ABSTRACT
This chapter explores features and concepts, and provides guidelines on the role and applicability of smart data captured in a non-intrusive way, in the inference and contextualization of human behavior and interaction. It deals with a brief introduction to concepts concerning modeling of human interaction. The chapter addresses concepts such as the need to redefine aspects of human interaction detection, such as proximity modeling, in a way that stems from an interdisciplinary perspective, providing examples on how such proposal can be achieved. Smart data captured via pervasive, mobile sensing technology is relied upon to model different aspects of human activities and human behavior. The chapter also deals with interaction inference and interaction contextualization: classification models that best suit the inference of behavior via smart data. In regular daily routines, several factors affect interaction between people. One of the most relevant factors is the way that people define and perceive the surrounding space.
