Research On Predictive Capability Of A New Neuro-Fuzzy Inference System-ANFIS On The Tonnage Supply And Deliveries Of World Bulk Fleet

Shipping market is changing dramatically, and predictions of freight volume, transportation capacity, and correspondent freight rate are noticed world-widely. By embedding the fuzzy inference system into the framework of adaptive networks, ANFIS (adaptive-network-based fuzzy inference system), however, can construct an input-output mapping based on both human knowledge (in the form of fuzzy if-then rules) and stipulated input-output data pairs. A survey of the principle of ANFIS is presented including the architectures and hybrid learning rules of adaptive networks and ANFIS. Besides, we demonstrate how to apply the Stone-Weierstrass theorem to ANFIS with simplified fuzzy if-then rules and how the radial basis function network relate to this kind of simplified ANFIS. In final, using Fuzzy Logic Toolbox of MATLAB, we establish a prediction modeling of the tonnage supply and deliveries of world bulk fleet based on ANFIS. In terms of the result of simulation, the modeling is very good.