RESEARCH POSTER PRESENTATION DESIGN © 2011 www.PosterPresentations.com ANALYTICS ON INDOOR MOVING OBJECTS: A STUDY ON RFID BASED AIRPORT BAGGAGE HANDLING SYSTEM Introduction and Motivation References [1]. T. Ahmed, T. B. Pedersen, and H. Lu. A data warehouse solution for analyzing RFID-based baggage tracking data. In MDM, pages 283–292, 2013. [2] T. Ahmed, T. B. Pedersen, and H. Lu. Capturing Hotspots for Constrained Indoor Movement. In SIGSPATIAL/GIS, pages 462–465, 2013 [3] T. Ahmed, T. B. Pedersen, and H. Lu. Finding Dense Locations in Indoor Tracking Data, In MDM, 2014 (to appear) Finding Dense Locations Tanvir Ahmed (tanvir@cs.aau.dk) Supervisor: Torben Bach Pedersen (AAU) , Co‐supervisors: Hua Lu(AAU), Toon Calders (ULB) RFID Based Airport Baggage Handling a This work is supported by the BagTrack project funded by the Danish National Advanced Technology Foundation under grant no. 010-2011-1.  Useful for finding overloaded locations  Tracking records do not provide when did an object enter and exit a location.  Need to map the tracking records before hotspot query  More topological detail need to be captured.  Use eq (1) (2), (3) and node type of a location for calculating the appropriate time start and time end from tracking record. Node types: Type 1 node No loop, No reader in dest. Type 2 node Example: Sorter-2 Type 3 node Example: Sorter-1 Type 4 node (Loop, reader at the destination) Type 5 node (Example: Screening belt) Image: http://www.dailymail.co.uk/travel/article‐ 1190003/Rising‐taxes‐force‐passengers‐desert‐UK‐ airports.html 260.4 M passengers/year Image: http://www.taopo.org/solution/05/14/2012/fyi‐what‐do‐ when‐your‐baggage‐loaded #34 M bags mishandled/year # 13.2 bags mishandled per 1000 passengers # Total cost to the industry/Year 3320 M USD Data Source: http://www.sita.aero/content/baggage‐report‐2012 Rid Obj Dev t r1 o1 dev1 4 r2 o1 dev1 5 r3 o1 dev3 15 r4 o1 dev3 17 r5 o1 dev3 18 r6 o1 dev4 26 r7 o1 dev4 27 r8 o1 dev4 29 r9 o1 dev4 51 r10 o1 dev4 53 r11 o1 dev4 54 Rec Obj Dev t_in t_out rec1 o1 dev1 4 5 rec2 o1 dev3 15 18 rec3 o1 dev4 26 29 rec4 o1 dev4 51 54 Data Warehouse Solution  Easy and fast queries for analysis Defining Density Modeling and Mapping for Constrained Path Space [2] Modeling and Mapping for Semi-constrained Path Space[3] The DLT-Index for Efficient Query Processing [3] Other Analytics  Extract interesting features from the tracking data  Apply different data mining algorithms to find relations among the features that are highly related for baggage mishandling  Due to very low ratio of mishandling, the data sets should be re-sampled for learning.  Outlier mining Airport baggage Handling RFID Deployment in Airport Raw Reading Records Tracking records after eliminating Multiple Readings Data Warehouse Design Many to Many relationship between Flight and Bag Tracking records into stay records [1] Example of Date Localization  Efficient Pruning feature