METHODS OF SELF-ADAPTATION OF SOFTWARE SYSTEMS BASED ON MACHINE LEARNING AND INTELLECTUAL DATA ANALYSIS 

Aleksandr S. Bozhday, Doctor of technical sciences, associate professor, professor of the sub-department of computer aided design, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: bozhday@yandex.ru
Yuliya I. Evseeva, Candidate of technical sciences, associate professor of the sub-department of computer aided design, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: shymoda@mail.ru
Aleksey A. Gudkov, Candidate of technical sciences, associate professor, associate professor of the sub-department of computer aided design, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: alexei-ag@yandex.ru 

004.4 

10.21685/2227-8486-2021-2-10 

Background. The issues of creating a universal technology for self-adaptation of applied software systems, as well as the mathematical apparatus underlying such a technology, are being studied.
Materials and methods. Methods of data mining and machine learning are considered as methods for creating a universal technology of self-adaptation.
Results and conclusions. Methods of self-adaptation of software systems are proposed, a distinctive feature of which is the identification of this knowledge about the subject area of the program that was unknown at the development stage. The proposed methods will make it possible to create software with an extended life cycle, which is distinguished by greater reliability and performance, as well as lower resource cost for development and maintenance. 

self-adaptive software, data mining, machine learning 

Bozday A.S., Evseeva Yu.I., Gudkov A.A. Methods of self-adaptation of software systems based on machine learning and intellectual data analysis. Modeli, sistemy, seti v ekonomike, tekhnike, prirode i obshchestve = Models, systems, networks in economics, technology, nature and society . 2021;2:144–152. (In Russ.). doi:10.21685/2227-8486- 2021-2-10