SlideShare a Scribd company logo
5th International Workshop on Semantic Sensor Networks at
                            ISWC2012



Deriving 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
Sensor Observations


 Semantic metadata
                                Annotations



       Sensor Raw Measurements

Representation
                         Characterize

                     Classify
                                      Publish



                     2
Streaming Sensor Data

                       Data streams
                       Continuous evaluation
                       Timestamped tuples
                       Time windows




Do we know what we are sensing?


               3
Sensor Web




4
The Sensor Web

Universal, web-based access to sensor data




                    5
Semantic Sensor Web
   “too much (streaming) data but not enough (tools to
   gain and derive) knowledge”*
                                                                                                  LinkedSensorData
Sensor data publishing

Linked Data                                  LSM

                                                                 Sense2Web


Semantic sensor metadata                             Sensor APIs


                                                                                       ETALIS
Semantic 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
SSN Ontology with other ontologies



  tool for modeling our sensor data




          ~what we are observing

      7
Sensor Metadata

swissex: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
Sensor Observations

swissex: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
Sensor Observations




 Heterogeneity




Reuse this data?
Publish as Linked Sensor Data?
Query with SPARQL-Stream?

   10
Cosm/Pachube Datastreams




not enough reliable metadata about
the observations

         11
Looking into the Data

        Air Pressure?




      Air Temperature?




12
Classifying Sensor Data




Unclassified input series
                                          Already classified time series

                       Representation
                            Classification
                              Metadata
                                     13
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
Deriving Semantic Metadata




15
Data Representation



Represent the data approximating
with fewer linear segments

Accuracy vs Numerosity




    16
Constant Approximation


          • Use constant segments for a subset of points
4.5

 4

3.5

 3

2.5

 2

1.5

 1
      0       10   20    30   40    50    60   70    80    90   100




                                     17
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

 4.1
4.05
  4
3.95
 3.9
3.85
 3.8
3.75
 3.7
3.65
       0       1   2   3   4   5   6   7   8   9   10




                                                          18
Piecewise Linear Approximation




ri                         hi+1



                   hi

li




     begi           endi




            Constructing segments




              19
Linear Approximations


We 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
Slope Distributions



ts1   adacdaaad   [5a,0b,1c,3d]

ts2   adabbaaad   [5a,2b,0c,2d]


ts3   adccdaaad   [4a,0b,2c,3d]



                       Distance measure
                       Classification




                      21
Use the representation for Classifying


Linear approximation
Compute distribution of the slopes
K-nearest neighbor classification
Training-Test datasets:
   SwissExperiment
   AEMET




                             22
Experiments SwissEx


Confusion matrix
Experiments AEMET


Confusion matrix
Evaluation AEMET




25
Evaluation AEMET




cf-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
Metadata Properties

cf-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.
Querying Metadata

SELECT ?sensor
WHERE {
 ?sensor a ssn:Sensor ;
           ssn:observes cf-property:air_temperature .}




SELECT ?stream ?observedProperty
WHERE {
 ?sensor a ssn:Sensor ;
          ssn:observes ?observedProperty .
 ?stream ssn:isProducedBy ?sensor .
 ?observedProperty qu:generalQuantityKind qu:temperature .}



                                28
Evaluation vs SAX




29
Evaluation vs SAX




30
How much data do we need?




31
Conclusions
Classify Sensor Data
  • Piecewise Linear Representation
  • Segment slope distributions
  • kNN classification


Generate Metadata
  • Observed properties
  • Potentially unknown metadata

Future work
  • Combine with tag disambiguation?
  • Use pattern mining for online queries
  • Other techniques, shapelets, use
    other parameters
                                  32
…Thanks


    Questions, please.




jp.calbimonte@upm.es


            33

More Related Content

Viewers also liked

Ptp 2012
Ptp 2012Ptp 2012
Ptp 2012
mapple2012
 
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAMESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
Sérgio Porfírio
 
Biodiesel in the Classroom
Biodiesel in the ClassroomBiodiesel in the Classroom
Biodiesel in the Classroom
Biodiesel Automotive
 
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
Maurílio Silva
 
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
Websec México, S.C.
 
