Download presentation
Presentation is loading. Please wait.
Published byCamron Waters Modified over 9 years ago
1
Performing event detection over real-time sensor data using ontology-driven approaches CSIRO LAND AND WATER Jonathan Yu | Research software engineer Environmental Information Systems, CLW Highett 14 May 2013
2
Outline Background: Event detection over real-time sensor data Capturing machine readable semantics – ontologies Enabling user-based events detection using ontology- driven approaches 2 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
3
Performing event detection over real-time sensor data Real-time observations are increasingly becoming available through sensor networks Reporting, monitoring, analysis Examine events that happen in a sensor network and get notifications Mitigate risk in the environment Improve management response times Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 3 | WQWeatherFlow Sensor Network
4
Water quality issues... Example events in this domain: Total nitrogen conc. in a river > X mg/L Dissolved oxygen conc. at sensor < Y mg/L Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 4 |
5
Undetected sewer rising mains pipe failures... Direct costs: water service providers ($ mil. per event) Indirect costs: social, environmental ($10k - $1 mil. per event) Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 5 |
6
Sewer rising mains case study Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 6 | Example event: Flow rate > 100 l/s
7
Sensor middleware - Global Sensor Network (GSN) Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu WQWeather Flow Sensor Network GSN Virtual Sensor (WQ) Virtual Sensor (Flow) Virtual Sensor (Aggr.) End users User Interface 7 |
8
Stepped notifications: 20 = high risk Using GSN for event detection on sewer rising mains Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu (Low risk) (High risk) Stepped Notifications Flow observations Simple Moving Average Looking for when flow exceeds a preset threshold over the Simple Moving average 8 |
9
Existing workflow: real-time event detection High level entry for an end user e.g. Scientists and managers Inefficient Knowledge hidden behind code or in people’s heads - implicit semantics Barrier for reusability Possible inconsistencies Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 9 | CurationCoding Analysis, Monitoring, Management Sensor Middleware (GSN) Sensor Network End users Programmers
10
Problem of data heterogeneity, integration Multiple datasets Often multiple data schemas, formats, field names, conventions The use of the observation property “Flow rate” Flow FLOW_RATE RATE_OF_FLOW_L_per_s Need a mechanism for consistent use of semantics Map to shared and commonly understood definitions Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 10 |
11
Capturing semantics, not just syntax Syntax of a language refers to the structure or grammar Semantics of a language refers to the meaning E.g. “Colorless green ideas sleep furiously.” Syntactically correct Semantically meaningless/inconsistent Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 11 | Zzzzzz...
12
Enable capture and consistent use of semantics Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 12 | Observation event at Flow Sensor X Observation event at Flow Sensor X Flow PVC Pipe at Clunies Ross Street PVC Pipe at Clunies Ross Street 100 litres per second Flow sensor X Flow rate sensing Has an observation result Some result Has value Produced by implements observes Has observation property Has feature of interest Observation event at WQ sensor Lake Burley Griffin Another result 10mg/L WQ meter Dissolved oxygen sensing Dissolved oxygen conc. Observation Feature of interest Sensor Output Observation Value Sensor Sensing Property
13
Ontologies Enable specification of semantics e.g. Concepts, relationships, logic assertions Provides ability to refer to ‘Flow rate’ concept (semantics), rather than FLOW_RATE (syntax) Machine readable/processable Using Web Ontology Language (OWL) W3C standard – “semantic web” Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 13 | implements observes Sensor Sensing Property Observation Sensor Output Has an observation result Produced by
14
Leverage ontology tools Query languages like “SPARQL” –SPARQL Protocol and RDF Query Language –For querying RDF statements which OWL builds upon –E.g. Find all sensors that observe flow rate Triple stores for storing RDF and ontology statements Ontology reasoners –Automated consistency checking –Inference engines All men are mortal, Socrates is a man => Socrates is mortal All sewer pipe bursts near rivers cause some environmental damage, Pipe X is near River Y, Pipe X has a pipe burst event => River X has caused some environmental damage at River Y Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 14 |
15
Enabling “user-based” real-time event detection Enable capture of user-defined semantics of events & reference sensors consistently 1)Sensor network system semantics described (e.g. Flow rate sensor is located at X) 2)Domain of interest semantics described (e.g. Flow is an observable property) 3)Event semantics described(e.g. Flow rate at sensor#1 > 100 l/s) 4)Machine-readability: for rendering in user interfaces & code generation Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 15 | Sensor Middleware (GSN) Sensor Network End users ?
