1 / 9

Secure Geospatial and Sensor Semantic Webs for Crime Analysis and Border Security

Secure Geospatial and Sensor Semantic Webs for Crime Analysis and Border Security. Prof. Bhavani Thuraisingham, PhD Prof. Latifur Khan, PhD Mr. Alam Ashraful (PhD Student) Mr. Ganesh Subbiah (MS Student) The University of Texas at Dallas and Prof. Shashi Shekar, PhD

dutch
Télécharger la présentation

Secure Geospatial and Sensor Semantic Webs for Crime Analysis and Border Security

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. Secure Geospatial and Sensor Semantic Websfor Crime Analysis and Border Security Prof. Bhavani Thuraisingham, PhD Prof. Latifur Khan, PhD Mr. Alam Ashraful (PhD Student) Mr. Ganesh Subbiah (MS Student) The University of Texas at Dallas and Prof. Shashi Shekar, PhD The University of Minnesota 3 May 2007

  2. Vision for Secure Geospatial Semantic Web * Semantic Metadata Extraction * Decision Centric Fusion * Geospatial data interoperability through web services * Geospatial data mining * Data Source A Tools for Analysts Data Source B SECURITY/ QUALITY Data Source C

  3. Technology Stack for Secure Geospatial Semantic Web • Adapted from Tim Berners Lee’s description of the Semantic Web TRUST CONF I DENT I AL I T Y Logic, Proof and Trust Rules/Query Other Services GRDF, Geospatial Ontologies (Our contributions) GML, GML Schemas (OGC Standard) Protocols

  4. GRDF Geospatial RDF (developed at the University of Texas at Dallas, Ashraful and Thuraisingham) • GRDF (Geospatial Resource Description Framework) • Adds semantics to data • Loosely-structured (easy to freely mix with other non-geospatial data) • Semantically extensible ComputerScience Building (33.98111, -96.4011) (33.989999, -96.4022) hasExtent

  5. GRDF Example (Topology Ontology) <owl:Class rdf:ID=“Edge"></owl:Class> <owl:Class rdf:ID=“Node"></owl:Class> <owl:Class rdf:ID=“Face"> <rdfs:subClassOf> <owl:Restriction> <owl:minCardinality rdf:datatype="http://www.w3.org/2001/XMLSchema#int" >1</owl:minCardinality> <owl:onProperty> <owl:DataTypeProperty rdf:ID=“hasEdge"/> </owl:onProperty> </owl:Restriction> … </owl:Class>

  6. Security: Semantic Access Control • Architecture D A G I S Geospatial Semantic WS Provider Client Enforcement Module Decision Module Authorization Module Semantic-enabled Policy DB Web Service Client Side Web Service Provider Side

  7. Testing Image Pixels Training Image Pixels SVM Classifier Classified Pixels Region Growing Graph of Regions Shortest Path Tree Graph of Near Neighboring Regions Ontology Driven Rule Mining High Level Concept Data Mining: Ontology-Driven Classification

  8. Geospatial data mining for Crime Analysis (a) Jul 19 to Jul 26, 2004 (b) Jul 26 to Aug 2, 2004 (Source: http:// www.diligencellc.com) (Best Viewed in Color) Activity Levels by Jurisdiction (Caution: Use numeric activity count data on right ) f or trend analysis. Color - codes are not directly comparable across Figures a and b • Examining theories of time • Examining current data mining techniques and their limitations (e.g. support vector machine and ontology driven classification) • Developing novel techniques for spatio temporal data analysis, The numeric activity count data, shows a diminishing trend for the number of insurgent incidents across multiple provinces from July 19-26, 2004 (Figure a) and July 26-Aug 2, 2004 (Figure2b). Notice the highlighted entries in numeric activity count data in Figure e.g. Anbar, where the number of insurgent incidents diminished in a matter of weeks.

  9. Current Research • Integrating with sensor/stream data emanating from RFID devices • Examining Sensor ML and developing Sensor RDF • Working with University of Minnesota on data integration and data mining for spatiotemporal data for crime analysis and border patrol • Security, privacy, misuse detection are all important considerations • Working with OGC for technology transfer to standards • Working with Raytheon to transfer technologies to operational programs

More Related