Abstract
Recent years have witnessed a huge progress in the automatic identification of individual primitives of human behavior, such as activities or locations. However, the complex nature of human behavior demands more abstract contextual information for its analysis. This work presents an ontology-based method that combines low-level primitives of behavior, namely activity, locations and emotions, unprecedented to date, to intelligently derive more meaningful high-level context information. The paper contributes with a new open ontology describing both low-level and high-level context information, as well as their relationships. Furthermore, a framework building on the developed ontology and reasoning models is presented and evaluated. The proposed method proves to be robust while identifying high-level contexts even in the event of erroneously-detected low-level contexts. Despite reasonable inference times being obtained for a relevant set of users and instances, additional work is required to scale to long-term scenarios with a large number of users.
Highlights
A revolutionary wave of smart systems has recently emerged to enable the automatic identification of human behavior
It is possible that the unclassified high-level context does not belong to any of the known classes described in the Mining Minds Context Ontology
The proposed Mining Minds Context Ontology has been evaluated to determine how robust the identification of high-level contexts can be in the event of having erroneously detected low-level contexts
Summary
A revolutionary wave of smart systems has recently emerged to enable the automatic identification of human behavior. In knowledge-driven approaches, ontologies and rules are utilized to model and infer different contexts [9,10,11] Both data-driven and knowledge-driven techniques are further combined in hybrid methods to determine various components of human behavior [12,13]. Most systems are only capable of identifying activities, locations or emotions, but generally not a combination of them While these primitives could be considered in isolation for a preliminary analysis of a person’s behavior, their appropriate combination can lead to more meaningful and richer expressions of context for behavior understanding. This work presents an ontology-based method to intelligently combine cross-domain behavior primitives, referred to as low-level contexts, in order to infer more abstract human context representations, hereafter high-level contexts.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
