Russian Federation
Approaches to creating artificial intelligence systems based on expert systems, genetic algorithms, game theory, and neural networks are considered; knowledge representation tools in artificial intelligence systems are based on symbolic patterns, sets of standard operations and procedures for finding solutions. The process of searching for solutions in artificial intelligence systems based on logical inference systems, which have the form of a semantic network with elements of conjunction and disjunction, is considered in detail. The features of a semantic network, which is an arbitrary graph (AND / OR network) and implements two methods of logical inference – forward and reverse wave methods are considered. An example of an artificial intelligence model in the form of a fuzzy expert system containing a knowledge base consisting of fuzzy production rules is considered in detail. Said artificial intelligence model is used to assess the risk of an emergency occurring when the water level rises during a flood. The considered fuzzy expert system, implemented in the form of a computer program, which makes it possible to assess flood risk in conditions of incomplete and inaccurate initial data.
artificial intelligence, neural networks, genetic algorithms, game theory, expert systems, knowledge representation, logical inference system, semantic networks, fuzzy sets
1. Herman O.V. Introduction to the theory of expert systems and knowledge processing. Minsk: BSU, 2005.
2. Varlamov O.O. The Mivar approach as the basis for a qualitative transition to a new level in the field of artificial intelligence // Radio industry. 2017. № 4.
3. Varlamov O.O. Evolutionary databases and knowledge for adaptive synthesis of intelligent systems. Mivar information space. Moscow: Radio and Communications, 2002.
4. Khadiev A.M. Development and practical implementation of a mivar logical inference machine // Radio industry. 2015. № 3.
5. Pegat A. Fuzzy modeling and control. Moscow: BINOM, 2013.
6. Mamdani E.H. Application of fuzzy algorithms // Fuzzy Sets and Systems // 2009. Vol. 2. № 4.
7. Labinsky A.Y. Modeling of the fuzzy inference system // Natural and anthropogenic risks. 2016. № 2.
8. Flondor P. An example a fuzzy system // Kybernetics. 2017. Vol. 6. № 1.
9. Pavlak Z. Roufh sets and fuzzy sets // Fuzzy Sets and Systems. 2018. Vol. 3. № 1.
10. Labinsky A.Y. On the issue of developing expert systems // Supervisory activities and forensic examination in the security system. 2022. № 2.
11. D. McConnell. Fundamentals of modern algorithms. M.: Technosphere,, 2004.
12. Labinsky A.Y. Promising areas of computer modeling of complex processes and systems: monograph. SPb.: S.-Petersburg uni. of SFS of EMERCOM of Russia, 2017.
