Ai-enhanced incentive design for crowdsourcing in internet of vehicles

Yanlin Yue, Wen Sun, Jiajia Liu, Yuanhe Jiang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publication2019 IEEE 90th Vehicular Technology Conference, VTC 2019 Fall - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728112206
DOIs
StatePublished - Sep 2019
Event90th IEEE Vehicular Technology Conference, VTC 2019 Fall - Honolulu, United States
Duration: 22 Sep 201925 Sep 2019

Publication series

NameIEEE Vehicular Technology Conference
Volume2019-September
ISSN (Print)1550-2252

Conference

Conference90th IEEE Vehicular Technology Conference, VTC 2019 Fall
Country/TerritoryUnited States
CityHonolulu
Period22/09/1925/09/19

Keywords

  • Artificial intelligence
  • Auction
  • Crowdsourcing
  • Deep learning
  • Internet of vehicles

Fingerprint

Dive into the research topics of 'Ai-enhanced incentive design for crowdsourcing in internet of vehicles'. Together they form a unique fingerprint.

Cite this