ISSN 1991-2927
 

ACP № 3 (61) 2020

Author: "Pavel Vladimirovich Dudarin"

Pavel Vladimirovich Dudarin, graduated from Ulyanovsk State University; Postgraduate Student at the Department of Information Systems of Ulyanovsk State Technical University; an author of scientific papers in the field of data processing by means of neural networks. e-mail: p.dudarin@ulstu.ru.P. Dudarin,

Vadim Georgievich Tronin, Candidate of Science in Engineering; Associate Professor at the Department of Information Systems of UlSTU; an author of scientific papers in the field of economics, finance and information technologies. e-mail: v.tronin@ulstu.ru.V. Tronin,

Kirill Valerevich Sviatov, Candidate of Science in Engineering; graduated from UlSTU; Dean of the Faculty Information Systems and Technologies of UlSTU; an author of scientific papers in the field of automation of management processes. e-mail: k.svyatov@ulstu.ru.K. Sviatov,

Vladimir Aleksandrovich Belov, graduated from UlSTU with a bachelor degree in Software Engineering; Master Student at the Department of Information Systems of UlSTU; an author of an article in the field of computer operation monitoring. e-mail: v.belov@ulstu.ru.V. Belov,

Roman Azatovich Shakurov, graduated from UlSTU with a bachelor degree in Software Engineering; Master Student at the Department of Information Systems of UlSTU; an author of articles in the field of computer operation monitoring and developing of system for determining the winner in cyber security competitions. e-mail: r.shakurov@ulstu.ru.R. Shakurov

An Approach To Labor Intensity Evaluation In Software Development Process Based On Neural Networks 57_8.pdf

Software development process is actively studied by experts from different spheres of science and different viewpoints. However, the degree of success of projects in the development of software intensive systems (Software Intensive Systems, SIS) has changed insignificantly, remaining at the level of 50% inconsistency with the initial requirements (finance, time and functionality) for medium-sized projects. The annual financial losses in the world because of the total failures are counted by hundreds of billions of dollars. Its high complexity leads to constant mistakes in labor intensity evaluation, and even new agile development paradigm does not solve this problem. This paper shows that retrospective labor intensity estimation could be approximated by a function, implemented by neural network, with some amount of code complexity metrics as arguments. Also there is a described an approach of neural network training and data collection, which allows to automate a process of retrospective labor intensity evaluation in agile software developing process. Experiments performed on the real life software project show the effectiveness of proposed technique.

Software developing process, neural network, data augmentation, Halstead metrics, Cyclomatic metric.

2019_ 3

Sections: Artificial intelligence

Subjects: Artificial intelligence.



Pavel Vladimirovich Dudarin, Ulyanovsk State Technical University, Postgraduate Student at the Department of Information Systems of Ulyanovsk State Technical University (UlSTU); graduated from the Ulyanovsk State Technical University; an author of papers in the field of text clustering. [e-mail: PDudarin@ibs.ru]P. Dudarin,

Aleksandr Petrovich Pinkov, Ulyanovsk State Technical University, Candidate of Economics, graduated from Ulyanovsk branch of Kuibyshev Planning Institute; Acting Rector of Ulyanovsk State Technical University, an author of more than 50 papers, a monograph, and articles in the field of economics, planning, marketing, production engineering, higher education organization, and corporate training. [e-mail: rector@ulstu.ru]A. Pinkov,

Nadezhda Glebovna Yarushkina, Ulyanovsk State Technical University, Doctor of Engineering, Professor; First Vice-Rector - Vice-Rector for Scientific Affairs of Ulyanovsk State Technical University; Head of the Department of Information Systems of UlSTU; graduated from Ulyanovsk Polytechnic Institute; an author of more than 300 papers in the field of soft computing, fuzzy logic, and hybrid systems. [e-mail: jng@ulstu.ru]N. Yarushkina

Methodology and the Algorithm for Clustering Economic Analytics Object 000_12.pdf

The purpose of the study, the results of which are described in the article, consist in developing new and modified methods and algorithms for solving the problem of clustering objects of economic analytics. The use of known algorithms for clustering formulations of economic indicators in order to determine the similarity of objects is complicated by the fact that the formulation of indicators are very short and the traditional indicators of terms occurrence (frequency) are inadequate. In addition, widespread occurrence of interviews and various forms of questionnaires in economic analysis implies the use of linguistic estimates. For example, "customer satisfaction level" indicator is difficult to quantify, so, instead of conventional points, fuzzy values such as “high”, “medium”, “low” are often used. As a result, it becomes feasible to use a fuzzy variant of the k-means method - the method of fuzzy k-means. Typically, the number of indicators in economic analysis is quite big, which makes it advisable to modify the algorithm on the basis of parallel execution. The study addresses the following issues: the k-means method is modified, it is adapted to the characteristics of the economic analytics objects; the methodology of data preprocessing for clustering is developed; new versions of clustering objects of economic analytics are developed, and experimental research of the effectiveness of the developed methods for large volumes of data is carried out.

Fcm-алгоритм, clustering, method of k-means, economic analysis, big data, fcm-algorithm, parallelization.

2017_ 1

Sections: Artificial intelligence

Subjects: Artificial intelligence.


© FRPC JSC 'RPA 'Mars', 2009-2018 The web-site runs on Joomla!