A Novel Trajectories Classification Approach for different types of ships using a Polynomial Function and ANFIS

摘要

In this paper, a Trajectories Classification Algorithm (TCA) is presented. The points of the tanker ship and fishing boat were collected in the same environment. Each trajectory of the tanker ship and fishing boat is partitioned to many segments to extract the features from each trajectory by using the polynomial function. The features extraction is used as input of the subtr active clustering to put the data in a group of clusters. Also it is used as an input of the neural network in ANFIS. The features extraction of each trajectory is represented with the membership functions and group of the Fuzzy If-then rules. The Initial Fuzzy Inference System (IFIS) is trained with artificial neural network to get the Final FIS. The performance of the TCA using a polynomial function and ANFIS is evaluated by different trajectories. The proposed TCA is tested using different trajectories obtaining a high classification accuracy 99.5%.