Data Fusion of Diverse Data Sources: Enrich Spatial Data Knowledge Using HINs.

A range of GPS, social network and transportation applications have been developed, targetting to improve the quality of life of the user. Furthermore, the development of smart devices allows the user to use the applications any time, while also providing the location of the user. As a result, a range of datasets of different nature has been created, describing events that are related to the location. Regardless the great volume of these datasets, their different nature (i.e. schema) deters the analysts from combining the datasets, losing insights of a location that could be important. In this study, we propose a framework that targets to achieve a knowledge fusion by connecting datasets of different nature. In order to achieve the fusion, we initially transform the datasets into graph bases. Afterwards, we import the graph bases into a knowledge base represented as Heterogeneous Information Network (HIN), using the location as the main node type that connects the datasets. This knowledge base provides to the user a bigger picture of the real world, is able to connect information across domains that initially seemed unconnected and provides a semantically rich data basis that is useful to answer many types of questions.