
Keyword: "forecasting"
Irina Aleksandrovna Moshkina, Ulyanovsk State Technical University, Candidate of Science in Engineering; Associate Professor at the Department of Information Systems of Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of articles in the field of intellectual analysis of time series. [email: timina_i@mail.ru]I. Moshkina,
Evgenii Nikolaevich Egov, Ulyanovsk State Technical University, graduated from the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; Assistant at the Department of Information Systems at Ulyanovsk State Technical University; at author of articles in the field of data mining. [email: e.egov@ulstu.ru]E. Egov


Project State Forecasting on Time Series of Metrics and on Detected Anomalies
The article deals with an example of the anomalies detection when analyzing the time series of metrics that characterize the project activity to adjust the project state forecasting. Project activity metrics are analyzed. A forecasting algorithm based on fuzzy tendency of time series metrics is developed and implemented. Authors suggest a procedure for detecting the time series anomaly based on entropy. A formula for computing the entropy measure for a fuzzy time series is proposed. The algorithm allows to take into account the dependence of the predicted values on the entropy measures. For forecasting, a hypothesis is used, which is formed for a given period on the basis of a trend. The results of the application of the proposed approach for forecasting the state of the project "FreeNAS9" are given. Time series, software metrics, entropy, forecasting.



Sections: Artificial intelligence
Subjects: Artificial intelligence, Information systems. 
Iulia Evgenevna Kuvaiskova, Ulyanovsk State Technical University, Candidate of Engineering, Associate Professor; graduated from the Faculty of Economics and Mathematics of Ulyanovsk State Technical University; Associate Professor of the Department of Applied Mathematics and Informatics at Ulyanovsk State Technical University; an author of papers in the field of time series analysis, fuzzy logic and technical diagnostics. [email: u.kuvaiskova@mail.ru]I. Kuvaiskova,
Anna Aleksandrovna Aleshina, SimbirSoft Company, Candidate of Engineering, graduated from the Faculty of Economics and Mathematics of Ulyanovsk State Technical University; Software Developer at SimbirSoft Company; an author of papers in the field of timeseries modeling and forecasting. [email: a2nia@mail.ru]A. Aleshina,
Kseniia Andreevna Fedorova, Ulyanovsk State Technical University, Candidate for the Master’s Degree at of the Faculty of Information Systems and Technologies of Ulyanovsk State Technical University; an author of papers in the field of fuzzy logic and technical diagnostics. [email: k.a.fedorova@bk.ru]K. Fedorova


Information and Mathematical System of Support of Decisionmaking on Management of the Object Based on Forecasting of Its Technical State
This article describes the developed information and mathematical system designed to support the decisionmaking on the management of an object on the basis of analysis and forecasting of its technical state. This system allows to obtain adequate mathematical models and forecasts of the monitored indicators of a technical object in an automatic mode. In this case, the model parameters are corrected by a pseudogradient procedure; the stability of the object is analyzed; fuzzification of numerical values of object state indicators is performed, as well as a qualitative assessment of the projected technical state of the object in the form of a fuzzy term with the degree of truth of the predicted result. To demonstrate the effectiveness of the system developed, the diagnostics of the hydrounit functioning was carried out according to the results of vibration measurements. Forecasting, decision support system, technical object.



Sections: Mathematical modeling
Subjects: Mathematical modeling. 
Iulia Evgenevna Kuvaiskova, Ulyanovsk State Technical University, Candidate of Engineering, Associate Professor; graduated from the Faculty of Economics and Mathematics of Ulyanovsk State Technical University; Associate Professor of the Department of Applied Mathematics and Informatics at Ulyanovsk State Technical University; an author of papers in the field of time series modeling and forecasting. [email: u.kuvaiskova@mail.ru]I. Kuvaiskova, Anna Aleksandrovna Aleshina, Ulyanovsk Instrument Manufacturing Design Bureau Joint Stock Company, Candidate of Engineering; graduated from the Faculty of Economics and Mathematics of Ulyanovsk State Technical University; Software Engineer at Ulyanovsk Instrument Manufacturing Design Bureau Joint Stock Company; an author of papers in the field of time series modeling and forecasting. [email: a2nia@mail.ru]A. Aleshina


