Core Concepts
The author proposes a recruitment strategy for mobile crowd sensing based on trustworthiness prediction using GCN, aiming to enhance task utility and worker satisfaction.
Abstract
The content discusses the importance of worker recruitment in collaborative mobile crowd sensing, focusing on trust relationships and abilities. It introduces the TSR algorithm to optimize worker selection, demonstrating superior performance compared to other strategies through extensive simulations.
Collaborative Mobile Crowd Sensing (CMCS) aims to improve data quality by enhancing teamwork among workers. Existing strategies overlook trust relationships between workers, impacting task utility evaluation. The paper introduces the TSR algorithm to recruit optimal worker sets based on abilities and trust values.
Privacy concerns in CMCS are addressed through high trust values between workers. The proposed strategy outperforms other methods in terms of effectiveness and efficiency, as demonstrated in simulation experiments on real-world datasets.
Stats
Extensive simulation experiments demonstrate the effectiveness of the proposed strategy, outperforming other strategies.
The TSR algorithm is proposed to rationally recruit a balanced multi-objective optimal task utility worker set for each task.
Four real-world datasets were used to verify the performance of the proposed strategy.
The Advogato dataset originates from an online social network for open-source developers.
The PGP dataset is derived from an encryption program and consists of four trustworthiness categories.