unable to work directly with all types and formats of data. Therefore, the preparation or the transformation of the input data set is an integral part of analysis system design. In the paper discusses methods of transformation of continuous and discrete types of data useful for analysis of the vector set. On the example of the domain "Information customs control" has been shown as configured training set for recognition of risks violation of customs legislation, based on a neural network the type multilayer perceptron. Were also considered methods of forming pseudographic patterns from the input sequence data initially did not a graphic of origin.

Keywords: preprocessing, transformation data

ACM Classification Keywords: D.2 SOFTWARE ENGINEERING – D.2.12 Interoperability – Data mapping

Link:

PREPROCESSING "RAW" DATA SETS AS AN IMPORTANT ASPECT OF INTELLIGENT INFORMATION PROCESSING

Sergii Konovalenko

http://foibg.com/ibs_isc/ibs-27/ibs-27-p21.pdf

Abstract: The article presents the design and construction of data acquisition module, which allows read and write data counted by the data acquisition board. The acquisition was controlled using a program that was created in the QNX Momentics development environment, based on the architecture of the RLP. It involves the measurement card control directly by the read and write to memory registers. Data acquisition was performed on a computer running a hard real-time system QNX6 Neutrino. With the use of available tools QNX Neutrino RTOS was realized network communication process for managing production data in a distributed system. The article presents also industrial networks such as Profibus and Ethernet. Discusses the characteristics of distributed systems and the requirements for real-time systems.

Keywords: real-time system, data acquisition, distributed system

ACM Classification Keywords: J. Computer Applications, J.2 Physical Sciences And Engineering, J.7 Computers In Other Systems,

Link:

USING REAL-TIME SYSTEM TO MANAGE PRODUCTION DATA IN A DISTRIBUTED SYSTEM

Magdalena Dobrzańska, Paweł Dobrzański, Artur Łopuszyński, Łukasz Kurowski

http://foibg.com/ibs_isc/ibs-27/ibs-27-p20.pdf

Abstract: Today in Lithuania understanding the principles of administrative justice is aggravated because of complicate system of institutions dealing with pre-trial procedure of administrative offenses and the administrative judicial system, and the imperfection of the current laws. For Lithuanian citizens are difficult to orient in administrative law norms. At the same time with the administrative law violations often every citizen is faced. Therefore, public awareness and legal education serve for formation of civil society. Information and communications technologies in today's society are perceived and practical sensed as background of any the modern organization and public management environments model. It can be argued that public education on matters of basic justice administrative measures should be applied in the information space. The first steps in usage of public relations and information technologies activities in courts have to go. Lithuanian administrative courts apply the public information activities on the court web sites. However, the authors’ studies show that public authorities and administrative courts websites provide information mainly oriented to publicity of proceedings the trial. Information about the administrative features of the infringement is almost unavailable. The article deals with public information policies and implementation of the accessibility of administrative justice in Lithuania in cyberspace.

Keywords: administrative justice, principles of public information, the information society.

ACM Classification Keywords: J.1 Administrative Data Processing - Law

Link:

INFORMATION SYSTEMS OF ADMINISTRATIVE JUSTICE – AS SOCIAL TOOL FOR IMPLEMENTATION OF PUBLICITY PRINCIPLE

Tatjana Bilevičienė, Eglė Bilevičiūtė

http://foibg.com/ibs_isc/ibs-27/ibs-27-p19.pdf

Abstract: German psychologist Hermann Ebbinghaus, the first person studied a memory, experimentally publishes his forgetting curve, which characterized the ability of a human brain to remember the information. He proved experimentally that during the first hour of learning process 60 percent of information is forgotten and after 10 hours of workload our memory abandons 35 percent of information. Then forgetting process become slower and after six days our memory abandons near 20 percent of the learning material. As a result of the research Hermann Ebbinghaus has suggested the algorithm of the effective learning. Based on the modification of the algorithm we have created a special service for learning foreign words called WordSteps?. It allows to learn more than 97 percent of new information even in a year after the first training.

Keywords: Memory, natural language processing, learning words

ACM Classification Keywords: I.2.7 Natural Language Processing

Link:

THE EDUCATIONAL TECHNOLOGY FOR LEARNING FOREIGN WORDS

Andrey Dukhovny

http://foibg.com/ibs_isc/ibs-27/ibs-27-p18.pdf

Abstract: The paper presents the concept of an intelligent tutoring system for learning Belarusian as a foreign language. At the heart of the system is a model of learning consisting of the following models: tutor model, learner model, model of Interaction, learning process structure model, learning activity forms model, academic discipline model.

