A system and method are provided that use context awareness with device-dependent training to improve precision while reducing classification latency and the need for additional computing, such as by relying on cloud-based processing. Moreover, the following can leverage signal analysis with multiple sensors and secondary validation in a multi-modal approach to track passive events that would otherwise be difficult to identify using classical methods. In at least one implementation, the system and method described herein can leverage low power sensors and integrate already available human behavior in modular algorithms isolating specific context to reduce user interact time and training to a minimum.