Mobile sensing has been gaining ground due to the increasing capabilities of mobileand personal devices that are carried around by citizens, giving access to a large variety of dataand services based on the way humans interact. Mobile sensing brings several advantages interms of the richness of available data, particularly for human activity recognition. Nevertheless,the infrastructure required to support large-scale mobile sensing requires an interoperable design,which is still hard to achieve today. This review paper contributes to raising awareness of challengesfaced today by mobile sensing platforms that perform learning and behavior inference with respect tohuman routines: how current solutions perform activity recognition, which classification models theyconsider, and which types of behavior inferences can be seamlessly provided. The paper providesa set of guidelines that contribute to a better functional design of mobile sensing infrastructures,keeping scalability as well as interoperability in mind.

--

Mobile sensing,Cloud–edge computing,Human behavior,Human behavior inference,Activity recognition,Context awareness