SlideShare une entreprise Scribd logo
1  sur  22
Enriching trajectory and trajectory pattern semantics with background knowledge Chiara Renso, Roberto Trasarti KDDLab, ISTI, CNR, Italy  Stefano Spaccapietra,  Christine Parent,  Jose  Macedo , Zhixian Yan EPFL, Lausanne, Switzerland  Miriam Baglioni Pisa University, Italy Monica Wachowicz Technical University of Madrid, Spain
Athena: Trajectories and city places Athena the greek goddess of wisdom Hotel University Monuments Show kinds of  points of interest and landmarks
And more … select kinds of trajectories according to the application domain TouristTrajectory ≡ Trajectory ⊓ ∃hasStop.∃isLocatedIn.TouristPlace ⊓∃hasStop.∃isLocatedIn.AccomodationPlace SELECT trajectory FROM ‘?trajectory rdf:type :TouristTrajectory’; Tourist Trajectories
GeoPKDD Tasks
The idea  (1/2)  ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
The idea  (2/2) ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Our Contribution so far … ,[object Object],[object Object],[object Object]
Organizing the Knowledge …
The  trajectory ontology Geography Ontology (GO) Traffic Domain Ontology (ADO) Geometric Trajectory Ontology (GTO) StreetG Time Instant SimpleTime Geo Line SimpleGeo B.E.S Move Point Interval Person Trajectory Surface hasGeometry hasGeometry hasGeometry hasTime islocatedIn hasTrajectory from is-a is-a is-a is-a is-a is-a Crossing between follows RoadWork islocatedIn StreetT sameAs hasMove Stop Begin End to hasStop hasEnd hasBegin is-a isLocatedIn is-a is-a is-a PointOfInterest Museum Hotel is-a is-a hasHome hasWork locatedIn LongTerm RoadWork GasStation Car hasCar LongTime Interval is-a is-a is-a
All Data are inside DB !! Geometric Trajectory Geographic Knowledge Domain Knowledge HERMES Mobility Pattern Mobility Data Raw Data
Semantic Enrichment Process ATHENA  ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES)  TRAJECTORY  ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS,  Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
Taxonomies and Axioms Time CityPlace Bridge Church … TouristTrajectory ≡ Trajectory ⊓ ∃hasStop.∃isLocatedIn.TouristPlace ⊓∃hasStop.∃isLocatedIn.AccomodationPlace Morning Geometric Trajectory Ontology (GTO) Time Instant SimpleTime Geo Line SimpleGeo B.E.S Move Point Interval Trajectory Surface hasGeometry hasGeometry hasTime from is-a is-a is-a is-a is-a is-a follows hasMove Stop Begin End to hasStop hasEnd hasBegin is-a isLocatedIn is-a is-a is-a LongTime Interval is-a Afternoon Evening Monument Museum
Semantic Enrichment Process ATHENA  ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES)  TRAJECTORY  ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS,  Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
Mapping Ontology to DB ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Semantic Trajectory HasTrajectory hasComponents BEStop 0:N list 1:1 2:N list 1:1 IsIn 0:1 0:N Move   ƒ(T) To 0:1 1:1 1:1 0:1 Its personalization --> IsIn 0:1 0:N The hooks TravelingOT Trajectory SpatialOT1 Bird name birth year location Does Migration year North/South StopsIn Country 0:N list 1:1 2:N list 0:N From SpatialOT2
Semantic Enrichment Process ATHENA  ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES)  TRAJECTORY  ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS,  Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
From Tables to Triples ,[object Object],[object Object],[object Object]
Reasoning Services ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],TouristTrajectory ≡ Trajectory ⊓ ∃hasStop.∃isLocatedIn.TouristPlace ⊓∃hasStop.∃isLocatedIn.AccomodationPlace
Semantic Enrichment Process ATHENA  ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES)  TRAJECTORY  ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS,  Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
Querying only the ontology ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Querying the ontology + original data ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]
Ongoing work ,[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]

Contenu connexe

En vedette

En vedette (8)

