Reliability-driven vehicular crowd-sensing: A Case study for localization in public transportation

This paper proposes a new framework for GPS-less identification of location of public transportation vehicles by using machine intelligence algorithms by exploiting the vehicular crowd-sensing concept. Since data trustworthiness is vital when data is crowd-solicited via various non-dedicated sensors, assessment and quantification of the trustworthiness of participating sensors plays a key role in the accuracy of the acquired information. To this end, we propose two trustworthiness-aware recruitment schemes for the non-dedicated sensors in a vehicular crowd-sensing environment: Reliability-driven naive recruitment (RDNR) and Reliability-driven exclusive recruitment (RDER). The former determines to use the data of a mobile device with a probability equal to the reliability of the device whereas the latter excludes the participating devices whose reliability scores are below a certain threshold. The data acquired from the recruited participant pool then undergoes an unsupervised machine learning module that is hosted in the cloud. We evaluate the performance of RDNR and RDER in comparison to each other and a non-restrictive recruitment mechanism which does not consider reliability of participants at all. Through simulations, we show that over 85% and 98% accuracy can be achieved in the worst and best cases, respectively while consuming less energy than GPS-based localization approaches.