Your SlideShare is downloading. ×
0
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×
Saving this for later? Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime – even offline.
Text the download link to your phone
Standard text messaging rates apply

Spatio-Temporal Data Mining and Classification of Ships' Trajectories

2,062

Published on

Laurent Etienne's presentation at Geomatics Atlantic 2012 (www.geomaticsatlantic.com) in Halifax, June 2012. More session details at http://lanyrd.com/2012/geomaticsatlantic2012/stbgx/ .

Laurent Etienne's presentation at Geomatics Atlantic 2012 (www.geomaticsatlantic.com) in Halifax, June 2012. More session details at http://lanyrd.com/2012/geomaticsatlantic2012/stbgx/ .

Published in: Education, Technology
0 Comments
3 Likes
Statistics
Notes
  • Be the first to comment

No Downloads
Views
Total Views
2,062
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
0
Comments
0
Likes
3
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. Spatio-Temporal Data Mining andClassification of Ships Trajectories Laurent ETIENNE PhD in geomatics French Naval Academy Research Institute Geographic Information Systems Group Maritime Activity and Risk Investigation NetworkDepartment of Industrial Engineering, Dalhousie University laurent.etienne@ecole-navale.fr Halifax, June 2012
  • 2. Introduction Movement is an important part of life Mobile objects tracking systems Large spatio-temporal databases Knowledge Discovery from movement Real time analysis Decision support systems Different kind of mobile objects Different mobility data interest  Ecology, Sociology, Transports, Intelligence... 2
  • 3. Research interests Knowledge discovery from moving objects databases (KDD) Algorithms for spatial data processing and modelling Advanced visualisation techniques for spatial data 3
  • 4. Process overview 4
  • 5. Spatio-temporal data mining Extract knowledge from a data warehouse  Cluster groups of trajectories  Main route followed by most trajectories of this group  Main trajectory  Spatial spreading (channel)  Temporal stretching (channel) Metrics and rules to compare trajectories to main routes 5
  • 6. Trajectories comparison Frechet distance and Dynamic Time Warping  Frechet : Minimise the max distance between pos  DTW : Minimise sum of distances between pos 6
  • 7. Group of Similar Trajectories The model allows trajectories clustering using :  Distance (Fréchet, DTW...)  Density (T-OPTICS)  Zone Graph (Itinerary) 7
  • 8. Main trajectory Median trajectory  Cluster positions (Normalized time, Frechet, DTW)  Compute aggregated median position (K-Mean) 8
  • 9. Statistical analysis Statistical analysis of points clusters distribution (distance, time, heading...)  Boxplot visualisation 9
  • 10. Spatio-temporal pattern Median trajectory and spatio-temporal channel  Cluster positions (Frechet matching) with the main trajectory positions  Compute spatial and temporal distance to the median position  Sort spatialy (left/right)  Sort temporaly (early/late)  Statistical selection 90%  Normality bounds  ∆left / ∆right  ∆early / ∆late 10
  • 11. Qualification Functional Process 11
  • 12. Qualify a Position Spatio-temporal channel  Merge together spatial and temporal channel  At each relative time of the median trajectory  Normality bounds  5 zones defined  Qualify a position How to qualify a trajectory ? 12
  • 13. Similarity measurements Average, maximum and variability of spatial/temporal distance between the trajectory and the spatio-temporal channel (%) 13
  • 14. Fuzzy Logic Spatio-temporal similarity classification of a trajectory compared to a pattern Using Fuzzy logic :  Fuzzy sets learned by statistical analysis of similarity measurements  Fuzzy rules defined by experts and combining similarity measurements 14