B 20 Biodiesel Oil Lubrication
B 20 Biodiesel Oil LubricationB 20 Biodiesel Oil Lubrication
B 20 Biodiesel Oil Lubrication
Biodiesel Automotive
 
Biodiesel and Exhaust AfterTreatment
Biodiesel and Exhaust AfterTreatment Biodiesel and Exhaust AfterTreatment
Biodiesel and Exhaust AfterTreatment
Biodiesel Automotive
 
Diesel engines
Diesel enginesDiesel engines
Diesel engines
alexandramaria2771
 
Understanding the Diesel Engine
Understanding the Diesel EngineUnderstanding the Diesel Engine
Understanding the Diesel Engine
Biodiesel Automotive
 
Diesel engine
Diesel engineDiesel engine
Diesel engine
vigyanashram
 
Diesel engine
Diesel engineDiesel engine
Diesel engine
vigyanashram
 
Spanish Hotron Intro 2012
Spanish Hotron Intro 2012Spanish Hotron Intro 2012
Spanish Hotron Intro 2012
Michelle Hayden
 
I.c. engine
I.c. engineI.c. engine
I.c. engine
smilingshekhar
 
Diretec 2011
Diretec 2011Diretec 2011
Diretec 2011
mapple2012
 

Viewers also liked (14)

Ptp 2012
Ptp 2012Ptp 2012
Ptp 2012
 
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAMESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
ESPUMA DE POLIURETANO FLEXIVEL MOLDADA / POLYURETHANE FLEXIBLE MOLDED FOAM
 
Biodiesel in the Classroom
Biodiesel in the ClassroomBiodiesel in the Classroom
Biodiesel in the Classroom
 
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
Arcabouço para o Desenvolvimento de Aplicações de Realidade Aumentada para Di...
 
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
Protección web con ESAPI y AppSensor [GuadalajaraCON 2013]
 
B 20 Biodiesel Oil Lubrication
B 20 Biodiesel Oil LubricationB 20 Biodiesel Oil Lubrication
B 20 Biodiesel Oil Lubrication
 
Biodiesel and Exhaust AfterTreatment
Biodiesel and Exhaust AfterTreatment Biodiesel and Exhaust AfterTreatment
Biodiesel and Exhaust AfterTreatment
 
Diesel engines
Diesel enginesDiesel engines
Diesel engines
 
Understanding the Diesel Engine
Understanding the Diesel EngineUnderstanding the Diesel Engine
Understanding the Diesel Engine
 
Diesel engine
Diesel engineDiesel engine
Diesel engine
 
Diesel engine
Diesel engineDiesel engine
Diesel engine
 
Spanish Hotron Intro 2012
Spanish Hotron Intro 2012Spanish Hotron Intro 2012
Spanish Hotron Intro 2012
 
I.c. engine
I.c. engineI.c. engine
I.c. engine
 
Diretec 2011
Diretec 2011Diretec 2011
Diretec 2011
 

Similar to SSN2012 Deriving Semantic Sensor Metadata from Raw Measurements

SRBench Streaming RDF SPARQL Benchmark
SRBench Streaming  RDF SPARQL BenchmarkSRBench Streaming  RDF SPARQL Benchmark
SRBench Streaming RDF SPARQL Benchmark
Jean-Paul Calbimonte
 
SSN11: Semantic Sensor Data Search in a Federated Sensor Network
SSN11: Semantic Sensor Data Search in a Federated Sensor NetworkSSN11: Semantic Sensor Data Search in a Federated Sensor Network
SSN11: Semantic Sensor Data Search in a Federated Sensor Network
Jean-Paul Calbimonte
 
Myriam phd
Myriam phdMyriam phd
Myriam phd
iammyr
 
Linked Sensor Data 101 (FIS2011)
Linked Sensor Data 101 (FIS2011)Linked Sensor Data 101 (FIS2011)
Linked Sensor Data 101 (FIS2011)
Jean-Paul Calbimonte
 
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
Arne Bröring
 
Semantic Sensor Web
Semantic Sensor WebSemantic Sensor Web
Semantic Sensor Web
Anusuriya Devaraju
 
Exposing Real World Information for the Web of Things
Exposing Real World Information for the Web of ThingsExposing Real World Information for the Web of Things
Exposing Real World Information for the Web of Things
PlanetData Network of Excellence
 
Publishing consuming Linked Sensor Data meetup Cuenca
Publishing consuming Linked Sensor Data meetup CuencaPublishing consuming Linked Sensor Data meetup Cuenca
Publishing consuming Linked Sensor Data meetup Cuenca
Jean-Paul Calbimonte
 
Semantically enabled standard development
Semantically enabled standard developmentSemantically enabled standard development
Semantically enabled standard development
Laurent Lefort
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and Development
IJERD Editor
 
