Low power ambivalent computing system by machine learning

摘要

Problem to be solved: to provide a method, system and apparatus for handling an application in an ambient computing system.The method determines that the low power processing component has a particular sensor signal having a particular characteristic, and in response, the machine learning engine generates model output The inference path is given to the machine learning model using the sensor signal.When the model output of the machine learning engine matches an application specific condition, one or more of the other processing components are activated to perform a particular application corresponding to the application specific conditions.Diagram