PROJECT TITLE :

VCAMS: Viterbi-Based Context Aware Mobile Sensing to Trade-Off Energy and Delay - 2018

ABSTRACT:

Monitoring context depends on continuous collection of raw knowledge from sensors that are either embedded in good mobile devices or worn by the user. But, continuous sensing constitutes a significant supply of energy consumption; on the other hand, lowering the sensing rate may cause missing the detection of critical contextual events. During this Project, we have a tendency to propose VCAMS: a Viterbi-based Context Aware Mobile Sensing mechanism that adaptively finds an optimized sensing schedule to make a decision when to trigger the sensors for data collection whereas trading off the sensing energy and the delay to detect a state change. The sensing schedule is adaptive from 2 aspects: one) the decision rules are learned from the user's past behavior, and 2) these rules are updated over real time whenever there is a important modification within the user's behavior. VCAMS is validated using multiple experiments, that include evaluation of model success when considering binary and multi-user states. We have a tendency to conjointly implemented VCAMS on an Android-based mostly device to estimate its computational prices beneath realistic operational conditions. Check results show that our proposed strategy provides better trade-off than previous state-of-the-art strategies below comparable conditions. Furthermore, the method provides 78 % energy saving compared to continuous sensing.