V

I remember reading an article back when GPS had first started appearing in cell phones on a large scale, and MIT had done a study to see if they could predict people's movement simply by using their cell phones as tracking devices. They restricted the study to the campus and the results turned out to be remarkably accurate. Anyways, I was jogging the Oracle's memory (surfing the internet that is), and came across the after effect of this study: Nathan Eagle leading a team of the Human Dynamics Group at MIT Media Labs creating something they coin "Reality Mining." Below you may find a brief synopsis from their website:

Research Design and Methodology
The Reality Mining research project has three aims: developing technology and algorithms for sensing, modeling, and changing human behavior. The sensing component is accomplished with mobile phone applications that capture data on users' location, proximity, communication and device usage behavior. The models are being generated using data from an ongoing study consisting of one hundred human subjects over the course of eight months and representing approximately 500,000 hours (~60 years) of human behavior. Seventy of the users are at the MIT Media Laboratory, while the remaining thirty are incoming students at the MIT Sloan business school adjacent to the laboratory. For the final aim, we develop algorithms for generating theoretically improved social network topologies and methods to implement these changes in a real social network through proximity-based notifications.

Summary

A smart environment is, by definition, context-aware: by combining inputs from multiple pervasive sensing devices, applications in the smart infrastructure should be able to intelligently deduce the intent or attributes of an individual without explicit manual input. Location is perhaps one of the earliest, and still most common, examples of such context. There are myriad examples of pervasive applications where the system uses the location of a mobile individual, or sometimes groups of individuals, to customize or adapt to the computing environment. A smart environment must be able to both determine and predict the location of an individual. In this chapter, we shall look at the various protocols, algorithms and technologies used for effective location prediction in smart environments. We shall first study the various research prototypes and techniques used to obtain the location information of a mobile user or device in a smart environment. We will then develop a unifying approach toward location prediction and finally concentrate on the problem of location prediction for both the geometric and symbolic group of location reporting technologies.