Fragmentation of Hydrographic Big Data Into Subsets During Reduction Process

The article presented problems of fragmentation of hydrographic big data into smaller subsets during reduction process. Data reduction is a processing of reduce the value of the data set, in order to make them easier and more effective for the goals of the analysis. The main aim of authors is to create new reduction method. The article presented the first stage of this method - fragmentation of bathymetric data into subsets. It consists of two steps: initial division of the area into a grid of squares and clustering using artificial neural networks. In the first step maximum level of division of the grid will be founded and its size will be determined. In the second step of fragmentation each square will be divided into clusters using Kohonen network. The experiments were performed on test areas with different slope of the bottom. The results and conclusion were presented.