Questions about what is happening, what has happened, and what will happen are important for individuals, organizations, and society. Sensors everywhere can help to answer these questions, but sensors themselves only record values along certain dimensions (for instance what is the value for water flow, or freeway traffic load, or calorie burnt) at any given time. They do not record what is happening - that is they do not tell us what events are or have been or will be taking place. Interpreting sensor data in terms of event descriptions that make sense for different types of users has accordingly become a key research challenge.So far ontological studies in event inference have made good progress in software architectures and tools, but the field still lacks good supporting theories. The central topic of the meeting is: how can ontologies support analysis of sensor data. Another aim of the meeting is to create a representative survey of all state-of-the-art approaches to the event inference problem. The subtopics include but are not limited to:
Inferencing event descriptions from sensor data using either natural language (narrative descriptions) or formal language or a combination of both;
Event localization and event identification;
Using sensor data to enhance and validate event descriptions (including events in the past);
Using sensor data to predict events in the future;
The role of sensor data analysis in areas such as environmental modeling and forecasting, criminal intelligence, monitoring of large-scale social actions;
Fusion of sensor data with soft data deriving from human observations and social media.
Researchers from all fields who are interested in sensor analytics, ontology, and spatial sciences are invited to share thoughts and exchange ideas through lively discussions at the conference. A special issue will be published in the journal of Applied Ontology based on contributions to the conference and an open call.
1) Beard K. & Neville M. (2014). A Place and Event Based Context Model for Environmental Monitoring. Proceedings of the 1st International Workshop on Context-Awareness in Geographic Information Services, in conjunction with GIScience 2014, edited by Huang H., Hahn J., Claramunt C. & Reichenbacher T., September 23, 2014, Vienna, Austria. PDF
2) Devaraju A., Kuhn W. & Renschler C. (2015). A Formal Model to Infer Geographic Events from Sensor Observations. International Journal of Geographical Information Science, 29(1):1-27. PDF
3) Eastman, R., Schlenoff, C., Balakirsky, S., & Hong, T. (2013). A Sensor Ontology Literature. NIST Interagency/Internal Report (NISTIR) - 7908. PDF
4) Llaves A. & Kuhn W. (2014). An event abstraction layer for the integration of geosensor data. International Journal of Geographical Information Science, 28(5):1085-1106. PDF
5) Mackay S., Ewers E., Loranty M., & Kruger L. (2010). On the representativeness of plot size and location for scaling transpiration from trees to a stand. Journal of Geophysical Research: Biogeosciences (2005–2012), 115(G2). PDF
6) Rude A. & Beard K. High-level event detection in spatially distributed time series (2012). Springer, Lecture Notes in Computer Science 8728: 160–172. PDF
7) Salman D., Malyuta T., Hansen A., Cronen S., & Smith B. Integration of intelligence data through semantic enhancement (2011). PDF