A New Localization Scheme in Sensor Networks

摘要

Physical location is an important attribute of a sensor's data stream in a large number of sensor network applications. Manual measurement for obtaining location does not scale and are error-prone, and equipping sensors with GPS is often expensive. In many outdoor urban environments, and most indoor environments, GPS is not available Sensor networks can therefore benefit from a self-configuring method where nodes cooperate with each other, estimate local distances to their neighbors, and coverage to a consistent coordinate assignment. In the paper a neural network is trained with precise localized nodes coordinate training set and localize any unknown node physical location. A common properties: 1-determine node - anchor distances by Received Signal Strength Indicator(RSSI) and 2-node-anchor coordinates , are used as data training set input vector.