Document Type


Publication Date



The increased availability of sensor data presents opportunities for machine-assisted analytics, reporting and exploration of the sensed environment. Sensor networks provide the ability to observe physical phenomena in real-time and provide useful information to help conservation and management of environmental resources. Thus, exploring these real-time datasets can provide valuable insights for informing policy and decision support in domains such as water quality monitoring, early warning disaster detection, and physical asset degradation monitoring. However, the semantic meaning, format and interface heterogeneity of the sensors and sensor observations are barriers to effective discovery and analysis of events. We propose ontology-driven approaches for performing event detection over real-time sensor data. In this paper, we apply linked data approaches using sensor and domain ontologies for describing sensor observations, event constraints and triggered event notifications for detecting failure in pressure sewers. Specifically, we present a prototype event detection system that implements the above approach for detecting multi-stage fracture failure of PVC and Asbestos Cement pressure sewer mains, that remotely monitor sensor data (i.e. pump flow and wet well levels) and produces event notifications based on sensor observation semantics. The methodology explores how new uses (and additional value) can be found for the large volumes of hydraulic sensor data that organisations such as water utilities already gather in business-as-usual practices.


Session S1-02, Special Symposium: Real-time Simulation Modeling in Urban Water Systems



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.