EvolvingClusters: Online Discovery of Group Patterns in Enriched Maritime Data
George S. Theodoropoulos, Andreas Tritsarolis, Yannis Theodoridis · Lecture notes in computer science · 2020
In this paper, we propose a novel unified online group pattern mining algorithm, EvolvingClusters , that aims to enrich geospatial data through the mapping of their group behaviour. Specifically, EvolvingClusters is used to discover collective movement behaviour (like flocks and convoys) by monitoring the activity of multiple clusters through time and space. We evaluate the aforementioned algorithm using a real-world marine traffic dataset consisting of vessels’ movement in Brest Bay, France. Our study demonstrates the efficiency and effectiveness of the proposed algorithm as well as its value towards a semantic enrichment tool that can be used to observe and categorize the behaviour of multiple moving objects in real time.