Narrow Results

This paper presents a computational technique for modeling the Earth's magnetic field using the framework of Adaptive Non-Additive Fuzzy System (ANAFS). The defuzzified output constructed from both the premise and consequent parts of the GFM rules takes the form of Choquet integral. Premise and consequent parameters of non-additive fuzzy model are then updated for each online data based on the estimation error to make the adaptive system. The resulting model is applied on the real data, i.e. H-component of the magnetic field obtained from the magnetometer and the training and prediction results are found to be better and can be used for modeling such a complex system whose mathematical or physical modeling is very difficult to obtain. Thus, this work makes an important contribution to the field of fuzzy modeling of real life complex systems.