Keywords: learning model, tutor model, learner model, model of Interaction, learning process structure model, learning activity forms model, academic discipline model.

ACM Classification Keywords: I.2 ARTIFICIAL INTELLIGENCE - I.2.1 Applications and Expert Systems - Natural language interfaces General.

Link:

INTELLIGENT TUTORING SYSTEM FOR BELARUSIAN AS A FOREIGN LANGUAGE

Olga Yeliseyeva, Yury Kim

http://foibg.com/ibs_isc/ibs-27/ibs-27-p17.pdf

Abstract: Millions of Facebook and Twitter users send their comments all over the world about products and services, political and economical events, etc. (almost 3 billions each day) The principal problem of opinion mining such information is text parameterization, and in the paper we describe our experience in solution of this problem with Peruvian Facebook and Twitter. We use enriched vocabularies of Spanish SentiStrength? and propose a simple algorithm for evaluation of sentiment contribution. The work was completed in the framework of the project WAYRA (Telefonica-Peru). The results proved to be promised: opinion analysis of parameterized texts showed the accuracy about 75% with elementary classifier

Keywords: opinion mining, SentiStrength?, Facebook and Twitter

ACM Classification Keywords: I.2.7 Natural Language Processing

Link:

PARAMETERIZATION OF COMMENTS FROM PERUVIAN FACEBOOK AND TWITTER: LEXICAL RESOURCES AND ALGORITHM

Angels Catena, Mikhail Alexandrov, Roque López

http://foibg.com/ibs_isc/ibs-27/ibs-27-p16.pdf

Abstract: SentiStrength? is a well-known tool for opinion mining texts circulated in social networks. There are English, Spanish, Russian versions of SentiStrength?, which demonstrated their advantages in numerous examples. In the paper we present our classifier of opinions for analysis of comments from the Peruvian Facebook and Twitter. We corrected and enriched SentiStrength? Spanish vocabularies having in view the properties of Peruvian Spanish. We also slightly modified the SentiStrength? algorithm rules. We demonstrate the results we have reached with our classifier and SentiStrength?. The experimental results are competitive with traditional approaches developed in this area, and the total accuracy proved to be 72%.

Keywords: SentiStrength?, Opinion Mining, Facebook and Twitter

Link:

SPANISH SENTISTRENGTH AS A TOOL FOR OPINION MINING PERUVIAN FACEBOOK AND TWITTER

Roque López, Javier Tejada, MikeThelwall?

http://foibg.com/ibs_isc/ibs-27/ibs-27-p15.pdf

Abstract: In this paper we consider the problem of keyword extraction for the document annotation. We study different statistic-based measures for such extraction and compare the results with the annotations made by skilled experts. The experiments were completed with the Inspec data set. The quality of annotation was evaluated by means of R-Precision? score.

Keywords: keywords extraction, single document annotation, natural language processing.

ACM Classification Keywords: I.2.7. Natural Language Processing

Link:

THE STUDY OF FACTORS RELADED WITH SINGLE-DOCUMENT KEYWORD EXTRACTION

Popova Svetlana

http://foibg.com/ibs_isc/ibs-27/ibs-27-p14.pdf

Abstract: This article aims to present the results of clustering in documents, extracted from Internet and related to compositional phrasemes (pragmatemes). We are studying conditions (situation, context), which can stipulate presence of these units in a text. Pragmateme’s structure and functioning particularities are taken into consideration. An important objective of the work is selection of an adequate algorithm for tag extraction and clustering, so that we can further compare and apply the results, obtained for different languages.

Keywords: pragmateme, compositional phraseme, tag extraction, clustering analysis

ACM Classification Keywords: I.2.7. Natural Language Processing

Link:

AUTOMATED TAG EXTRACTION & CLUSTERING IN DOCUMENTS CONTAINING COMPOSITIONAL PHRASEMES

Vera Danilova, Xavier Blanco, Dmitry Stefanovskiy

http://foibg.com/ibs_isc/ibs-27/ibs-27-p13.pdf

Abstract: The paper presents the results of automatic term extraction from a special text corpus (a collection of papers on corpus linguistics) by means of statistical methods (association measures) combined with certain syntactic models. The approach undertaken in the paper is based on lexico-syntactic models that can be viewed as models of phrases for the Russian language. The Sketch Engine system represents itself a corpus tool which takes as input a corpus of any language and corresponding grammar patterns. The system gives information about a word’s collocability on concrete dependency models, and generates lists of the most frequent phrases for a given word based on appropriate models. The extracted terms belong to various clusters and represent the lexical structure of the texts in question. The applied method includes statistical analysis that enables estimating paradigmatic and syntagmatic relations between lexemes based on their distribution.

