Using Bayesian inference for sensor management of air traffic control systems

Sensor management deals with the efficient resource allocation to meet mission objectives of the application, in the case air traffic control. A sensor schedule is constructed by integrating a Bayesian network with a particle swarm optimizer, which simultaneously meets the measurement accuracy and update rate, while minimizing the transmissions from the sensor. Bayesian networks automatically determine the management requirements for individual aircraft by monitoring the dynamically changing situations. BN is used to maintain the best overall performance possible from the entire sensor network system. In this paper, system performance with Bayesian networks is improved as much as 74.30% for highest priority of the 3 level priority system.