Upgrade to Pro — share decks privately, control downloads, hide ads and more …

incident identification platform based on mobile devices

Tasos
September 25, 2013

incident identification platform based on mobile devices

My presentation for the eRA8 conference. A prototype platform that identifies incidents by accumulating reports from mobile devices.

Tasos

September 25, 2013
Tweet

More Decks by Tasos

Other Decks in Research

Transcript

  1. Incident Identification Platform
    Based on Mobile devices
    Dissertation submitted
    for the Degree of Master of Science in Networking and Data Communications
    By
    ANASTASIOS LATSAS
    Supervisor
    DR. CHARALAMPOS Z. PATRIKAKIS

    View full-size slide

  2. Importance of Incident Detection

    View full-size slide

  3. Incident Detection Systems
    TraCS
    (Traffic and Criminal Software)

    View full-size slide

  4. Incident Detection Systems
    SARACEN
    (Socially Aware, collaboRative, scAlable Coding mEdia distributioN)

    View full-size slide

  5. Incident Detection Systems
    Delasoft Incident Locator Tool

    View full-size slide

  6. Motivation
    ● Existing systems are based on user input
    (assume location knowledge)
    ● Not "smart" enough
    ● Not open
    ● Not accessible

    View full-size slide

  7. Incident Identification Platform
    ● Detect incidents without assuming any location
    knowledge
    ● Detect both static and evolving incidents
    ● Web based platform (accessible)
    ● Mobile clients for Android™ devices
    ● Communication using open APIs and common
    protocols (HTTP)
    ● Open source

    View full-size slide

  8. Static Incident Detection
    1. calculate all possible incidents using
    the collected reports
    2. filter out too distant incidents
    3. calculate the average incident location
    4. calculate standard deviation of
    incidents
    5. determine safe point of location
    identification

    View full-size slide

  9. Evaluation Process
    ● collecting real data (using different
    mobile devices)
    ● collecting virtual data (using gmaps)
    ● randomizing collected data (location)
    ● randomizing collected data (run order)
    ● replaying scenarios
    ● plotting results

    View full-size slide

  10. Static Incidents - Results

    View full-size slide

  11. Tracking Algorithm
    ● 3 main phases
    ● filtering based on space and
    time criteria
    ● can detect evolving incidents
    ● adjusting existing position
    using two different
    algorithms
    ● scalable

    View full-size slide

  12. Tracking Algorithm - Phase 1

    View full-size slide

  13. Tracking Algorithm - Phase 2

    View full-size slide

  14. Tracking Algorithm - Phase 3

    View full-size slide

  15. Static vs Tracking Performance

    View full-size slide

  16. Future Work
    Expand available clients

    View full-size slide