Open AccessIntelligent tools for analyzing NON-factors of the project environment
Author(s) -
Olga V. Bulygina,
Aleksandr Emel'yanov,
Olga Ivanova
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1862/1/012017
Subject(s) - computer science , fuzzy logic , fuzzy inference system , identification (biology) , data mining , classifier (uml) , inference , risk analysis (engineering) , artificial neural network , quality (philosophy) , machine learning , artificial intelligence , adaptive neuro fuzzy inference system , fuzzy control system , medicine , philosophy , botany , epistemology , biology
The implementation of complex innovative projects to create high-tech products is usually associated with a high level of uncertainty, which is due to the lack of “quality” (accurate, complete, reliable, consistent, etc.) data on their internal and external environment. In this regard, special attention must be paid to the stage of project planning, which takes into account the results of identification and analysis of risk situations that may arise during the project implementation. In conditions of information uncertainty, it is advisable to use data mining methods to solve these problems. So, to identify the factors of the internal and external environment, which can negatively affect the project, it is proposed to use a neural fuzzy classifier. The analysis of the identified factors must be carried out taking into account the possibility of the simultaneous occurrence of several risks, i.e. the appearance of a systemic effect, which can be assessed using the Hartley emergence coefficient. In turn, the obtained values of this indicator determine the choice of analysis tools: in the case of a low value, it is proposed to use fuzzy logical inference according to the Mamdani algorithm, otherwise - fuzzy pyramidal networks.