CONTROL AND EXPLANATION IN A SIGNAL UNDERSTANDING ENVIRONMENT

To interpret sensor signals like images, image sequences, or continuou s speech the representation and use of task-specific knowledge is nece ssary. The paper presents a framework for the representation of declar ative and procedural knowledge using a suitable definition of a semant ic network. Based on that formalism a problem-independent control algo rithm for the interpretation of sensor signals is presented. It provid es both data-driven and model-driven control structures which can easi ly be combined to perform any mixed strategy. An explanation facility is available which makes the development of complex knowledge bases ea sier and increases the acceptance of such a knowledge-based analysis s ystem.