The Use of Adaptive Regression Modeling in the Description and Forecasting of the Object Technical State
The safe operation of the technical object is an important task. The technical object management system often includes a subsystem for monitoring its settings, so, the object management solution is made due to its technical condition. The effectiveness of such a subsystem essentially depends on the accuracy of prediction of the object technical parameters. Therefore, it is necessary to build adequate mathematical models of the controlled object parameters and their subsequent use for the object state forecasting and, accordingly, for providing effective and operational management decisions. In order to solve the formulated problems, the article describes the algorithms of mathematical modeling and forecasting of the object technical state on the basis of the adaptive regression modeling. The algorithms allow several times increase of the prediction accuracy. High accurate results of the object state forecasting are used in the decisionmaking process related to the object management. The efficiency of the offered algorithms is investigated by the example of modeling and forecasting of the object technical state. Adaptive regression modeling, time series, forecasting, technical object.



Sections: Mathematical modeling
Subjects: Mathematical modeling. 
Tatiana Vasilievna Afanaseva, Ulyanovsk State Technical University, Doctor of Engineering; Associate Professor, Deputy Head of Information System Department at Ulyanovsk State Technical University; graduated from the Faculty of Radioengineering at Ulyanovsk State Technical University; an author of articles and monographs in the field of the intellectual analysis of time series. [email: tv.afanasjeva@gmail.com]T. Afanaseva, Aleksei Andreevich Sapunkov, Ulyanovsk State Technical University, Postgraduate Student of the Information System Department at Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of articles in the field of the intellectual analysis of time series. [email: sapalks@gmail.com]A. Sapunkov, Mkrtych Sarkisovich Tonerian, Ulyanovsk State Technical University, Postgraduate Student of the Information System Department at Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technologies at Ulyanovsk State Technical University; an author of articles in the field of the intellectual analysis of time series. [email: mkr73@yandex.ru]M. Tonerian


The Twostage Algorithm of Choosing the Fuzzy Model for Time Series Firecasting
The article deals with a twostage algorithm for the best timeseries forecasting model based on the assessment of the model adequacy with the use of behavior and accuracy. For testing, the authors use time series that have been exploited at the International Time Series Forecasting Competition IFASEUSLAT in 2015 ([http://irafm.osu.cz/cif/main.php]). Database of this Competition includes 91 numerical time series of different length, tendency, and data reading frequency. Time series values depicted the dynamic of parameters reported from banking area, social networks, and medicine. Three models based on the fuzzy time series concept have been used for timeseries forecasting. In order to choose the best model, the twostage algorithm based on the comparison of time series and model tendencies has been proposed. In addition to the already known quality criterion, the new ones are also exploited in the algorithm. In the conclusion, the results obtained are discussed and the effectiveness of the suggested algorithm is demonstrated. Fuzzy tendency, fuzzy time series, forecasting, linguistic description.



Sections: Information systems
Subjects: Information systems. 
Kadyrova Gulnara Rivalevna, Ulyanovsk State Technical University, Candidate of Engineering; graduated from the Faculty of Radioengineering of Ulyanovsk Polytechnic Institute; Associate Professor of the Department of Applied Mathematics and Informatics of Ulyanovsk State Technical University; an author of monographs, textbooks, and articles in the field of statistical modeling, software information systems. [email: gulya@ulstu.ru] G.R. Kadyrova


Evaluation and Prediction of Technical Object Condition With the Use of Regression Models
The article presents information about the System of Optimum Regression Search (SORS) statistical package realizing the approach of adaptive regression modelling and providing an evaluation of the observation model adequacy and search of its optimal structure. The methodology means reduction of the model dimension and increase of determination accuracy of its parameters and the forecast. Efficiency of the methodology is directly proportional to dimension, the degree of noisiness, and multicollinearity of the initial data. Consequently, it allows considering its application for the description of technical objects conditions as perspective mathematical approach. One of the tasks in data analysis is the problem of choice of a comparison measure for the competitive models. The use of internal quality measures for smaller dimension models intended for forecasting cannot always give as authentic view of a particular competitive structure that is preferable as possible. The article investigates properties of the cross validation measure that is based on the complete sample of data and uses it as control data sample for familiar internal and external measures. The prospect of its application for identification of the forecasting optimal model within SORS is demonstrated in the article. Regression modelling, forecasting, methods of structural identification, quality measure, sors, statistical package.