Keywords: Corpora, distributional and statistical methods, collocations, automatic term extraction, thesaurus.

ACM Classification Keywords: I.2.7 Natural Language Processing

Link:

STUDYING SPECIAL TEXT RUSSIAN CORPORA BY THE LEXICO-SYNTACTIC MODELS

Maria Khokhlova, Victor Zakharov

http://foibg.com/ibs_isc/ibs-27/ibs-27-p12.pdf

Abstract: The paper presents the results of automatic term extraction from a special text corpus (a collection of papers on corpus linguistics) by means of statistical methods (association measures) combined with certain syntactic models. The approach undertaken in the paper is based on lexico-syntactic models that can be viewed as models of phrases for the Russian language. The Sketch Engine system represents itself a corpus tool which takes as input a corpus of any language and corresponding grammar patterns. The system gives information about a word’s collocability on concrete dependency models, and generates lists of the most frequent phrases for a given word based on appropriate models. The extracted terms belong to various clusters and represent the lexical structure of the texts in question. The applied method includes statistical analysis that enables estimating paradigmatic and syntagmatic relations between lexemes based on their distribution.

Keywords: Corpora, distributional and statistical methods, collocations, automatic term extraction, thesaurus.

ACM Classification Keywords: I.2.7 Natural Language Processing

Link:

STUDYING SPECIAL TEXT RUSSIAN CORPORA BY THE LEXICO-SYNTACTIC MODELS

Maria Khokhlova, Victor Zakharov

http://foibg.com/ibs_isc/ibs-27/ibs-27-p12.pdf

Abstract: The problem of selection of perspective objects for investments is considered. Objects are Russian companies of mobile communication. To solve this problem we use the decision-making support system (DSS) SVIR and manual procedures of the Muchnik method. We shortly describe these tools and show that both approaches lead to close results. The paper is prepared on the basis of B.Sc. thesis of the first author

Keywords: multicriteria selection, DSS SVIR, Muchnik method

Link:

MULTICRITERIA SELECTION OF PERSPECTIVE OBJECTS FOR INVESTMENTS: DSS SVIR VS. MUCHNIK METHOD

Pavel Mogilyov, Mikhail Alexandrov, Stanislav Mikoni

http://foibg.com/ibs_isc/ibs-27/ibs-27-p11.pdf

Abstract: In this paper, we propose to extend traditional Fuzzy Logic(FL) techniques by creating a second set of inference rules (and the corresponding inference mechanism) in order to effectively produce results exploitable by decision makers. We present a formal definition of a multi-level FL scheme and its application in the development of: i) a break-even inference machine and ii) a legal argumentation system. The proposed scheme is shown to be useful in modeling systems where intermediary fuzzy concepts come to play, and it could be applied in several problems analog to the ones presented in this study.

Keywords: Multilevel Fuzzy Logic, Knowledge Based Systems, Legal Argumentation System.

Link:

A MULTI-LEVEL FUZZY LOGIC SCHEME FOR MODELING COMPLEX PROBLEMS

July Diana Banda-Tapia?, Regina Ticona Herrera, Dennis Barrios-Aranibar? Joe Tekli, Richard Chbeir

http://foibg.com/ibs_isc/ibs-27/ibs-27-p10.pdf

Abstract: Decision making processes in manufacturing companies are becoming extremely complex and require more and more knowledge, both of technological quality of products, concerning a production process, as well as the industrial engineering and control. The increase in the scale of production and the level of technological development have caused that industrial companies have become systems that require the application of modern effective methods of the decision making. This paper presents a study of the issues related to decision-making and knowledge acquisition in enterprises. The model of intelligent decision support system for the production company has been developed. The paper presents the main idea of system and data models in the form of ER diagram, that will finally be implemented in RDBMS environment. In addition, an attempt to assess such systems.

Keywords: decision support systems, knowledge base, knowledge representation, knowledge acquisition.

