An Unlicensed Taxi Identification Model Based on Big Data Analysis

Abstract

Social networks and mobile networks are exposing human beings to a big data era. With the support of big data analytics, conventional intelligent transportation systems (ITS) are gradually changing into data-driven ITS (D ² ITS). Along with traffic growth, D ² ITS need to solve more real-life problems, including the issue of unlicensed taxis and their identification, which potentially disrupts the taxi business sector and endangers society safety. As a remedy to this issue, a smart model is proposed in this paper to identify unlicensed taxis. The proposed model consists of two submodel components, namely, candidate selection model and candidate refined model. The former is used to screen out a coarse-grained suspected unlicensed taxi candidate list. The list is taken as an input for the candidate refined model, which is based on machine learning to get a fine-grained list of suspected unlicensed taxis. The proposed model is evaluated using real-life data, and the obtained results are encouraging, demonstrating its efficiency and accuracy in identifying unlicensed taxis, helping governments to better regulate the traffic operation and reduce associated costs.