Loading…

Designing Data Validation Framework for Crowd-Sourced Road Monitoring Applications

With the wide availability of smartphone sensing and the Internet connections, mobile crowd sourcing (MCS) has become a promising paradigm for collecting opinions and providing services to the citizens. In the smart city context, crowd data, both in the form of their opinions and in the form of sens...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering Electrical Engineering, Electronics and telecommunication engineering, Computer engineering, 2022, Vol.103 (4), p.1083-1096
Main Authors: Saha, Jayita, Roy, Sathi, Das, Tanmoy Kr, Purkait, Kriti, Chowdhury, Chandreyee
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the wide availability of smartphone sensing and the Internet connections, mobile crowd sourcing (MCS) has become a promising paradigm for collecting opinions and providing services to the citizens. In the smart city context, crowd data, both in the form of their opinions and in the form of sensing data from their smartphones are very useful for scalable monitoring of resource demand and planning. Since these devices are portable, it is carried by almost every citizen, thus making them ubiquitous. However, the main bottleneck of such crowd intelligence-based services is data validation as opinions can be biased, influenced by some factors not relevant to the problem in focus. So, in this paper, a data validation framework utilizing machine learning techniques for mobile crowdsourcing applications is proposed. It is focused on MCS-based road monitoring applications. The idea of crowdsourced urban area road monitoring application(CURMA) presented in the paper is implemented and results show the crucial need for such data validation frameworks.
ISSN:2250-2106
2250-2114
DOI:10.1007/s40031-022-00713-x