Opportunistic activity and context recognition systems do not presume a static sensor infrastructure that is defined at the design time of a system. They also do not have a fixed recognition goal that has to be accomplished. These systems rather make best use of the available sensor systems according to a sensing mission whereas the topology of a sensor network may change at runtime. To being able to configure the available sensor systems and to react on topological changes in the ambient sensor infrastructure goal-oriented sensing approaches capable of handling dynamic sensor setups have to be developed within the authors PhD-thesis. Author Keywords Activity and Context Recognition, Goal-oriented Sensing, Wireless Sensor Networks, Goal Processing. ACM Classification Keywords I.0 Computing Methodologies: General. General Terms Algorithms, Design, Theory.