Sections: Mathematical modeling
Subjects: Mathematical modeling, Information systems. 
Tatyana Vasilievna Afanasieva, Ulyanovsk State Technical University, Doctor of Engineering; graduated from the Radio Engineering Faculty of Ulyanovsk Polytechnic Institute; Professor of Information System Department in Ulyanovsk State Technical University; an author of books and articles in the field of time series data mining and analysis. [email: tv.afanasjeva@gmail.com]T. Afanasieva


Forecasting Timeseries Local Trends in the Big Data Analysis
According to the forecasts in the field of IT (IDC) the growth of the stored data volumes obtained from various sources will be doubling every two years until 2020. This tendency will remain stable in the conditions of the data increase generated in the OLTP systems, on social networks and by devices in case of mutual exchange of information during the intensive development of the data warehouse, "cloud computing", "the Internet of things" and "digital production" technologies. All that gives rise to a considerable interest in the Big Data analysis and processing from both business and a scientific community. The technology of analytical OLAPsystems for the analysis of the large data, focused on providing a visualization of the multidimensional data and the formation of interactive reports, is one of the most popular in decision support and Business intelligence systems. A promising technology in the field of analysis in addition to the OLAPsystems and aiming at identifying hidden patterns in the large data, is a technology of time series data mining. The most important tasks of time series data mining certainly should include forecasting time series points. A scientific basis of the methodology of the local trends forecasting as fuzzy trends for univariate time series (numeric and nonnumeric) which lead to the fuzzy time series are discussed in this article. The solution to this problem is interesting both in theoretical and practical aspects. It is known that fuzzy time series models are proven themselves for a short length time series, and for a long length time series a large computation is required. This paper proposes a ktrend algorithm for extracting local trends out of the big data, considered as a time series, and a time series model in terms of fuzzy local trends is shown. An effect of applying the proposed approach, expressed in a significant reduction of the computational cost when using a fuzzy time series model is shown. Big data, fuzzy models, time series, local trends, forecasting.



Sections: Mathematical modeling
Subjects: Mathematical modeling, Automated control systems, Artificial intelligence. 
Irina Aleksandrovna Timina, Ulyanovsk State Technical University, Postgraduate student at the Department of Information systems at Ulyanovsk State Technical University; graduated from the Faculty of Information Systems and Technology at Ulyanovsk State Technical University with the speciality in Applied Information Science (in Economics); an author of articles and research papers in the field of data mining. [email: timina_i@mail.ru]I. Timina


Fuzzy Dependency As a Problemsolving Method for Timeseries Mining
The article is concerned with a fuzzy timeseries dependency analysis intended for the problem solving of modelling and forecasting of the economicunits behaviour. The problem solving is based on the application of a linear regression model, on the degree of similarity between the time series and their correlation. In order to forecast the value of Fuzzy Time Series, a method of fuzzy elementary tendencies is used. The proposed approach has been examined experimentally. Fuzzy time series, forecasting, fuzzy tendency.



Sections: Mathematical modeling, calculi of approximations and software systems
Subjects: Artificial intelligence, Operational research. 
Tatiana Vasilyevna Afanasyeva, Ulyanovsk State Technical University, Candidate of Engineering, Associate Professor at the Chair 'Applied Mathematics and Information Science' of Ulyanovsk State Technical University; author of articles, a monograph, a textbook in the field of intellectual analysis of time series. [email: tv.afanaseva@mail.ru]T. Afanasyeva, Nadezhda Glebovna Yarushkina, Ulyanovsk State Technical University, Doctor of Engineering, Professor; ProRector for Science; head of the Chair 'Information Systems' at Ulyanovsk State Technical University; author of articles and monographs in the field of intellectual analysis of data. [email: jng@ulstu.ru]N. Yarushkina


Efficiency Analysis of Fuzzy Trend Model for Forecasting of Time Series
The article describes a new model for the analysis of time series for the forecast of small time series. The base of the new model is formalization and identification of a new object of time series  a fuzzy trend. The suggested model does not have assumptions used in stochastic simulation, and is easy for the implementation and developed for linguistic interpretation of results. The experiment studies of the accuracy figures of the suggested model reveal its adequacy for forecasting of small time series and competitiveness in comparison with its analogues. Forecasting, time series, fuzzy trend, accuracy figures.



Sections: Artificialintelligence systems
Subjects: Artificial intelligence, Automated control systems, Mathematical modeling. 
