PROJECT TITLE :

Density-Based Place Clustering Using Geo-Social Network Data - 2018

ABSTRACT:

Spatial clustering deals with the unsupervised grouping of places into clusters and finds necessary applications in urban coming up with and promoting. Current spatial clustering models disregard info concerning the individuals and the time who and when are connected to the clustered places. In this Project, we have a tendency to show how the density-based clustering paradigm can be extended to use on places that are visited by users of a geo-social network. Our model considers spatio-temporal data and the social relationships between users who visit the clustered places. When formally defining the model and the gap measure it relies on, we tend to offer alternatives to our model and the gap measure. We evaluate the effectiveness of our model via a case study on real information; in addition, we design two quantitative measures, referred to as social entropy and community score, to evaluate the standard of the discovered clusters. The results show that temporal-geo-social clusters have special properties and cannot be found by applying straightforward spatial clustering approaches and alternative alternatives.