Fuzzy logic-based and neural network-based reasoning with application to blood pressure management

Two distinctive approaches to the implementation of approximate reasoning in rule-based fuzzy decision-making and control systems are presented. While the first approach, based on possibility theory, bears some resemblance to a traditional event-driven inference system with the incorporation of fuzzy concepts, the second scheme, based on the technique of neural networks, represents a substantial departure from the traditional one and shows some promise in dealing with these fundamental issues. To demonstrate the applicability of the proposed approaches, a problem of multivariable fuzzy management of blood pressure has been studied using the simulation method