Open AccessAPPLICATION OF NEURO-FUZZY MODELS IN THE SYSTEM FOR ASSESSING THE PROFESSIONAL ABILITIES OF APPLICANTS
Author(s) -
Yuliia Riabchun,
Roman Skrypak,
Olena Riabchun,
Iryna Aznaurian
Publication year - 2021
Publication title -
upravlìnnâ rozvitkom skladnih sistem
Language(s) - English
Resource type - Journals
eISSN - 2412-9933
pISSN - 2219-5300
DOI - 10.32347/2412-9933.2021.45.107-113
Subject(s) - computer science , field (mathematics) , neuro fuzzy , fuzzy logic , decision support system , object (grammar) , process (computing) , identification (biology) , knowledge base , artificial intelligence , expert system , knowledge management , machine learning , management science , fuzzy control system , engineering , mathematics , botany , pure mathematics , biology , operating system
The work is devoted to solving a problem of assessing the professional abilities of entrants to higher education institutions. The subject of the study is the process of automatic support of entrants' decisions in conditions of fuzzy uncertainty caused by the need to communicate "online". The object of the study is a supporting means of the decisions of applicants to choose the direction of study "online". The main purpose of the work is to substantiate the technology of decision support for choosing a direction of study using an infocommunication system, the work of which has based on a neuro-fuzzy output system. Particular attention has paid to overcoming the problems that accompany the creation of infocommunication systems, which has designed to support decision-making on the choice of field of study in conditions of unclear uncertainty caused by the limitation of offline communication. The article presents the results of a study of the criteria for admission to higher education institutions in different countries. The structural model of the Specialized Intellectual System of Identification of Abilities of Entrants has offered. The system has designed to support the decision to choose a specialty of higher education institution. It has shown that to substantiate the recommendation conclusion based on the results of professional game; it is advisable to use a fuzzy neural network Takagi-Sugeno-Kanga. To solve the problem of substantiation of expert decisions at the stage of formation of a priori base of rules of fuzzy knowledge base of fuzzy inference system, it is expedient to use Mamdani model, which operates with linguistic variables and fuzzy sets.