In this paper, we present a multilevel fuzzy inference model for predicting the risk of type 2 diabetes. We have designed a system for predicting this risk by taking into account various factors such as physical, behavioral, and environmental parameters related to the investigated patient and thus facilitate experts to diagnose the risk of diabetes. The important risk parameters of type 2 diabetes are identified based on the literature and the recommendations of experts. The parameters are scaled and fuzzified on their own universe and, based on the experts’ recommendation, fuzzy inference subsystems are created with 3–4 related risk parameters to calculate the risk level. These sub-systems are then arranged into Mamdani-type inference systems so that the system calculates an aggregated risk level. The overview of the large number of diverse types of risk factors, which may be difficult for specialists and doctors, is facilitated by the proposed system.

Hemodialysis machines have an important role in the support and maintenance of life functions, wherein the strict control of peristaltic pumps is a serious need. The current paper targets to present soft computing methods, which can be applied for the peristaltic pumpcontrol problem, demonstrating their applicability on real systems as well. The performances of these controllers are compared with those of the classical PID controller, in order to highlight the advantages and applicability of these modern control strategies over classical controllers. An adaptive fuzzy-logic system and an adaptive neuro-fuzzy inference system were designed to fulfill the proposed control criteria. The requirements for the sought controller were formulated in three aspects: to be fast, to eliminate the residual error, and to be insensitive to disturbances. The designed controllers were compared and the one demonstrating the best performance has been tested on a real system as well.

In this paper a fuzzy inference system in fuzzy toolbox package in MATLAB using two “fuzzified” control parameters for the fixed point transformation-based adaptive controller is applied for the strongly dynamic non-linear system, the “van der Pol Oscillator”. The paper presents a comparison of the operation of the classical controller and a novel one combined with fuzzy inference system.