A multi-dimensional framework for improving data reliability in mobile crowd sensing

Abstract

Mobile Crowd Sensing (MCS) has become a promising new data perception paradigm. It is to be able to easily submit the wrong or untrusted data for the malicious attackers in such an environment. This greatly affects the normal operation of the MCS system and the authenticity of task results. Therefore, ensuring the reliability of data is becoming a key research direction in MCS, especially for real-time application scenarios. For this purpose, we propose a multi-dimensional framework for improving data reliability, named MDF. It integrates three dimensions of temporal, spatial context and sensing measurement. Through a series of experiments, it is demonstrated that MDF outperforms existing methods.