1 / 31

Towards Semantic Trajectory Outlier Detection

Towards Semantic Trajectory Outlier Detection. Artur Ribeiro de Aquino 1 Luis Otavio Alvares 1 Chiara Renso 2 Vania Bogorny 1. 1 Dep. de Matem ática e Estatística – U niversidade Federal de Santa Catarina (UFSC) 2 KDD Lab – Pisa, Italy. Summary. Introduction and Motivation

anka
Download Presentation

Towards Semantic Trajectory Outlier Detection

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Towards Semantic Trajectory Outlier Detection Artur Ribeiro de Aquino1 Luis OtavioAlvares1 Chiara Renso2 Vania Bogorny1 1Dep. de Matemática e Estatística – UniversidadeFederal de Santa Catarina (UFSC) 2KDD Lab – Pisa, Italy

  2. Summary • Introduction and Motivation • Problem • Objective • Proposal • Definition • Algorithm • Experimental Results • Related Works • Conclusion and Future Works

  3. Introduction and Motivation

  4. Introduction and Motivation

  5. Introduction and Motivation • Manytrajectorypatterns • Chasing [Siqueira, 2011] • Frequentmovements[Giannotti, 2007], [Trasarti 2011]; • Meeting, Leadership, Convergence, Recurrence, Flocks [Laube, 2005];

  6. Introduction and Motivation • Some worksfocusedonoutliers • Uncommonbehavior • Example • [Lee, 2008] • [Yuan, 2011] • [Alvares, 2011] • [Fontes, 2013]

  7. Problem • Existing works do not interpret the outliers • Application examples • Publicsafety • Trafficengineering • Slowtraffic • Alternativeroutes

  8. Objective • Extendtheworkof Fontes [Fontes, 2013] • Outlierinterpretation • Semanticclassification • Stop Outliers • EventAvoidingOutliers • TrafficAvoidingOutliers

  9. Proposal

  10. Proposal • Fontes [Fontes, 2013]

  11. Definition:Stop Outlier

  12. Definition – Outlier Segment

  13. Definition – Stop Outlier

  14. Definitions:Event Avoiding Outlier

  15. Definition – Standard Segment

  16. Definition - Event Avoiding Outlier

  17. Definitions:Traffic Avoiding Outlier

  18. Definition – Synchronized Standard Segment

  19. Definition – Traffic Avoiding Outlier

  20. Algorithm

  21. Proposal - Algorithm • Main

  22. Proposal - Algorithm • findEventAvoidingOutlier

  23. Proposal - Algorithm • findTrafficAvoidingOutlier

  24. Experimental Results

  25. Experimental Results • Taxi trajectories in San Francisco • Split trajectories (occupation, weekdays) • 537.098 trajectories with 6.314.120 points in total • maxDist = 100m • minSup = 5% • minLength = 10%

  26. Experimental Results – Stop Outlier • minTime = 15 min • 73 stop outliers • 44:13 min of duration

  27. Experimental Results – Event Avoiding Outlier • Event at Bayshore Freeway (US101) • From 17:30 to 21:30

  28. Experimental Results – Traffic Avoiding Outlier • timeTol = 15 min • 6 traffic avoiding outliers • Synchronized standard segments (avg): 7:05 min • Fastest standard segments (avg): 3:30 min

  29. Related Works

  30. Conclusion and Future Works • Lack of interpretation on previous approaches • New concepts were provided aiming the semantics • Cases found were correctly interpreted • Future… • Weight to each outlier segment • Outlier classification based on their outlier segments

  31. Towards Semantic Trajectory Outlier Detection Artur Ribeiro de Aquino1 Luis OtavioAlvares1 Chiara Renso2 Vania Bogorny1 1Dep. de Matemática e Estatística – UniversidadeFederal de Santa Catarina (UFSC) 2KDD Lab – Pisa, Italy

More Related