Crowdsourcing, as an essential part in Internet of Vehicles (IoV), can provide vehicles with various functions such as road condition monitoring and path planning. The prevalence and heterogeneity of crowdsourcing devices, although enabling various emerging applications in IoV, makes it challenging to yield intelligent and flexible incentive and management framework, while ensuring optimal choice for all entities. Note that artificial intelligence (AI) algorithms could automatically select the significant features in the underlying data and globally find optimal solutions even for non-convex object functions. In this paper, we propose an AI-driven incentive scheme using a deep learning based reverse auction scheme, in order to achieve revenue-optimal, dominant-strategy incentive compatible objectives. The effectiveness of the proposed framework has been verified through extensive simulations.
Ai-Enhanced Incentive Design for Crowdsourcing in Internet of Vehicles
01.09.2019
952607 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
FedBeam: Reliable Incentive Mechanisms for Federated Learning in UAV-Enabled Internet of Vehicles
DOAJ | 2024
|