Smart Trace Crowdsourced Trace Similarity with Smartphones Costantinos

Smart. Trace Crowdsourced Trace Similarity with Smartphones Costantinos Costa, Christos Laoudias, Demetrios Zeinalipour-Yazti and Dimitrios Gunopulos University of Cyprus & University of Athens Goals and Contributions Problem: Find the K users moving more similarly to a Similarity Comparison ignore majority of noise query trajectory Q, in a Smartphone Network. • Privacy: User trajectories and User identities are not disclosed to the Query Processor. • Performance: a) In-situ data storage of trajectories (on smartphone flash) and b) Query Processing using a Top. K Query Processing Algorithm that uses Bound Scores* • Ubiquity: Our system works both outdoors (using GPS) and indoors (using WLAN Signal Strength) match – Flexible matching in time (ignore temporal noise) – Flexible matching in space (ignore spatial noise) The Smart. Trace Framework Performance Evaluation High Level Idea System Model Smartphone Energy: ↓ 81% Server Console Android-based Smartphone Implementation Smart. Trace Outdoors (GPS) “No Sharing” Policy Server • Ubuntu Linux • JDK 6, ~1500 LOC Smart. Trace Indoors (WLAN RSS) Client • HTC Desire smartphones • Android 2. 1 (Eclair) • Google Map API • ~2500 LOC, ~250 lines XML • 510 KB installation package APK • Runs on Dalvik VM (future: native C with Android NDK) Smart. Trace Client GUI • Query devices by example • Plot and iterate through the responses using a variety of presentation styles • Configure parameters (e. g. K) • Control privacy settings • Online/Offline modes for recorded scenario playback • GPS/Wi. Fi modes Indoor scenario at KIOS Research Center • 560 m 2 area, 3 APs, 1 Query (Q) RSS trajectory • 4 other (T 1 -T 4) RSS trajectories, top-2 search • T 2 and T 3 correctly identified as top-2 answers "Disclosure-free GPS Trace Search in Smartphone Networks", D. Zeinalipour-Yazti, C. Laoudias, M. I. Andreou, D. Gunopulos, The 12 th IEEE International Conference on Mobile Data Management (MDM'11), IEEE Computer Society, Lulea, Sweden, June 6 -9, 2011 (accepted) [ Acceptance Rate: 25% (22/88) ] "Smart. Trace: Finding Similar Trajectories in Smartphone Networks without Disclosing the Traces", C. Costas, C. Laoudias, D. Zeinalipour-Yazti, D. Gunopulos, The 27 th IEEE International Conference on Data Engineering (ICDE'11) (Demo Paper), April 11 -16, Hannover, Germany, 2011, accepted. "Crowdsourced Trace Similarity with Smartphones", D. Zeinalipour-Yazti, C. Laoudias, C. Costa, M. Vlachos, M. I. Andreou, D. Gunopulos, IEEE Transactions on Knowledge and Data Engineering, accepted, January 2012. Data Management Systems Laboratory Web: http: //smarttrace. cs. ucy. ac. cy/ Email: smarttrace@cs. ucy. ac. cy Acknowledgements: This work was supported in part the third author’s Startup Grant, EU’s FP 6 Marie Curie TOK “SEARCHi. N” project, EU’s FP 7 CONET project and EU’s FP 7 “Sem. Sor. Grid 4 Env” and “MODAP” projects.