Preserving Privacy in Semantic-Rich Trajectories of Human Mobility
Preserving Privacy in Semantic-Rich Trajectories of Human MobilityPreserving Privacy in Semantic-Rich Trajectories of Human Mobility
Preserving Privacy in Semantic-Rich Trajectories of Human Mobility
 
K-BestMatch
K-BestMatchK-BestMatch
K-BestMatch
 
Cast
CastCast
Cast
 
Individual movements and geographical data mining. Clustering algorithms for ...
Individual movements and geographical data mining. Clustering algorithms for ...Individual movements and geographical data mining. Clustering algorithms for ...
Individual movements and geographical data mining. Clustering algorithms for ...
 
Algoritmi di clustering
Algoritmi di clusteringAlgoritmi di clustering
Algoritmi di clustering
 
Mining Object Movement Patterns from Trajectory Data
Mining Object Movement Patterns from Trajectory DataMining Object Movement Patterns from Trajectory Data
Mining Object Movement Patterns from Trajectory Data
 
Trajectory clustering - Traclus Algorithm
Trajectory clustering - Traclus AlgorithmTrajectory clustering - Traclus Algorithm
Trajectory clustering - Traclus Algorithm
 
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' TrajectoriesSpatio-Temporal Data Mining and Classification of Ships' Trajectories
Spatio-Temporal Data Mining and Classification of Ships' Trajectories
 

Similaire à Athena

Multimedia Data Navigation and the Semantic Web (SemTech 2006)
Multimedia Data Navigation and the Semantic Web (SemTech 2006)Multimedia Data Navigation and the Semantic Web (SemTech 2006)
Multimedia Data Navigation and the Semantic Web (SemTech 2006)
Bradley Allen
 
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
Beniamino Murgante
 
How to empower community by using GIS lecture 1
How to empower community by using GIS lecture 1How to empower community by using GIS lecture 1
How to empower community by using GIS lecture 1
wang yaohui
 

Similaire à Athena (20)

Daedalus
DaedalusDaedalus
Daedalus
 
On the Management, Analysis and Simulation of our LifeSteps
On the Management, Analysis and Simulation of our LifeStepsOn the Management, Analysis and Simulation of our LifeSteps
On the Management, Analysis and Simulation of our LifeSteps
 
ST-Toolkit, a Framework for Trajectory Data Warehousing
ST-Toolkit, a Framework for Trajectory Data WarehousingST-Toolkit, a Framework for Trajectory Data Warehousing
ST-Toolkit, a Framework for Trajectory Data Warehousing
 
Trajectory Segmentation and Sampling of Moving Objects Based On Representativ...
Trajectory Segmentation and Sampling of Moving Objects Based On Representativ...Trajectory Segmentation and Sampling of Moving Objects Based On Representativ...
Trajectory Segmentation and Sampling of Moving Objects Based On Representativ...
 
Gis capabilities on Big Data Systems
Gis capabilities on Big Data SystemsGis capabilities on Big Data Systems
Gis capabilities on Big Data Systems
 
Visualizing Unstructured Text Documents using Trees and Maps: Analyzing Verba...
Visualizing Unstructured Text Documents using Trees and Maps: Analyzing Verba...Visualizing Unstructured Text Documents using Trees and Maps: Analyzing Verba...
Visualizing Unstructured Text Documents using Trees and Maps: Analyzing Verba...
 
Multimedia Data Navigation and the Semantic Web (SemTech 2006)
Multimedia Data Navigation and the Semantic Web (SemTech 2006)Multimedia Data Navigation and the Semantic Web (SemTech 2006)
Multimedia Data Navigation and the Semantic Web (SemTech 2006)
 
GIS Data Types
GIS Data TypesGIS Data Types
GIS Data Types
 
Compass Framework
Compass FrameworkCompass Framework
Compass Framework
 
Gis and Ruby 101 at Ruby Conf Kenya 2017 by Kamal Ogudah
Gis and Ruby 101 at Ruby Conf Kenya 2017 by Kamal OgudahGis and Ruby 101 at Ruby Conf Kenya 2017 by Kamal Ogudah
Gis and Ruby 101 at Ruby Conf Kenya 2017 by Kamal Ogudah
 