Data Visualization and Communication by Big Data
Data Visualization and Communication by Big DataData Visualization and Communication by Big Data
Data Visualization and Communication by Big Data
IRJET Journal
 
Sensors, Mappings and Queries in the Semantic Web
Sensors, Mappings and Queries in the Semantic WebSensors, Mappings and Queries in the Semantic Web
Sensors, Mappings and Queries in the Semantic Web
Jean-Paul Calbimonte
 
Sensors presentation-06a
Sensors presentation-06aSensors presentation-06a
Sensors presentation-06a
abhijitrao
 
1 Object tracking using sensor network Orla Sahi
1       Object tracking using sensor network Orla Sahi1       Object tracking using sensor network Orla Sahi
1 Object tracking using sensor network Orla Sahi
SilvaGraf83
 
MDM-2013, Milan, Italy, 6 June, 2013
MDM-2013, Milan, Italy, 6 June, 2013MDM-2013, Milan, Italy, 6 June, 2013
MDM-2013, Milan, Italy, 6 June, 2013
Charith Perera
 
Ingredients for Semantic Sensor Networks
Ingredients for Semantic Sensor NetworksIngredients for Semantic Sensor Networks
Ingredients for Semantic Sensor Networks
Oscar Corcho
 
Colored petri nets theory and applications
Colored petri nets theory and applicationsColored petri nets theory and applications
Colored petri nets theory and applications
Abu Hussein
 
Semantic Sensor Network Ontology: Description et usage
Semantic Sensor Network Ontology: Description et usageSemantic Sensor Network Ontology: Description et usage
Semantic Sensor Network Ontology: Description et usage
catherine roussey
 
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
The Air Force Office of Scientific Research
 
Real-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for SurveillanceReal-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for Surveillance
IRJET Journal
 

Similar to SSN2012 Deriving Semantic Sensor Metadata from Raw Measurements (20)

SRBench Streaming RDF SPARQL Benchmark
SRBench Streaming  RDF SPARQL BenchmarkSRBench Streaming  RDF SPARQL Benchmark
SRBench Streaming RDF SPARQL Benchmark
 
SSN11: Semantic Sensor Data Search in a Federated Sensor Network
SSN11: Semantic Sensor Data Search in a Federated Sensor NetworkSSN11: Semantic Sensor Data Search in a Federated Sensor Network
SSN11: Semantic Sensor Data Search in a Federated Sensor Network
 
Myriam phd
Myriam phdMyriam phd
Myriam phd
 
Linked Sensor Data 101 (FIS2011)
Linked Sensor Data 101 (FIS2011)Linked Sensor Data 101 (FIS2011)
Linked Sensor Data 101 (FIS2011)
 
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
Jirka - Integrating the ogc sensor web enablement framework into the ogc cata...
 
Semantic Sensor Web
Semantic Sensor WebSemantic Sensor Web
Semantic Sensor Web
 
Exposing Real World Information for the Web of Things
Exposing Real World Information for the Web of ThingsExposing Real World Information for the Web of Things
Exposing Real World Information for the Web of Things
 
Publishing consuming Linked Sensor Data meetup Cuenca
Publishing consuming Linked Sensor Data meetup CuencaPublishing consuming Linked Sensor Data meetup Cuenca
Publishing consuming Linked Sensor Data meetup Cuenca
 
Semantically enabled standard development
Semantically enabled standard developmentSemantically enabled standard development
Semantically enabled standard development
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and Development
 
Data Visualization and Communication by Big Data
Data Visualization and Communication by Big DataData Visualization and Communication by Big Data
Data Visualization and Communication by Big Data
 
Sensors, Mappings and Queries in the Semantic Web
Sensors, Mappings and Queries in the Semantic WebSensors, Mappings and Queries in the Semantic Web
Sensors, Mappings and Queries in the Semantic Web
 
Sensors presentation-06a
Sensors presentation-06aSensors presentation-06a
Sensors presentation-06a
 
1 Object tracking using sensor network Orla Sahi
1       Object tracking using sensor network Orla Sahi1       Object tracking using sensor network Orla Sahi
1 Object tracking using sensor network Orla Sahi
 
MDM-2013, Milan, Italy, 6 June, 2013
MDM-2013, Milan, Italy, 6 June, 2013MDM-2013, Milan, Italy, 6 June, 2013
MDM-2013, Milan, Italy, 6 June, 2013
 
Ingredients for Semantic Sensor Networks
Ingredients for Semantic Sensor NetworksIngredients for Semantic Sensor Networks
Ingredients for Semantic Sensor Networks
 
Colored petri nets theory and applications
Colored petri nets theory and applicationsColored petri nets theory and applications
Colored petri nets theory and applications
 
Semantic Sensor Network Ontology: Description et usage
Semantic Sensor Network Ontology: Description et usageSemantic Sensor Network Ontology: Description et usage
Semantic Sensor Network Ontology: Description et usage
 
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
Reinhardt - Adaptive Combinatorial Multimodal Sensing Physics & Methods - Spr...
 