ACM Classification Keywords: I. Computing Methodologies, I.2.1 Applications and Expert Systems, J. Computer Applications,

Link:

THE MODEL OF DECISION SUPPORT SYSTEM FOR A MANUFACTURING COMPANY

Monika Piróg-Mazur?

http://foibg.com/ibs_isc/ibs-27/ibs-27-p09.pdf

Abstract: We consider the condition of the same ordering of objects due to using the convolution of utility functions and membership functions. It turns out that the same order takes place when the each utility function of an attribute is constructed as a convolution of fuzzy membership functions of this attribute. To transform membership functions to utility function of an attribute the formula was deduced. The example illustrates that transforming. The paper provides examples of application of the transformation of membership functions in the utility function, and vice versa.

Keywords: utility function, membership function, additive and multiplicative convolution.

ACM Classification Keywords: G. Mathematics of Computing, I.2.1 Applications and Expert Systems.

Link:

STUDY RELATIONSHIP BETWEEN UTILITY FUNCTION AND MEMBERSHIP FUNCTION IN THE PROBLEM OF OBJECT RANKING1

Stanislav V. Mikoni, Marina I. Garina

http://foibg.com/ibs_isc/ibs-27/ibs-27-p08.pdf

Abstract: In the paper different well-known market characteristics and indicators of financial accounting (net income, revenue, revenue growth, etc.) are considered. We propose new characteristics, which could be useful for company assessment. We also describe a classification technique based on Naive Bayes method to identify the most attractive companies.

Keywords: classification, Naive Bayes, financial market, stock’s returns.

ACM Classification Keywords: I.2 ARTIFICIAL INTELLIGENCE

Link:

STUDY OF INVESTMENT ATTRACTIVENESS OF RUSSIAN COMPANIES ON THE BASIS OF THEIR MARKET CHARACTERISTICS AND PERFORMANCE REPORTING

Dmitriy Bogachev

http://foibg.com/ibs_isc/ibs-27/ibs-27-p07.pdf

Abstract: Time series prognosis of economical indexes is one of the main problems of econometrics. In the paper we study possibility to give an interval prognosis of time series using the set of the best prognostic models. Speaking ‘model’ we mean a combined model of regression and auto-regression. Speaking ‘the best models’ we mean the ordered series of models constructed by the well-known Group Method of Data Handling (GMDH). The proposed simple approach consists in the following: a) one generates the fixed numbers of models on the basis of experimental data b) these models give correspondent prognoses c) the real value is supposed to belong to min-max interval the models provide. We shortly describe the software tool GMDH-Shell (GS) that implements GMDH and the results of experiments with GS. The experimental data are time series of the Gross Domestic Products (GDP) of 100 countries given on the period 1980-2000.

Keywords: GMDH, GMDH Shell, time series prognosis, gross domestic product

ACM Classification Keywords: I.2 Artificial Intelligence

Link:

TIME SERIES PROGNOSIS OF GDP WITH THE SYSTEM GMDH-SHELL (EXPERIMENTAL WORK)

Victor Lebedev

http://foibg.com/ibs_isc/ibs-27/ibs-27-p06.pdf

Abstract: Smoothing and prognosis belong to the main problems, which we deal with when process various time series. Unlike the typical approaches related with lineal regression on polynomial and trigonometric functions we consider local procedures. We describe algorithms that resolve these problems and present results of experiments using data of the Russian State Statistical Committee. All procedures are realized in the Excel-VBA.

Keywords: econometrics, local regression, time series, seasonality

ACM Classification Keywords: I.2.m Miscellaneous

Link:

SMOOTHING AND PROGNOSIS OF MULTI-FACTOR TIME SERIES OF ECONOMICAL DATA BY MEANS OF LOCAL PROCEDURES (REGRESSION AND CURVATURE EVALUATION)

Alexander Kovaldji, Vladimir Averkiev, Marina Sarkissyan

http://foibg.com/ibs_isc/ibs-27/ibs-27-p05.pdf

Abstract: The article is devoted to the issue of using financial multipliers to estimate the value of a company. In our research we identified the industries that account for more than 50% of Gross Domestic Product. We took the companies with publicly available information. Then we used multicriteria Muchnik's model to identify promising companies and receive the required sample. At the final stage, we used a comparative approach for the evaluation of companies in these industries. The results of experiments showed the essential advantage of the proposed method. Notably, we marked multiplier, which were most likely gave a more realistic evaluation of companies. The paper reflects the results of Bachelor research.

