Ce diaporama a bien été signalé.
Nous utilisons votre profil LinkedIn et vos données d’activité pour vous proposer des publicités personnalisées et pertinentes. Vous pouvez changer vos préférences de publicités à tout moment.

SSN2012 Deriving Semantic Sensor Metadata from Raw Measurements

1 427 vues

Publié le

Presented at the SSN2012 workshop at ISWC

  • Soyez le premier à commenter

SSN2012 Deriving Semantic Sensor Metadata from Raw Measurements

  1. 1. 5th International Workshop on Semantic Sensor Networks at ISWC2012Deriving Semantic Sensor Metadata from Raw Measurements Jean-Paul Calbimonte1, Hoyoung Jeung2, Zhixian Yan3, Oscar Corcho1, Karl Aberer3 1Ontology Engineering Group, Universidad Politécnica de Madrid 2SAP Research, Birsbane 3LSIR, EPFL Ecole Polytechnique Fédérale de Lausanne jp.calbimonte@upm.es Date: 14/11/2012
  2. 2. Sensor Observations Semantic metadata Annotations Sensor Raw MeasurementsRepresentation Characterize Classify Publish 2
  3. 3. Streaming Sensor Data Data streams Continuous evaluation Timestamped tuples Time windowsDo we know what we are sensing? 3
  4. 4. Sensor Web4
  5. 5. The Sensor WebUniversal, web-based access to sensor data 5
  6. 6. Semantic Sensor Web “too much (streaming) data but not enough (tools to gain and derive) knowledge”* LinkedSensorDataSensor data publishingLinked Data LSM Sense2WebSemantic sensor metadata Sensor APIs ETALISSemantic Sensor Network ontology Videk SwissEx BOTTARI, UrbanMatch AEMET transporte. linkeddata.es SSN +CEP …many many more working on this * Sheth et al. 2008, Semantic Sensor Web 6
  7. 7. SSN Ontology with other ontologies tool for modeling our sensor data ~what we are observing 7
  8. 8. Sensor Metadataswissex:Sensor1 rdf:type ssn:Sensor; ssn:onPlatform swissex:Station1; ssn:observes cf-property:wind_speed.swissex:Sensor2 rdf:type ssn:Sensor; ssn:onPlatform swissex:Station1; ssn:observes cf-property:air_temperature.swissex:Station1 :hasGeometry [ rdf:type wgs84:Point; wgs84:lat "46.8037166"; wgs84:long "9.7780305"]. 8
  9. 9. Sensor Observationsswissex:WindSpeedObservation1 rdf:type ssn:Observation; ssn:featureOfInterest cf-feature:wind; ssn:observedProperty cf-property:wind_speed; ssn:observationResult [rdf:type ssn:SensorOutput; ssn:hasValue [qudt:numericValue "6.245"^^xsd:double]]; ssn:observationResultTime [time:inXSDDatatime "2011-10-26T21:32:52"]; ssn:observedBy swissex:Sensor1 ; 9
  10. 10. Sensor Observations HeterogeneityReuse this data?Publish as Linked Sensor Data?Query with SPARQL-Stream? 10
  11. 11. Cosm/Pachube Datastreamsnot enough reliable metadata aboutthe observations 11
  12. 12. Looking into the Data Air Pressure? Air Temperature?12
  13. 13. Classifying Sensor DataUnclassified input series Already classified time series Representation Classification Metadata 13
  14. 14. Related Tasks• Querying time series • e.g. find a sub-sequence in a time series database• Measuring time series similarity • e.g. are these time series the same?• Time series classification • e.g. classify heart beat series: normal, murmur, et 14
  15. 15. Deriving Semantic Metadata15
  16. 16. Data RepresentationRepresent the data approximatingwith fewer linear segmentsAccuracy vs Numerosity 16
  17. 17. Constant Approximation • Use constant segments for a subset of points4.5 43.5 32.5 21.5 1 0 10 20 30 40 50 60 70 80 90 100 17
  18. 18. Piecewise Linear Approximation 4.1 4.05 3.95 4 Reflect data trends 3.9 3.85 3.8 Apply with different resolutions 3.75 3.7 0 1 2 3 4 5 6 7 8 9 10 Applicable for different rates 4.14.05 43.95 3.93.85 3.83.75 3.73.65 0 1 2 3 4 5 6 7 8 9 10 18
  19. 19. Piecewise Linear Approximationri hi+1 hili begi endi Constructing segments 19
  20. 20. Linear ApproximationsWe care about the angles π/2 a π/4 a c b d 0 a c -π/4 d Divide the angle space in sectors Distribution of angles in training set 20
  21. 21. Slope Distributionsts1 adacdaaad [5a,0b,1c,3d]ts2 adabbaaad [5a,2b,0c,2d]ts3 adccdaaad [4a,0b,2c,3d] Distance measure Classification 21
  22. 22. Use the representation for ClassifyingLinear approximationCompute distribution of the slopesK-nearest neighbor classificationTraining-Test datasets: SwissExperiment AEMET 22
  23. 23. Experiments SwissExConfusion matrix
  24. 24. Experiments AEMETConfusion matrix
  25. 25. Evaluation AEMET25
  26. 26. Evaluation AEMETcf-property:wind_speed rdf:type dim:VelocityOrSpeed; rdfs:label "wind speed"; ssn:isPropertyOf cf-feature:wind; qu:propertyType qu:scalar; qu:generalQuantityKind qu:speed. 26
  27. 27. Metadata Propertiescf-property:air_temperature rdf:type dim:Temperature; ssn:isPropertyOf cf-feature:air; qu:propertyType qu:scalar; qu:generalQuantityKind qu:temperature.cf-property:soil_temperature rdf:type dim:Temperature; ssn:isPropertyOf cf-feature:soil; qu:propertyType qu:scalar; qu:generalQuantityKind qu:temperature.
  28. 28. Querying MetadataSELECT ?sensorWHERE { ?sensor a ssn:Sensor ; ssn:observes cf-property:air_temperature .}SELECT ?stream ?observedPropertyWHERE { ?sensor a ssn:Sensor ; ssn:observes ?observedProperty . ?stream ssn:isProducedBy ?sensor . ?observedProperty qu:generalQuantityKind qu:temperature .} 28
  29. 29. Evaluation vs SAX29
  30. 30. Evaluation vs SAX30
  31. 31. How much data do we need?31
  32. 32. ConclusionsClassify Sensor Data • Piecewise Linear Representation • Segment slope distributions • kNN classificationGenerate Metadata • Observed properties • Potentially unknown metadataFuture work • Combine with tag disambiguation? • Use pattern mining for online queries • Other techniques, shapelets, use other parameters 32
  33. 33. …Thanks Questions, please.jp.calbimonte@upm.es 33

×