Intelligent Engineering Systems through Artificial Neural Networks, Volume 20
43 Neuro-Fuzzy Systems Approach in Modeling Rule and Experience-Based Expectations
Download citation file:
Application of fuzzy sets within the field of decision making improves the efficiency of interactive systems, and it has, for the most part, consisted of “fuzzifications” of the classical theories of decision making. While decision making under condition of risk and uncertainty has been modeled by probabilistic decision theories and by the game theories, fuzzy decision theories attempt to deal with the fuzziness inherent in imprecise determination of preferences, constrains, and goals. Imprecision and uncertainty play a large role in the field of medicine, life and social sciences.
In this paper we propose topology and learning algorithm of neuro-fuzzy system for generation and correction of objects' membership function and respective generalized patterns. The results have been used in medical diagnostics system for determination of influence of chosen set of features (symptoms) over different classes (diseases).