Sensor failure-test in repeatedly performed Bayesian identification tasks in air surveillance
Max Kruger · 2014
Identification in an air surveillance system is applied to a large number of tracks and can be implemented by means of Bayesian classification. Performed in an automated system, there is a strong need to monitor the identification process and contributing sensors by the operator. This paper describes two sensor failure-tests based on frequencies' evaluation of conflicting evidence by statistical means. In a simulated air surveillance scenario, a Conflict Binomial and a Conflict Ratio Failure-Test are evaluated and compared, with particular respect to operationally relevant performance measures.