A fog-assisted group-based truth discovery framework over mobile crowdsensing data streams

With the proliferation of mobile crowdsensing (MCS) and crowdsourcing, new challenges are emerging every day. Although crowdsensing has become a popular sensing paradigm to aggregate sensor readings from a variety of sources, data inconsistency has arisen as a serious challenge. Truth discovery (TD) has been developed as an effective method for reducing data inconsistency and as a validity assessment for conflicting data from various sources. In addition, MCS applications and services are moving beyond a single individual participant to community groups and are influenced by group behavior. To address these challenges in this paper, we propose a novel Fog-assisted Group-based Truth Discovery Framework over MCS Data Streams, an efficient TD system for real-time applications. Specifically, we first initialized the weights for the weight update process in TD with the participants' credibility level. Then, we developed a novel Two-layer Group-based Truth Discovery (TGTD) mechanism in which the first layer estimates the truth of the group's members and the second layer estimates the aggregated truth for the groups. We have conducted extensive experiments over synthetic and real-world datasets to prove the effectiveness and efficiency of our framework. The results indicate that TGTD achieves superior truth discovery accuracy compared to current streaming truth discovery approaches, while maintaining a reasonable running time. The organization of the streaming process within the fog architecture simulation is identified as an area for further investigation and future work.