SmartTrace 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 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)

System Model

– –

Similarity Comparison

ignore majority of noise match match

Flexible matching in time (ignore temporal noise) Flexible matching in space (ignore spatial noise)

The SmartTrace Framework High Level Idea Performance Evaluation Smartphone Energy: ↓ 81% Server Console

SmartTrace Outdoors (GPS)

Android-based Smartphone Implementation “No Sharing” Policy

SmartTrace Indoors (WLAN RSS)

Server

• Ubuntu Linux • JDK 6, ~1500 LOC

Client

• HTC Desire smartphones • Android 2.1 (Eclair) • Google Map API • ~2500 LOC, ~250 lines XML • 510KB installation package APK • Runs on Dalvik VM (future: native C with Android NDK)

SmartTrace 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/WiFi modes

Indoor scenario at KIOS Research Center

• 560m 2 area, 3 APs, 1 Query (Q) RSS trajectory • 4 other (T1-T4) RSS trajectories, top-2 search •

T2 and T3 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 12th IEEE International Conference on Mobile Data Management (MDM'11), IEEE Computer Society, Lulea, Sweden, June 6-9, 2011 (accepted) [ Acceptance Rate: 25% (22/88) ] "SmartTrace: Finding Similar Trajectories in Smartphone Networks without Disclosing the Traces", C. Costas, C. Laoudias, D. Zeinalipour-Yazti, D. Gunopulos, The 27th 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: [email protected]

Acknowledgements: This work was supported in part the third author’s Startup Grant, EU’s FP6 Marie Curie TOK “SEARCHiN” project, EU’s FP7 CONET project and EU’s FP7 “SemSorGrid4Env” and “MODAP” projects.