Dynamic Quantification of Activity Recognition Capabilities in opportunistic Systems

Opportunistic activity and context recognition systems draw from the characteristic to use sensing devices according to a recognition goal at runtime that just happen to be available instead of pre-defining them at the design time of the system. Whenever a user and/or application states a recognition goal at runtime to the system, the available sensing devices configure to an ensemble which is the best available set of sensors for a specified recognition goal. This paper presents an approach how machine learning technologies (classification, fusion and anomaly detection), that are integrated in a prototypical opportunistic activity and context recognition system (referred to as the OPPORTUNITY Framework) can be applied to define a metric value that quantifies the ensemble’s capabilities according to a recognition goal and evaluates the approach with respect to the requirements of an opportunistic system (e.g. ensemble configuration and reconfiguration at runtime).