TM-DBSCAN: A Spatio-Temporal Memory Density Clustering for Battle Space Object Aggregation

The aggregation of Battle Space Objects (BSOs) within a situational picture is the combination of BSOs into units, i.e. higher organizational entities. Aggregation is part of situational assessment. As has been shown by [1], aggregation can be achieved by clustering, in particular Density-Based Spatial Clustering of Applications with Noise (DBSCAN). In this paper, we present a significant improvement of the DBSCAN approach, namely Temporal Memory (TM) DBSCAN: the situational picture is enhanced with a temporal memory (TM) so that previous situations can be taken into account for clustering the current situational picture. Thereby, it becomes possible to “remember” previous but still valid divisions of BSOs as well as to recognize outdated BSO representations that should be ignored. We describe the TM-DBSCAN algorithm in detail and explain its effects on aggregation. This paper was originally presented at the NATO Science and Technology Organization Symposium (ICMCIS) organized by the Information Systems Technology (IST) Panel, IST-200 IST-200 RSY — the ICMCIS, held in Skopje, North Macedonia, 16–17 May 2023.