Channel capacity related power allocation for distributed sensor networks with application in object classification

This publication analyzes the power allocation problem for a distributed wireless sensor network which is based on ultra-wide bandwidth communication technology. The network is used to classify target objects. In the considered scenarios, the absence, the presence, or the type of an object is observed by the sensors independently. Due to noisy communication channels, the interfered observations are fused into a reliable global decision in order to increase the overall classification probability. An approach based on information theory that aims at maximization of the mutual information is employed. It enables the analytical allocation of the given total power to the sensor nodes so as to optimize the overall classification probability. Furthermore, we demonstrate the feasibility of object classification by using the introduced power allocation method in ultra-wide bandwidth signaling and energy-efficient systems.