Ann-Based Multiple Dimension Predictor for Ship Route Prediction

Abstract

This paper presents a new multiple dimension prediction model based on the diagonal recurrent neural networks (PDRNN) with a combined learning algorithm. This method can be used to predict not only values, but also some points in the multi-dimension space. And also its applications in data mining will be discussed in the paper. Some analysis results show the significant improvement to ship route prediction using the PDRNN model in database of geographic information system (GIS).