Sequential detection/isolation of abrupt changes with some applications
Abstract
The quickest change detection/isolation (multidecision) problem is of im- portance for a variety of applications. Efficient statistical decision tools are needed for detecting and isolating abrupt changes in the properties of stochastic signals and dynamical systems, ranging from on-line fault di- agnosis in complex technical systems to detection/classification in radar, infrared, and sonar signal processing. The early on-line fault diagnosis (detection/isolation) in industrial processes helps in preventing these pro- cesses from more catastrophic failures. The problem of on-line target detec- tion/classification is important when detecting and classifying a type of an abruptly appearing target.