Fuzzy Inference Systems for Multistage Patern Recognition - Application to Medical Diagnosis

M.W. Kurzynski (Poland)


Multistage recognition, fuzzy systems, medical application


The paper deals with the fuzzy inference systems for multistage recognition based on a decision tree scheme. For the given learning set two conceptually different fuzzy methods are presented and discussed. The first method which uses the fuzzy rule based technique is developed to the multistage approach known Mamdani inference engine with rules generated from the learning set. In the second approach we first construct fuzzy relation between decision set and feature space which next is used to decision making. Both methods were practically applied to the computer-aided medical diagnosis of acute renal failure and results of comparative experimental analysis are also given.

Important Links:

Go Back