Location: Dept. of Computer Science, University of Pittsburgh, Pittsburgh, PA USA.
Smartphone devices have emerged as powerful computational platforms equipped with multitude of sensors that are capable of generating vast amounts of data (geo-location, audio, video, etc.) Collections of such devices connected to the Internet yield Smartphone Networks, which can be utilized for opportunistic and participatory sensing applications in intelligent transportation systems, social networking applications, city planning and others. The uptake of applications in this domain, is currently severely hampered by the fact that these devices have: i) a limited energy budget (i.e., smartphone devices still operate on batteries), ii) limited connectivity (i.e., not all regions offer unlimited Internet connectivity at the same cost); and iii) high privacy constraints (i.e., these devices might reveal the identity and habits of their custodians). In this talk I will present SmartTrace, a powerful framework for finding similar trajectories in a smartphone network, without disclosing the traces of participating users. Our framework, coined SmartTrace, quickly answers queries of the form: “Report the users that move more similar to Q, where Q is some query trace.” SmartTrace relies on an in-situ data storage model, where geo-location data is recorded locally on smartphones for both performance and data-disclosure reasons. SmartTrace then deploys an efficient top-K query-processing algorithm that exploits distributed trajectory similarity measures, resilient to spatial and temporal noise, in order to derive the most relevant answers to Q quickly and efficiently. We assess our propositions with realistic and real workloads from Microsoft Research Asia and other sources. Our study reveals that SmartTrace computes the desired results with 74% less energy consumption and 13% faster than its centralized and decentralized counterparts. My talk will be succeeded by a summary of related research efforts, namely SmartNet, an innovative programming cloud for smartphone networks; and SmartOpt, a multi-objective query optimizer that enables efficient content searches in smartphone networks.