ANET: Interest-Aware Delivery for Future Mobile Social Networks: A TRACE-driven Approach

University Of Florida, Gainesville FL

Investigators

Abstract

This project introduces a novel communication paradigm, called profile-cast, to support new classes of interest-aware services in mobile networks. Unlike unicast, multicast or directory-based paradigms, profile-cast infers user interest using implicit behavioral profiling via a self-monitoring and mining technique. Privacy preserving design is a high priority. A spatio-temporal representation is introduced to capture users' interest within a behavioral-space. Users identify similarity of interest based on their position in such space. The design philosophy begins by intensive analysis of measurements from the target context that drives the modeling and protocol design through a systematic framework, called TRACE. Components of TRACE include: 1. Tracing and monitoring of behavior, 2. Representing and Analyzing the data, 3. Characterizing behavioral profiles using data mining techniques, and 4. designing mobile user behavioral models and efficient protocols for future mobile societies. This project tackles the design and development of profile-cast and TRACE, and quantifying the extent to which they are privacy-preserving, scalable, efficient, flexible and robust. The broader impacts of this research include enabling new classes of socially valuable service, from navigation of mobile societies, to emergency alert systems. The mobility models developed will provide novel and key elements for the success of future mobile networks. The project includes education plan to involve students at the university in using profile-cast devices and to integrate the research into curricula both at the University of Florida, and into K-12 schools in north-central Florida.