Architecture of hybrid generalized additive neuro-fuzzy system in modelling technological process

In this paper we propose architecture of hybrid generalized additive neuro-fuzzy system. Such system is hybrid of the neuro-fuzzy system by Wang-Mendel and the generalized additive models by Hastie-Tibshirani. Proposed hybrid generalized additive neuro-fuzzy system can be used for modelling technological process, identification and prediction of nonlinear nonstationary signal. The results of experimental modelling confirm the effectiveness of the proposed approach in comparison with conventional neuro-fuzzy systems.