MeT

Abstract

A semantic sensor network describes the physical world using the metadata obtained from a sensor network. In this paper, we present our design and implementation of MeT, a real world oriented metadata management system for semantic sensor networks. MeT generates metadata either statically based on the application semantics, or dynamically using inference rules. It then constructs relationships between physical objects through these metadata. The sensor devices in MeT include RFID tags, position sensors and Motes. The users can query MeT about physical objects through either a Graphic User Interace, or Robovie, a communication robot. We give several concrete examples of querying physical objects in MeT to demonstrate the functionality of our system.