GroupUs: Smartphone Proximity Data and Human Interaction Type Mining
ISWC '11 Proceedings of the 2011 15th Annual International Symposium on Wearable Computers
Social fMRI: Investigating and shaping social mechanisms in the real world
Pervasive and Mobile Computing
Exploring social context with the wireless rope
OTM'06 Proceedings of the 2006 international conference on On the Move to Meaningful Internet Systems: AWeSOMe, CAMS, COMINF, IS, KSinBIT, MIOS-CIAO, MONET - Volume Part I
Hi-index | 0.00 |
The increasing mobile technology raises a new paradigm of people-centric sensing using today's smartphones. Towards this paradigm, we present "CoSoBlue", a novel framework for Bluetooth based social sensing. In CoSoBlue, we propose novel Bluetooth semantic and statistical features, in addition to count and similarity features, and apply these discriminative features to infer context and compute sociability. We evaluate CoSoBlue on two Bluetooth datasets: (1) the longitudinal MIT friend-and-family dataset with 9+ millions records, and (2) a new 2-month dataset with ground-truth labels collected using our own developed Android app. Our primilinary experiments show CoSoBlue's efficacy on Bluetooth based social and context sensing.