Active Perception over Machine and Citizen Sensing
Download as PPTX, PDF0 likes479 views
A cross-country flight from New York to Los Angeles generates 240 terabytes of sensor data, and in the next few years sensor networks will produce 10-20 times more data than social media. The document discusses using ontologies and semantic web technologies to represent observations and perceptions from both human and machine sensors to enable situation awareness on the web. It describes models of the perception cycle where observers and perceivers exchange information using background knowledge to perceive entities and qualities. Applications are proposed for using these techniques for traffic and weather analysis.
Active Perception over Machine and Citizen Sensing
- 1. 1
- 2. A cross-country flight from New York to Los Angeles on a Boeing 737 plane generates a massive 240 terabytes of data- GigaOmni Media2
- 3. In the next few years, sensors networks will produce10-20 times the amount of generated by social media- GigaOmni Media3
- 4. Active Perception over Machine and Citizen SensingCory Henson and AmitShethKno.e.sis – Ohio Center of Excellence in Knowledge-enabled ComputingWright State University, Dayton, Ohio, USA4
- 5. To enable situation awareness on the Web, we must utilize abstractions capable of representing observations and perceptions generated by either people or machines.Webobserveperceive“real-world”5
- 6. For example, both people and machines are capable of observing qualities, such as redness.observesObserverQuality* Formally described in a sensor/observation ontology6
- 7. Sensor and Sensor Network (SSN) Ontologyhttp://www.w3.org/2005/Incubator/ssn/wiki/7
- 8. The ability to perceive is afforded through the use of background knowledge, relating observable qualities to entities in the world.Quality* Formally described in domain ontologies(and knowledge bases)inheres inEntity8
- 10. With the help of sophisticated inference, both people and machines are also capable of perceiving entities, such as apples.perceivesEntityPerceiver the ability to degrade gracefully with incomplete information
- 11. the ability to minimize explanations based on new information
- 12. the ability to reason over data on the Web
- 14. minimizeexplanationstractabledegrade gracefullyWeb reasoningWeb OntologyLanguage (OWL)Parsimonious Covering Theory (PCT)11
- 15. Conversion of PCT to OWL 2 (EL)ParsimoniousCovering Theory(Abductive Logic)*OWL-DLCory Henson, KrishnaprasadThirunarayan, AmitSheth, Pascal Hitzler. Representation of Parsimonious Covering Theory in OWL-DL. In: Proceedings of the 8th International Workshop on OWL: Experiences and Directions (OWLED 2011), San Francisco, CA, United States, June 5-6, 2011.1212
- 16. The ability to perceive efficiently is afforded through the cyclical exchange of information between observers and perceivers. Observersends observationsendsfocusTraditionally called the Perception Cycle(or Active Perception)Perceiver13
- 18. Cognitive Theory of Perception (timeline)1970’s - Perception is an active, cyclical process of exploration and interpretation - Nessier’s Perception Cycle1980’s - The perception cycle is driven by background knowledge in order to generate and test hypotheses. - Richard Gregory (optical illusions)1990’s - In order to effectively test hypotheses, some observations are more informative than others. - Norwich’s Entropy Theory of Perception15
- 19. Integrated together, we have an general model – capable of abstraction – relating observers, perceivers, and background knowledge.observesObserverQualitysends observationsendsfocusinheres inperceivesEntityPerceiver16
- 23. Detection of events, such as blizzards, from weather station observations on LinkedSensorDataWeather Application50% savings in resource requirements needed for detection20
- 24. thank you, and please visit us athttp://semantic-sensor-web.comKno.e.sis – Ohio Center of Excellence in Knowledge-enabled ComputingWright State University, Dayton, Ohio, USA21
Editor's Notes
- #2: Cory Henson (delivered 07/07/10)