Social Signal Processing: Detecting Human Interactions using Wireless Sensor Networks

In this paper we address the problem of capturing and processing certain spatiotemporal, social characteristics of human interactions with the use of Wireless Sensor Networks. Using TelosB motes, we basically monitor the binary proximity within a group of people. The collected data give an insight of how people interact with each other (how often, for how much time, in which room) and provide a novel tool (which can be further enhanced) to study (quantitatively, in an automated manner) human social networks.