Combining Global Model and Local Adaptive Neuro-Fuzzy Network

摘要

This paper is concerned with a method for combining global model with local adaptive neuro-fuzzy network. The underlying principle of this approach is to consider a two- step development. First, we construct a standard linear regression as global model which could be treated as a preliminary design capturing the linear part of the data. Next, all modeling discrepancies are compensated by a collection of rules that become attached to the regions of the input space in which the error becomes localized. The incremented neuro-fuzzy network is constructed by building a collection of information granules through some specialized fuzzy clustering, called context-based fuzzy c-means that is guided by the distribution of error of the linear part of its development. The experimental results reveal that the proposed method shows a good approximation and generalization capability in comparison with the previous works.