Keywords: financial multiples; company valuation; multicriteria Muchnik's model; comparable company

ACM Classification Keywords: I.2.m Miscellaneous

Link:

ESTIMATION OF THE INVESTMENT ATTRACTIVENESS OF COMPANIES USING MULTIPLES THAT ACCOUNT FOR INDUSTRY SPECIFIC FACTORS

Evgeniy Ageev

http://foibg.com/ibs_isc/ibs-27/ibs-27-p04.pdf

Abstract: Forrester model is a system of differential equations reflecting dynamics of 5 macro-economical variables (population, resources, etc.) . Such a model were developed more then 40 year ago and it proved to be an effective tool for qualitative analysis of world dynamics. By the moment there is no an accessible end-user program based on this model and our goal was the development of such a program with a comfortable graphical interface. In the paper we describe the program World-Dyn?, which allows to set initial data and noise level, to set moments of parameter changes, to form the necessary visualization of results. We demonstrate the program functionality both on Forrester’s example and on our example related with crisis.

Keywords: Forrester model, world dynamics, numerical analysis.

Link:

PROGRAM WORLD-DYN BASED ON FORRESTER MODEL OF WORLD DYNAMICS

Olga Proncheva

http://foibg.com/ibs_isc/ibs-27/ibs-27-p03.pdf

Abstract: Decision trees are the well-known a popular tool in the areas where non-numerical data are used. In the paper we demonstrate the application of decision trees for analysis of International logistics. First of all we cluster data to reduce the number of variants for comparison. Then the regression analysis is completed and the significant parameters combinations are determined. The logical function and decision tree could be useful for revealing possible corruption schemes in logistics. Finally we complete experiments with this decision tree. The suggested method can be used for constructing a decision tree based on a large amount of similar data.

ACM Classification Keywords: 1.2 Artificial Intelligence

Keywords: decision trees, logistics, corruption

Link:

CONSTRUCTING DECISION TREE BASED ON QUESTIONNAIRES TO DETECT A POSSIBLE CORRUPTION IN LOGISTICS

Dmitry Stefanovskiy, Sergey Maruev, Xavier Tejada

http://foibg.com/ibs_isc/ibs-27/ibs-27-p02.pdf

Abstract: We consider queuing systems as models of distance learning system we analyze how characteristics of business process in the system affect on throughput and on learning outcomes. The processes of executing tasks and tasks validation process are the key processes in the distance learning. A model of the process performed by a student is a queuing system with refusals. A model of the process performed by the teacher is a multi-channel queuing system with limited queue. We present a structure of one of the courses of the University, where the authors work to form individual trajectory of learning. for students with different levels of knowledge. Such an approach allow to increase the throughput of distance learning system.

Keywords: distance learning, process modeling, queuing system analysis

ACM Classification Keywords: K.3.1 Computer Uses in Education, Distance Learning

Link:

ANALYSIS OF THE THROUGHPUT OF THE PROCESS OF DISTANCE LEARNING

Sergey Maruev, Evgeniya Gorbunova

http://foibg.com/ibs_isc/ibs-27/ibs-27-p01.pdf

Abstract: This paper describes the principles for the development of interactive query or question-answer expert systems (ES) in the Multi Studio software environment in Multi (the universal language), as well as in such environments as Visual Prolog and CLIPS. The paper also presents a comparative analysis of those principles checked by solving the test problems to show a significant advantage of Multi in the development of those ES according to the main quality parameters: language usability, work content of ES development, electronic memory size and speed of the developed ES. As a result of our study we formulate several principles of developing ES tool environments:  Development of a super-high-level universal environment language by integrating the best qualities of all the languages considered in the paper.  Development of a universal structure of a knowledge base with a unitized syntax based on semantic networks.  Development of a hybrid tool environment which can separately perform the following:  A one-time translation (compilation) of program and data input texts into an internal language of a knowledge base  Multiple fetch of programs from a knowledge base (the programs are executed by interpretation of those programs’ instructions in a hybrid environment)

Keywords: expert systems, CLIPS, Multi Studio, Prolog.

ACM Classification Keywords: I.2.5 Programming Language and Software.

Link:

PRINCIPLES OF THE DEVELOPMENT OF INTERACTIVE QUERY EXPERT SYSTEMS

Valentin Kataev

http://www.foibg.com/ibs_isc/ibs-26/ibs-26-p24.pdf