Working with OpenStreetMap using Apache Spark and Geotrellis
Working with OpenStreetMap using Apache Spark and GeotrellisWorking with OpenStreetMap using Apache Spark and Geotrellis
Working with OpenStreetMap using Apache Spark and Geotrellis
 
GeoMesa on Spark SQL: Extracting Location Intelligence from Data
GeoMesa on Spark SQL: Extracting Location Intelligence from DataGeoMesa on Spark SQL: Extracting Location Intelligence from Data
GeoMesa on Spark SQL: Extracting Location Intelligence from Data
 
Euro30 2019 - Benchmarking tree approaches on street data
Euro30 2019 - Benchmarking tree approaches on street dataEuro30 2019 - Benchmarking tree approaches on street data
Euro30 2019 - Benchmarking tree approaches on street data
 
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
Dealing with multiple source spatio-temporal data in urban dynamics analysis ...
 
GeoMesa on Apache Spark SQL with Anthony Fox
GeoMesa on Apache Spark SQL with Anthony FoxGeoMesa on Apache Spark SQL with Anthony Fox
GeoMesa on Apache Spark SQL with Anthony Fox
 
Locality Sensitive Hashing By Spark
Locality Sensitive Hashing By SparkLocality Sensitive Hashing By Spark
Locality Sensitive Hashing By Spark
 
DITA's New Thang: Going Mapless!
DITA's New Thang: Going Mapless!DITA's New Thang: Going Mapless!
DITA's New Thang: Going Mapless!
 
Sql Saturday Spatial Data Ss2008 Michael Stark Copy
Sql Saturday Spatial Data Ss2008 Michael Stark   CopySql Saturday Spatial Data Ss2008 Michael Stark   Copy
Sql Saturday Spatial Data Ss2008 Michael Stark Copy
 
Intro To PostGIS
Intro To PostGISIntro To PostGIS
Intro To PostGIS
 
How to empower community by using GIS lecture 1
How to empower community by using GIS lecture 1How to empower community by using GIS lecture 1
How to empower community by using GIS lecture 1
 