  • 15. Fuzzy Logic (Fuzzy sets) Use statistics of similarity measurements  Min  20%  40%  50%  60%  80%  Max Define fuzzy sets 15
  • 16. Fuzzy Logic (Fuzzification) Match a trajectory to the spatio-temporal pattern (Frechet matching) Compute the similarity measurements Fuzzify similarity measurements using fuzzy sets Value : 145 75% Medium 25% High 16
  • 17. Fuzzy Logic (Fuzzy Rules) Apply fuzzy rules using a fuzzy associative matrix combining the fuzzified similarity measurements Fuzzy rules are activated at different degree of truth depending on the membership of the similarity measurements to fuzzy sets 17
  • 18. Fuzzy Logic (Defuzzification) How to get an human friendly similarity score combining the similarity ratings measurements ? Defuzzify the fuzzy rules sets activated Using the « center of gravity » method 18
  • 19. Visualisation 19
  • 20. Visualisation of spatio-temporal data How to display spatio-temporal patterns and qualified positions/trajectories ? 3D space/time cube ? 20
  • 21. Visualisation (spatio-temporal patterns) 21
  • 22. Visualisation (2D analysis) 22
  • 23. Conclusion Model of trajectory, itineraries and matching tools General methodology Data mining : spatio-temporal patterns Position and trajectory classification using fuzzy logic 23
  • 24. Future work Improve statistics analysis (skewness/kurtosis) Detect multimodal groups of trajectories Investigate patterns generalization (aggregation ?) Consider more similarity measurements (heading, speed) Extend to trajectories partial matching, data streams, real time analysis Improve geovisualisation of outliers ... 24
  • 25. Questions ? L. Etienne, T. Devogele, A. Bouju. In Shi, Goodchild, Lees & Leung (Eds.) Advances in Geo-Spatial Information Science, Chap. Modeling Space and Time, Spatio-temporal Trajectory Analysis of Mobile Objects Following the same Itinerary. CRC Press, Taylor & Francis Group, ISPRS Orange book series, ISBN 978-0-415-62093-2, pages 47-58, 2012. 25
  • 26. Plateform programming PostgreSQL / PostGIS database  Model & data integration (60 Gb of raw AIS data frames from different sources, 6 month )  PostGIS spatial functions & indexes  PL/PgSQL, PL/C, PL/Java programming Java  Spatio-temporal pattern extraction & similarity measurements  Fuzzy logic Statistics  Matlab Web  PHP/HTML/JS/AJAX (Ajax Push Engine)  GeoServer WFS/WMS Openlayers KML 26
  • 27. Related publications Book chapters  T. Devogele, L. Etienne, C. Ray, and C. Claramunt. In C. Renso, S. Spaccapietra & E. Zimányi (Eds.) Mobility Data: Modeling, Management, and Understanding, Chapter Mobility Applications, Maritime Applications. Cambridge press, to be published in 2012.  L. Etienne, T. Devogele, A. Bouju. In Shi, Goodchild, Lees & Leung (Eds.) Advances in Geo-Spatial Information Science, Chap. Modeling Space and Time, Spatio-temporal Trajectory Analysis of Mobile Objects Following the same Itinerary CRC Press, Taylor & Francis Group, ISPRS Orange book series, ISBN 978-0-415-62093-2, pages 47-58, 2012. 27
  • 28. Related publications International conferences  L. Etienne, C. Ray, and G. Mcardle. Spatio-temporal visualisation of outliers. Proceedings of the international workshop on Maritime Anomaly Detection (MAD), pages 119–120, 2011.  L. Etienne, T. Devogele, and A. Bouju. Spatio-temporal trajectory analysis of mobile objects following the same itinerary. Proceedings of the International Symposium on Spatial Data Handling (SDH), pages 86–91, 2010.  A. Lecuyer, J.M. Burkhardt, and L. Etienne. Feeling bumps and holes without a haptic interface: the perception of pseudo-haptic textures. Proceedings of the SIGCHI conference on Human factors in computing systems, pages 239–246, 2004. 28
  • 29. Europe map 29
  • 30. Passenger ships 30
  • 31. Calais - Dovers 31
  • 32. Dover straits 32

×