Nf-gvein: Adaptive Neuro-fuzzy Based Modelling of Flow Field inside Graft- To-vein Connection under Steady Flow Conditions

This paper presents the application of the adaptive neuro fuzzy inference system (ANFIS) to a model of the flow field inside an in vitro arteriovenous (AV) graft-to-vein connection implanted to the kidney patients. A model based on ANFIS is proposed. Its relevant steps oriented to find the optimal AV graft angle are given. The advantage of this neuro-fuzzy hybrid approach is that it does not require the model structure to be known a priori, in contrast to most of the modeling techniques. A case study with real experimental data was carried out. The model parameters and the fully developed turbulent velocity profile are defined. The model was optimized by means of selection of the algorithm among 34 ANFIS algorithms by terms of minimal error. The optimal neural network structure was determined. The optimal AV graft angle closest to the fully developed turbulent flow was obtained. The simulation results showed that this model is feasible for forecasting of the optimal AV graft angle of the flow field series inside AV graft-to-vein connection. The results are highly promising, and a comparative analysis suggests that the proposed modeling approach outperforms artificial neural networks and other traditional time series models.