Real-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for SurveillanceReal-Time Pertinent Maneuver Recognition for Surveillance
Real-Time Pertinent Maneuver Recognition for Surveillance
 

More from Jean-Paul Calbimonte

Towards Collaborative Creativity in Persuasive Multi-agent Systems
Towards Collaborative Creativity in Persuasive Multi-agent SystemsTowards Collaborative Creativity in Persuasive Multi-agent Systems
Towards Collaborative Creativity in Persuasive Multi-agent Systems
Jean-Paul Calbimonte
 
A Platform for Difficulty Assessment and Recommendation of Hiking Trails
A Platform for Difficulty Assessment andRecommendation of Hiking TrailsA Platform for Difficulty Assessment andRecommendation of Hiking Trails
A Platform for Difficulty Assessment and Recommendation of Hiking Trails
Jean-Paul Calbimonte
 
Stream reasoning agents
Stream reasoning agentsStream reasoning agents
Stream reasoning agents
Jean-Paul Calbimonte
 
Decentralized Management of Patient Profiles and Trajectories through Semanti...
Decentralized Management of Patient Profiles and Trajectories through Semanti...Decentralized Management of Patient Profiles and Trajectories through Semanti...
Decentralized Management of Patient Profiles and Trajectories through Semanti...
Jean-Paul Calbimonte
 
Personal Data Privacy Semantics in Multi-Agent Systems Interactions
Personal Data Privacy Semantics in Multi-Agent Systems InteractionsPersonal Data Privacy Semantics in Multi-Agent Systems Interactions
Personal Data Privacy Semantics in Multi-Agent Systems Interactions
Jean-Paul Calbimonte
 
RDF data validation 2017 SHACL
RDF data validation 2017 SHACLRDF data validation 2017 SHACL
RDF data validation 2017 SHACL
Jean-Paul Calbimonte
 
SanTour: Personalized Recommendation of Hiking Trails to Health Pro files
SanTour: Personalized Recommendation of Hiking Trails to Health ProfilesSanTour: Personalized Recommendation of Hiking Trails to Health Profiles
SanTour: Personalized Recommendation of Hiking Trails to Health Pro files
Jean-Paul Calbimonte
 
Multi-agent interactions on the Web through Linked Data Notifications
Multi-agent interactions on the Web through Linked Data NotificationsMulti-agent interactions on the Web through Linked Data Notifications
Multi-agent interactions on the Web through Linked Data Notifications
Jean-Paul Calbimonte
 
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition MetadataThe MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
Jean-Paul Calbimonte
 
Linked Data Notifications for RDF Streams
Linked Data Notifications for RDF StreamsLinked Data Notifications for RDF Streams
Linked Data Notifications for RDF Streams
Jean-Paul Calbimonte
 
Fundamentos de Scala (Scala Basics) (español) Catecbol
Fundamentos de Scala (Scala Basics) (español) CatecbolFundamentos de Scala (Scala Basics) (español) Catecbol
Fundamentos de Scala (Scala Basics) (español) Catecbol
Jean-Paul Calbimonte
 
Connecting Stream Reasoners on the Web
Connecting Stream Reasoners on the WebConnecting Stream Reasoners on the Web
Connecting Stream Reasoners on the Web
Jean-Paul Calbimonte
 
RDF Stream Processing Tutorial: RSP implementations
RDF Stream Processing Tutorial: RSP implementationsRDF Stream Processing Tutorial: RSP implementations
RDF Stream Processing Tutorial: RSP implementations
Jean-Paul Calbimonte
 
Query Rewriting in RDF Stream Processing
Query Rewriting in RDF Stream ProcessingQuery Rewriting in RDF Stream Processing
Query Rewriting in RDF Stream Processing
Jean-Paul Calbimonte
 
Toward Semantic Sensor Data Archives on the Web
Toward Semantic Sensor Data Archives on the WebToward Semantic Sensor Data Archives on the Web
Toward Semantic Sensor Data Archives on the Web
Jean-Paul Calbimonte
 
