Increasing the Accuracy of the Approximation of Microprocessor Fuzzy Solvers Supporting Membership Functions of an Arbitrary Type
Alexei Evgenievich VASSILIEV · Journal of Communications Technology and Electronics · 2021
Abstract A new approach to the development of microprocessor systems for fuzzy information processing using membership functions of an arbitrary type is proposed, which consists in supplementing the main fuzzy solver with a set of correcting fuzzy nodes. It is shown that the application of the approach makes it possible to reduce the complexity of the description and the complexity of the technical implementation while increasing the accuracy of fuzzy computations. Examples of using the approach in practical tasks are given.