Reshaping Mobile Crowd Sensing using Cross Validation to Improve Data Credibility

TL;DR

This paper introduces a cross validation method for mobile crowd sensing that leverages a validating crowd to enhance data credibility, providing a lightweight, adaptable solution for improving truth verification in IoT data collection.

Contribution

It proposes a novel cross validation approach using a validating crowd and a privacy-aware algorithm, enhancing data credibility without redesigning existing MCS systems.

Findings

Significantly improves data credibility in MCS datasets.

Effectively verifies obscure and hidden truths.

Operates as a lightweight plug-in for practical deployment.

Abstract

Data credibility is a crucial issue in mobile crowd sensing (MCS) and, more generally, people-centric Internet of Things (IoT). Prior work takes approaches such as incentive mechanism design and data mining to address this issue, while overlooking the power of crowds itself, which we exploit in this paper. In particular, we propose a cross validation approach which seeks a validating crowd to verify the data credibility of the original sensing crowd, and uses the verification result to reshape the original sensing dataset into a more credible posterior belief of the ground truth. Following this approach, we design a specific cross validation mechanism, which integrates four sampling techniques with a privacy-aware competency-adaptive push (PACAP) algorithm and is applicable to time-sensitive and quality-critical MCS applications. It does not require redesigning a new MCS system but rather functions as a lightweight "plug-in", making it easier for practical adoption. Our results demonstrate that the proposed mechanism substantially improves data credibility in terms of both reinforcing obscure truths and scavenging hidden truths.