URBAN ANALYSIS FOR THE XXI CENTURY: USING PERVASIVE INFRASTRUCTURES FOR MODELING URBAN DYNAMICS

  • 289 views
Uploaded on

 

More in: Technology , Real Estate
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
289
On Slideshare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
7
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide

Transcript

  • 1. Urban Analysis for the XXI Century: Using Pervasive Infrastructures for  Modeling Urban Dynamics Enrique Frias‐Martinez Telefonica Research, Madrid, Spain efm@tid.es
  • 2. Índice• Introducción• Pervasive Infrastructure• Hotspot Detection• Land Use Classification• Commuting Patterns• Conclusiones
  • 3. Introducción
  • 4. Introducción “The 19th century was a century of empires, the 20th century was a century of nation states, the 21st century will be a century of cities” Wellington E. Webb, former mayor of Denver
  • 5. Introducción Digital Footprints  For the first time in human history, we have  access to large‐scale human behavioral  data at varying levels of spatial and  temporal granularities
  • 6. Pervasive Infrastructure
  • 7. Pervasive Infrastructure Ce ll Phone N e t w ork Cell Phone networks are built using Base Transceiver Stations (BTS). Each BTS will be characterized by a feature vector that describes the calling behavior area. 1
  • 8. Pervasive Infrastructure CDR da t a se t Our Dataset • 1 month of phone call interactions. • 1100 Base Transceiver Stations. • Each CDR contains: › phoneSource | phoneDestiny | btsSource | btsDestiny | DD/MM/YYYY | hh:mm:ss | d • Phone number are encrypted to anonymize user identities. Traffic M b o ility alg rith s o m Subscribers sample 2233445566|15/02/ 2008| 2233445567|15/01/ 2008| 2233445568|15/07/ 2008|25/07/2010 2233445569|15/09/ 2008| Cell catalogue 1
  • 9. Hotspot Detection
  • 10. Hotspot Detection• What is a hotspot? – In this context a hotspot is understood as a  concentration of people (or activities) over a  specific period of time and a specific geographic  area.• Interesting for urban planning, emergency relief,  public health, context‐aware services• Approach – Greedy clustering algorithm seeded with local maxima – Hotspots based on activity or on number of people.
  • 11. Hotspot Detection• Data: – CDR from Mexico for a period of 4 months. • Output:  – At a national level: cities. At an urban level: city  blocks. Evolution of dense areas for urban  planning.
  • 12. Hotspot Detection
  • 13. Hotspot Detection Weekdays Morning Weekdays Afternoon Weekdays Evening Weekdays Night
  • 14. Land Use Classification
  • 15. Land Use Classification• Aggregate and clean data for each BTS. – Obtain signature of each BTS (total number of  calls every hour: 24 hours average week day and  24 hours average weekend day) – BTS based Voronoi gives the tessellation for land  classification. – Automatic Identification of clusters with similar  behaviour that maximize the compactness of the  groups identified.
  • 16. Land Use ClassificationR e p r e s e n t a t io n s Activity signature vectors are built: each component contains the number of managed calls by the BTS in 5-minute intervals. 1
  • 17. Land Use Classification• Industrial Parks / Office Areas
  • 18. Land Use Classification• Commercial ‐ Residential
  • 19. Land Use Classification• Night Life Areas
  • 20. Land Use Classification• Weekend Activities
  • 21. Land Use Classification• Residential
  • 22. Commuting Patterns
  • 23. Commuting Patterns
  • 24. Commuting Patterns
  • 25. Conclusions
  • 26. Conclusiones• Traditional approaches are costly and based on questionnaires.• Urban Dynamics can be modelled using pervasive infrastructures• Reduction in cost, increment of the flexibility• Possibility of real‐time modelling