Detection of hypoglycemic events through wearable sensors
Detection of hypoglycemic events through wearable sensorsDetection of hypoglycemic events through wearable sensors
Detection of hypoglycemic events through wearable sensors
Jean-Paul Calbimonte
 
RDF Stream Processing and the role of Semantics
RDF Stream Processing and the role of SemanticsRDF Stream Processing and the role of Semantics
RDF Stream Processing and the role of Semantics
Jean-Paul Calbimonte
 
The Schema Editor of OpenIoT for Semantic Sensor Networks
The Schema Editor of OpenIoT for Semantic Sensor NetworksThe Schema Editor of OpenIoT for Semantic Sensor Networks
The Schema Editor of OpenIoT for Semantic Sensor Networks
Jean-Paul Calbimonte
 
Scala Programming for Semantic Web Developers ESWC Semdev2015
Scala Programming for Semantic Web Developers ESWC Semdev2015Scala Programming for Semantic Web Developers ESWC Semdev2015
Scala Programming for Semantic Web Developers ESWC Semdev2015
Jean-Paul Calbimonte
 
Streams of RDF Events Derive2015
Streams of RDF Events Derive2015Streams of RDF Events Derive2015
Streams of RDF Events Derive2015
Jean-Paul Calbimonte
 

More from Jean-Paul Calbimonte (20)

Towards Collaborative Creativity in Persuasive Multi-agent Systems
Towards Collaborative Creativity in Persuasive Multi-agent SystemsTowards Collaborative Creativity in Persuasive Multi-agent Systems
Towards Collaborative Creativity in Persuasive Multi-agent Systems
 
A Platform for Difficulty Assessment and Recommendation of Hiking Trails
A Platform for Difficulty Assessment andRecommendation of Hiking TrailsA Platform for Difficulty Assessment andRecommendation of Hiking Trails
A Platform for Difficulty Assessment and Recommendation of Hiking Trails
 
Stream reasoning agents
Stream reasoning agentsStream reasoning agents
Stream reasoning agents
 
Decentralized Management of Patient Profiles and Trajectories through Semanti...
Decentralized Management of Patient Profiles and Trajectories through Semanti...Decentralized Management of Patient Profiles and Trajectories through Semanti...
Decentralized Management of Patient Profiles and Trajectories through Semanti...
 
Personal Data Privacy Semantics in Multi-Agent Systems Interactions
Personal Data Privacy Semantics in Multi-Agent Systems InteractionsPersonal Data Privacy Semantics in Multi-Agent Systems Interactions
Personal Data Privacy Semantics in Multi-Agent Systems Interactions
 
RDF data validation 2017 SHACL
RDF data validation 2017 SHACLRDF data validation 2017 SHACL
RDF data validation 2017 SHACL
 
SanTour: Personalized Recommendation of Hiking Trails to Health Pro files
SanTour: Personalized Recommendation of Hiking Trails to Health ProfilesSanTour: Personalized Recommendation of Hiking Trails to Health Profiles
SanTour: Personalized Recommendation of Hiking Trails to Health Pro files
 
Multi-agent interactions on the Web through Linked Data Notifications
Multi-agent interactions on the Web through Linked Data NotificationsMulti-agent interactions on the Web through Linked Data Notifications
Multi-agent interactions on the Web through Linked Data Notifications
 
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition MetadataThe MedRed Ontology for Representing Clinical Data Acquisition Metadata
The MedRed Ontology for Representing Clinical Data Acquisition Metadata
 
Linked Data Notifications for RDF Streams
Linked Data Notifications for RDF StreamsLinked Data Notifications for RDF Streams
Linked Data Notifications for RDF Streams
 
Fundamentos de Scala (Scala Basics) (español) Catecbol
Fundamentos de Scala (Scala Basics) (español) CatecbolFundamentos de Scala (Scala Basics) (español) Catecbol
Fundamentos de Scala (Scala Basics) (español) Catecbol
 
Connecting Stream Reasoners on the Web
Connecting Stream Reasoners on the WebConnecting Stream Reasoners on the Web
Connecting Stream Reasoners on the Web
 
RDF Stream Processing Tutorial: RSP implementations
RDF Stream Processing Tutorial: RSP implementationsRDF Stream Processing Tutorial: RSP implementations
RDF Stream Processing Tutorial: RSP implementations
 
Query Rewriting in RDF Stream Processing
Query Rewriting in RDF Stream ProcessingQuery Rewriting in RDF Stream Processing
Query Rewriting in RDF Stream Processing
 
