Self Organizing Maps for Distributed Localization in Wireless Sensor Networks

Providing an efficient localization system is one of the most important goals to be pursued if an efficient utilization of sensor networks has to be addressed. This paper proposes a novel localization system based on Kohonen ´s self organizing maps (SOMs), able to provide some Artificial Intelligence features to sensor nodes. A SOM is a particular neural network that learns to classify data without any supervision. In each sensor node, a SOM is implemented to evaluate the sensor node position, using a very little amount of storage and computing resources. In a scenario where thousands of sensor nodes are placed, this system evaluates the position of each sensor in a distributed manner, assuming a very little percentage of nodes knowing their actual position.