Abstract: A mobile device includes a plurality of sensors, each with one or more costs associated with it. In order to reduce the cost associated with using the sensors to infer information about the device's current context, a sensor manager first collects readings from relatively low-cost sensors, and attempts to infer the device's context based on these readings. If the context cannot be unambiguously determined (within an acceptable degree of tolerance) using the low-cost sensor readings, the sensor manager activates one or more higher-cost sensors to identify the current context. In some instances, if the higher-cost sensor is still not adequate to determine the context, one or more even higher-cost sensors are activated. The weighting of the various costs associated with the sensors can be adjusted based on previous and/or predicted contexts.

Abstract: A mobile device includes a plurality of sensors, each with one or more costs associated with it. In order to reduce the cost associated with using the sensors to infer information about the device's current context, a sensor manager first collects readings from relatively low-cost sensors, and attempts to infer the device's context based on these readings. If the context cannot be unambiguously determined (within an acceptable degree of tolerance) using the low-cost sensor readings, the sensor manager activates one or more higher-cost sensors to identify the current context. In some instances, if the higher-cost sensor is still not adequate to determine the context, one or more even higher-cost sensors are activated. The weighting of the various costs associated with the sensors can be adjusted based on previous and/or predicted contexts.