Toward Semantic Sensor Data Archives on the Web
Toward Semantic Sensor Data Archives on the WebToward Semantic Sensor Data Archives on the Web
Toward Semantic Sensor Data Archives on the Web
 
Detection of hypoglycemic events through wearable sensors
Detection of hypoglycemic events through wearable sensorsDetection of hypoglycemic events through wearable sensors
Detection of hypoglycemic events through wearable sensors
 
RDF Stream Processing and the role of Semantics
RDF Stream Processing and the role of SemanticsRDF Stream Processing and the role of Semantics
RDF Stream Processing and the role of Semantics
 
The Schema Editor of OpenIoT for Semantic Sensor Networks
The Schema Editor of OpenIoT for Semantic Sensor NetworksThe Schema Editor of OpenIoT for Semantic Sensor Networks
The Schema Editor of OpenIoT for Semantic Sensor Networks
 
Scala Programming for Semantic Web Developers ESWC Semdev2015
Scala Programming for Semantic Web Developers ESWC Semdev2015Scala Programming for Semantic Web Developers ESWC Semdev2015
Scala Programming for Semantic Web Developers ESWC Semdev2015
 
Streams of RDF Events Derive2015
Streams of RDF Events Derive2015Streams of RDF Events Derive2015
Streams of RDF Events Derive2015
 

SSN2012 Deriving Semantic Sensor Metadata from Raw Measurements

  • 1. 5th International Workshop on Semantic Sensor Networks at ISWC2012 Deriving 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. Sensor Observations Semantic metadata Annotations Sensor Raw Measurements Representation Characterize Classify Publish 2
  • 3. Streaming Sensor Data Data streams Continuous evaluation Timestamped tuples Time windows Do we know what we are sensing? 3
  • 5. The Sensor Web Universal, web-based access to sensor data 5
  • 6. Semantic Sensor Web “too much (streaming) data but not enough (tools to gain and derive) knowledge”* LinkedSensorData Sensor data publishing Linked Data LSM Sense2Web Semantic sensor metadata Sensor APIs ETALIS Semantic 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. SSN Ontology with other ontologies tool for modeling our sensor data ~what we are observing 7
  • 8. Sensor Metadata swissex: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. Sensor Observations swissex: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. Sensor Observations Heterogeneity Reuse this data? Publish as Linked Sensor Data? Query with SPARQL-Stream? 10
  • 11. Cosm/Pachube Datastreams not enough reliable metadata about the observations 11
  • 12. Looking into the Data Air Pressure? Air Temperature? 12
  • 13. Classifying Sensor Data Unclassified input series Already classified time series Representation Classification Metadata 13
  • 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
  • 16. Data Representation Represent the data approximating with fewer linear segments Accuracy vs Numerosity 16
  • 17. Constant Approximation • Use constant segments for a subset of points 4.5 4 3.5 3 2.5 2 1.5 1 0 10 20 30 40 50 60 70 80 90 100 17
  • 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 4.1 4.05 4 3.95 3.9 3.85 3.8 3.75 3.7 3.65 0 1 2 3 4 5 6 7 8 9 10 18
  • 19. Piecewise Linear Approximation ri hi+1 hi li begi endi Constructing segments 19
  • 20. Linear Approximations We 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. Slope Distributions ts1 adacdaaad [5a,0b,1c,3d] ts2 adabbaaad [5a,2b,0c,2d] ts3 adccdaaad [4a,0b,2c,3d] Distance measure Classification 21
  • 22. Use the representation for Classifying Linear approximation Compute distribution of the slopes K-nearest neighbor classification Training-Test datasets: SwissExperiment AEMET 22
  • 26. Evaluation AEMET cf-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. Metadata Properties cf-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. Querying Metadata SELECT ?sensor WHERE { ?sensor a ssn:Sensor ; ssn:observes cf-property:air_temperature .} SELECT ?stream ?observedProperty WHERE { ?sensor a ssn:Sensor ; ssn:observes ?observedProperty . ?stream ssn:isProducedBy ?sensor . ?observedProperty qu:generalQuantityKind qu:temperature .} 28
  • 31. How much data do we need? 31
  • 32. Conclusions Classify Sensor Data • Piecewise Linear Representation • Segment slope distributions • kNN classification Generate Metadata • Observed properties • Potentially unknown metadata Future work • Combine with tag disambiguation? • Use pattern mining for online queries • Other techniques, shapelets, use other parameters 32
  • 33. …Thanks Questions, please. jp.calbimonte@upm.es 33