Neuro-fuzzy algorithm for clustering multidimensional objects in conditions of incomplete data

Abstract

The paper is considered development of fuzzy expert system model for identifying faults in complex systems using data mining methods based on searching for hidden patterns in databases. The use of neural network technologies makes it possible to detect nonlinear dependencies of input and output data, improve the quality of an objective assessment of the state of complex technical objects, which ultimately will reduce the number of emergency situations during operation. A method is proposed for identifying the optimal number of fuzzy clusters in the space of training examples and determining, on their basis, the parameters of the membership functions for the input variables and inference results. Considered a neuro-fuzzy algorithm for clustering multidimensional objects in conditions of incompleteness and fuzzy initial information.