Real Time Feature Streams

Abstract

<p>Sensors are increasingly being deployed for continuous monitoring of physical phenomena, resulting in avalanche of sensor data. Current sensor data streams provide summaries (e.g., min., max., avg.) of how phenomena change over time; however, such summaries are of little value to decision makers attempting to attain an insight or an intuitive awareness of the situation. Feature-streams, on the other hand, provide a higher-level of abstraction over the sensor data and provide actionable knowledge useful to the decision maker. This work presents an approach to generate feature-streams in real-time. This is accomplished through the application of ontological domain knowledge in order to integrate multiple, multi modal, heterogeneous low-level sensor data streams and infer the existence of real-world events like Blizzard, RainStorm etc. The generated feature-streams are publicly accessible on the Linked Open Data (LaD) Cloud.</p><p>This presentation occurred at the Wright State University Campus-Wide Celebration of Research, Scholarship and Creative Activities on April 8, 2011</p>