OPTIMIZED THE MARITIME BIG DATA K-MEANS CLUSTERING BASED ON THE MAPREDUCE MODEL

Abstract

With the development of information technology, the maritime big data is an increasing trend of applications being expected to deal with big data that usually do not fit in the main memory of an analyzing big data is a challenging problem today. For such data intensive application, the maritime big data, the “MapReduce” framework has recently attracted considerable attention and started to be investigated for analysis which can handle petabyte of AIS data for millions of vessels. MapReduce is a programming model that allows easy development of scalable parallel applications to process big data on large clusters of commodity machines. This study, a standard clustering algorithm called K-means is based on the MapReduce model to be processed the marine traffic data in southern region, Viet Nam. According to the main results obtained, we concerned with making inference or prediction the clustering data which were collected and were shown the dashboard of maritime vessels traffic, including the scale, the trend of change and the spatial distribution situation.