ABSTRACT
Human beings involve in a vast variety of activities within a very diverse context. A specific context can be extracted by a smartphone application, which acquires relevant data through built-in sensors. A desired activity within the context is then inferred by successful algorithmic implementations. Unfortunately, all of these operations put a heavy workload on the smartphone processor and sensors. Constantly running built-in sensors consume relatively much more power than a smartphone does for fundamental functions such as calling or text messaging. Therefore, mobile device batteries do not last a long time while operating sensors simultaneously.
