Alexandra Moraru Carolina Fortuna Jozef Stefan Institute Slovenia - - PowerPoint PPT Presentation

▶
alexandra moraru carolina fortuna jozef stefan institute
SMART_READER_LITE
LIVE PREVIEW

Alexandra Moraru Carolina Fortuna Jozef Stefan Institute Slovenia - - PowerPoint PPT Presentation

Nov 03, 2022 207 likes •345 views

Using Semantic Annotation for Knowledge Extraction from Geographically Distributed and Heterogeneous Sensor Data Alexandra Moraru Carolina Fortuna Jozef Stefan Institute Slovenia Dunja Mladeni Outline Introduction System

slide-1
SLIDE 1

Using Semantic Annotation for Knowledge Extraction from Geographically Distributed and Heterogeneous Sensor Data

Alexandra Moraru Carolina Fortuna Dunja Mladenić Jozef Stefan Institute Slovenia

slide-2
SLIDE 2

Outline

  • Introduction
  • System architecture
  • Case Study: Participatory Sensing
  • Conclusions
slide-3
SLIDE 3

Introduction

Internet of Things Internet of Things Sensor Web Sensor Web Participatory sensing Participatory sensing

  • Scalability
  • Mobility
  • Interoperability
  • Scalability
  • Mobility
  • Interoperability
  • Web accessible sensor

network and archive sensor data

  • Web accessible sensor

network and archive sensor data

  • Access to various types
  • f data
  • Problems may appear in

understanding the data

  • Solution: providing

semantic context

  • Access to various types
  • f data
  • Problems may appear in

understanding the data

  • Solution: providing

semantic context

slide-4
SLIDE 4

Semantic Annotation

  • Annotating sensor descriptions with concepts

from an ontology

  • Machine understanding of the sensors

descriptions and data streams

  • Enables reasoning mechanism for selecting

streams for processing or monitoring

slide-5
SLIDE 5

Semantic Sensor Web

System Architecture

Knowledge Base Ontology Logic Rules Knowledge Base Ontology Logic Rules Inference Engine Publishers

Sensor Descriptions Sensor Data Semantic Annotations

? A

slide-6
SLIDE 6

Case Study: Participatory Sensing

  • Pachube

– platform that supports storing and sharing sensor data (stream of measurements). – structured metadata describing the sensor data streams (including natural language description and tags).

www.pachube.com

  • Cyc

– general ontology and a knowledge base for representing common sense knowledge – organized by contexts (microtheories)

www.opencyc.org

slide-7
SLIDE 7

Case Study: Participatory Sensing

<title> IJSSensor</title> <status>live</status> <location domain="physical" exposure="indoor"> <lat>46.0425085163033</lat> <lon>14.4882792234421</lon> </location> <data id="0"> <tag>Temperature</tag> <unit type="basicSI" symbol="°C">Celsius</unit> </data> Individual: IJSSensor isa: Sensor hasDataStream: IJSSensor-Data1 hasDomain: Physical hasExposure: Indoor latitude: (Degree-UnitOfAngularMeasure 46.0425085163033) longitude: (Degree-UnitOfAngularMeasure 14.4882792234421) Individual: IJSSensor-Data1 isa: DataStream hasUnitOfMeasurement: DegreeCelsius measures: Temperature

slide-8
SLIDE 8

Case Study: Participatory Sensing

<title> IJSSensor</title> <status>live</status> <location domain="physical" exposure="indoor"> <lat>46.0425085163033</lat> <lon>14.4882792234421</lon> </location> <data id="0"> <tag>Temperature</tag> <unit type="basicSI" symbol="°C">Celsius</unit> </data> Individual: IJSSensor isa: Sensor hasDataStream: IJSSensor-Data1 hasDomain: Physical hasExposure: Indoor latitude: (Degree-UnitOfAngularMeasure 46.0425085163033) longitude: (Degree-UnitOfAngularMeasure 14.4882792234421) Individual: IJSSensor-Data1 isa: DataStream hasUnitOfMeasurement: DegreeCelsius measures: Temperature

slide-9
SLIDE 9

Case Study: Participatory Sensing

Domain Tag Number of

  • ccurrences

Cyc Concept Temperature related tags temperature 336 Fever temp 32 Temporary Worker celsius 293 Degree Celsius Power consumption related tags electricity 389 Electricity watts 34 Watt Distinct tags Data streams Total 2238 9466

Frequent tags for data streams descriptions in Pachube

slide-10
SLIDE 10

Searching for Sensors

  • Which are the sensors that measure

temperature in Ljubljana?

(and (isa ?X Sensor) (hasDataStream ?X ?DS) (measures ?DS Temperature) (distanceBetween ?X CityOfLjubljanaSlovenia (Kilometer ?DIST)) (lessThan ?DIST 10))

slide-11
SLIDE 11

Reasoning with Sensor Data

  • Detection of anomalous data measurements
  • data streams measuring temperature
  • Mediterranean region
  • Summer time
  • Temperature measurements below a 10 °C

are considered anomalous

  • for an outdoor exposure of the sensing device
slide-12
SLIDE 12

Reasoning with Sensor Data

(implies (and (isa ?SENSOR Sensor) (sensorMeasurmentsInterval ?SENSOR ?INT) (temporalBoundsContain ?SEASON ?INT) (isa ?SEASON SummerSeason) (hasRegionLocation ?SENSOR ?REGION) (hasClimateType ?REGION MediterraneanClimateCycle) (hasExposure ?SENSOR Outdoor) (hasDataStream ?SENSOR ?DS) (measures ?DS Temperature) (valueOf ?DS (DegreeCelsius ?C)) (lessThan ?C 10)) (anomalousMeasurments ?SENSOR ?DS))

slide-13
SLIDE 13

Conclusions & Future Work

  • Semantic annotations can provide context for the

sensor measurements and observations

  • We proposed and discussed a system architecture

for automatic annotation

– a too general ontology will not be able to successfully annotate all sensor descriptions

  • Future Work

– provide more specific context for the concepts used in sensor annotation – virtual sensor composition