Athena

  • 1. Enriching trajectory and trajectory pattern semantics with background knowledge Chiara Renso, Roberto Trasarti KDDLab, ISTI, CNR, Italy Stefano Spaccapietra, Christine Parent, Jose Macedo , Zhixian Yan EPFL, Lausanne, Switzerland Miriam Baglioni Pisa University, Italy Monica Wachowicz Technical University of Madrid, Spain
  • 2. Athena: Trajectories and city places Athena the greek goddess of wisdom Hotel University Monuments Show kinds of points of interest and landmarks
  • 3. And more … select kinds of trajectories according to the application domain TouristTrajectory ≡ Trajectory ⊓ ∃hasStop.∃isLocatedIn.TouristPlace ⊓∃hasStop.∃isLocatedIn.AccomodationPlace SELECT trajectory FROM ‘?trajectory rdf:type :TouristTrajectory’; Tourist Trajectories
  • 5.
  • 6.
  • 7.
  • 9. The trajectory ontology Geography Ontology (GO) Traffic Domain Ontology (ADO) Geometric Trajectory Ontology (GTO) StreetG Time Instant SimpleTime Geo Line SimpleGeo B.E.S Move Point Interval Person Trajectory Surface hasGeometry hasGeometry hasGeometry hasTime islocatedIn hasTrajectory from is-a is-a is-a is-a is-a is-a Crossing between follows RoadWork islocatedIn StreetT sameAs hasMove Stop Begin End to hasStop hasEnd hasBegin is-a isLocatedIn is-a is-a is-a PointOfInterest Museum Hotel is-a is-a hasHome hasWork locatedIn LongTerm RoadWork GasStation Car hasCar LongTime Interval is-a is-a is-a
  • 10. All Data are inside DB !! Geometric Trajectory Geographic Knowledge Domain Knowledge HERMES Mobility Pattern Mobility Data Raw Data
  • 11. Semantic Enrichment Process ATHENA ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES) TRAJECTORY ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS, Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
  • 12. Taxonomies and Axioms Time CityPlace Bridge Church … TouristTrajectory ≡ Trajectory ⊓ ∃hasStop.∃isLocatedIn.TouristPlace ⊓∃hasStop.∃isLocatedIn.AccomodationPlace Morning Geometric Trajectory Ontology (GTO) Time Instant SimpleTime Geo Line SimpleGeo B.E.S Move Point Interval Trajectory Surface hasGeometry hasGeometry hasTime from is-a is-a is-a is-a is-a is-a follows hasMove Stop Begin End to hasStop hasEnd hasBegin is-a isLocatedIn is-a is-a is-a LongTime Interval is-a Afternoon Evening Monument Museum
  • 13. Semantic Enrichment Process ATHENA ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES) TRAJECTORY ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS, Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
  • 14.
  • 15. Semantic Trajectory HasTrajectory hasComponents BEStop 0:N list 1:1 2:N list 1:1 IsIn 0:1 0:N Move ƒ(T) To 0:1 1:1 1:1 0:1 Its personalization --> IsIn 0:1 0:N The hooks TravelingOT Trajectory SpatialOT1 Bird name birth year location Does Migration year North/South StopsIn Country 0:N list 1:1 2:N list 0:N From SpatialOT2
  • 16. Semantic Enrichment Process ATHENA ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES) TRAJECTORY ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS, Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
  • 17.
  • 18.
  • 19. Semantic Enrichment Process ATHENA ORACLE + (SPATIO-TEMPORAL & DATA MINING & SEMANTIC FEATURES) TRAJECTORY ONTOLOGY Semantic Trajectories stops, moves,etc Trajectories Patterns TAS, Domain Information Domain Geography Geometric Import ABOX mapping Import TBOX Create Ontology Query SQL+Semantics 1 5 3 2 4 Analyst
  • 20.
  • 21.
  • 22.

Notes de l'éditeur

  1. Advantages: Oracle is the DMBS chosen in Geopkdd for storing sptaio-temporal data. It also has been chosen for data warehouse. We aim at experimenting the reasoning capabilities. Disadvantages: The tools is not very friendly to use, the OWL reasoning engine is available from version 11g, just distributed on the market. The OWL fragment is a subset of OWL DL called OWLPRIME. Limited expressive power
  2. Advantages: this is the simplest case, exploiting of the ontology reasoning capabilities. The user query the ontology directly. Disadv: size of the ontology may grow, the query are possible only on the ontology: no possibility to query ontology joint with relational data Other scenarios are possible
  3. Advantages: this is the simplest case, exploiting of the ontology reasoning capabilities. The user query the ontology directly. Disadv: size of the ontology may grow, the query are possible only on the ontology: no possibility to query ontology joint with relational data Other scenarios are possible
  4. This step allow to link the ontology concepts with the data in the database. All the data become triples and populate the ontology.
  5. Advantages: this is the simplest case, exploiting of the ontology reasoning capabilities. The user query the ontology directly. Disadv: size of the ontology may grow, the query are possible only on the ontology: no possibility to query ontology joint with relational data Other scenarios are possible
  6. This step allow to link the ontology concepts with the data in the database. All the data become triples and populate the ontology.
  7. This step allow to link the ontology concepts with the data in the database. All the data become triples and populate the ontology.
  8. Advantages: this is the simplest case, exploiting of the ontology reasoning capabilities. The user query the ontology directly. Disadv: size of the ontology may grow, the query are possible only on the ontology: no possibility to query ontology joint with relational data Other scenarios are possible
  9. This step allow to link the ontology concepts with the data in the database. All the data become triples and populate the ontology.
  10. This step allow to link the ontology concepts with the data in the database. All the data become triples and populate the ontology.