An architecture for local decision support in ad hoc sensor networks

The Intelligent Job Site is becoming a reality as applications (e.g., RFID for materials tracking, laser scanning and GPS for surveying and layout) using sensors and mobile computing devices are being developed and deployed commercially. This creates an opportunity for workers to access sensors in an ad hoc manner as they move through a job site. However, re-tasking and re-use of sensor data in a dynamic setting presents significant challenges including ad hoc identification of sensors in a local environment, the generalization of sensor information, and the use of such dynamic info for decision support applications. All these tasks require coordinated advancement of a variety of information and communication technologies. To achieve a generalized approach to make use of local sensor data, this paper describes a three-layer architecture which abstracts functionality into three corresponding tiers: a layer for sensor communication that handles physical communication between devices; a middle-layer for data processing and abstraction of sensor data from specific devices; and a top layer for decision support applications. At each of the three tiers in the architecture the level of abstraction increases, allowing for development of decision support applications at the top level that are not directly tied to specific sensors or computing devices. This paper demonstrates the usefulness and versatility of the proposed three-tier architecture by describing two safety applications envisaged for the Intelligent Job Site.