16
Return notifications from triggered events with metadata based on ontology semantics e.g. The sewer rising main has a problem due to Ontology-driven event detection system Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 16 | Sensor Middleware (GSN) Sensor Network End users Ontology-enabled User Interface Ontologies Semantic Sensor Net. Ontology Domain Ontology Annotates available sensors and their capabilities e.g. Flow rate sensor data at Location X Generate code for event detection using event constraint semantics e.g. FLOW_RATE > 100 l/s Populate user interface elements based on domain semantics and sensor network annotations. Allow users to define event constraints
17
Semantic Sensor Network Event- detection WQ domain Urban water domain WQ user Urban water user Mid-Upper ontologies Application ontologies Domain ontologies User ontologies Representing domains and applications ??? 17 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
18
Event Detection Ontology def’s: Event Rule, Value Constraints, Units 18 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
19
Domain ontologies (uwda:) - Sensors 19 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
20
Event rule definition instances Rule IDObserved property Value constraint Feature of interest Observed By (Sensor) 1Flow 2 > 100 l/s 3Flow> 100 l/sPipe A 4Flow> 100 l/sPipe Sensor A-1 5Flow> 100 l/sPipe APipe Sensor A-1 20 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
21
Event dashboard - User interface demo for urban water domain Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 21 |
22
Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 22 |
23
Ontology APIs Ontology-driven user interface Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 23 | Sensor Middleware (GSN) Ontology-enabled User Interface Triple store (User ontologies) Ontology Reasoner Ontology definitions End users Query/Rule engines Presentation Widgets (Standard web forms)
24
Advantages of ontology-driven approach End users can focus more on exploring real-time datasets Semantics are explicitly specified and transferrable User interface allows domain ontologies to be interchangeable Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 24 | CurationCodingAnalysis, Monitoring, Management CurationCoding Analysis, Monitoring, Management
25
Fusing real-time events with domain knowledge Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 25 | Knowledge Base Sensor Network Real-time data Event of Interest Query knowledge base (domain knowledge) Notifications e.g. Populate knowledge base with parameterised historical pipe failure data. Infer likelihood of pipe failure based on physical attributes and known operating environment
26
Modelling the feature of interest – pipe materials 26 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
27
Modelling the burst events 27 | Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu
28
Event detections using dynamic and static info Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 28 | > 200 PSI + Pipe material is PVC and Risk level of pipe is A (good) (Dynamic) (Static) Notification: Location: Pipe X Risk of burst: LOW
29
Event detections using dynamic and static info Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 29 | > 200 PSI + Pipe material is PVC and Risk level of pipe is E (bad) (Dynamic) (Static) Notification: Location: Pipe X Risk of burst: HIGH
30
Summary Availability of real-time sensor data presents many potential applications Ontologies offer a means to capture semantics of a domain of discourse Ontology-driven approaches can assist user-definition of events over a given sensor network and consistent use of domain, application, sensor network semantics Shown how real-time events can be combined with domain knowledge for context sensitive event detection using ontologies Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 30 |
31
Future work Notification handling Messaging queue systems Attaching metadata based on event rule semantics More complex events Event semantics Incorporate processing-filters User studies to evaluate the user interface Deployments on actual sensor networks Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 31 | A B Event Smoothing function Email / SMS Database Execute workflow Existing alert systems Ontology-enabled User Interface Sensor Network
32
Questions? Performing event detection over real-time sensor data using ontology-driven approaches | Jonathan Yu 32 |
33
Land and Water Scott Gould Research Projects Officer t +61 3 9252 6103 escott.gould@csiro.au wwww.csiro.au/clw ICT Centre Kerry Taylor Principal Research Scientist t+61 2 6216 7038 ekerry.taylor@csiro.au wwww.csiro.au/ict Land and Water Donavan Marney Research team leader t +61 3 9252 6585 edonavan.marney@csiro.au wwww.csiro.au/clw LAND AND WATER Thank you Land and Water Jonathan Yu Research Software Engineer t+61 3 9252 6440 ejonathan.yu@csiro.au wwww.csiro.au/clw Land and Water Paul Davis Research Scientist t +61 3 9252 6310 epaul.davis@csiro.au wwww.csiro.au/clw Land and Water Brad Sherman Research Scientist e Brad.Sherman@csiro.au wwww.csiro.au/clw
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.