Evaluation and augmentation of traffic data including Bluetooth detection system on arterials

• Published in: Journal of intelligent transportation systems Vol. 25; no. 6; pp. 561 - 573
• Main Authors: Gong, Yaobang, Abdel-Aty, Mohamed, Park, Juneyoung
• Format: Journal Article
• Language: English
• Published: Philadelphia Taylor & Francis 08.10.2021; Taylor & Francis Ltd
• Subjects: arterial; Augmentation; Bayesian analysis; Bluetooth; Bluetooth detection system; evaluation; Flow distribution; Highway access ramps; Performance evaluation; Private sector; private sector data; Real time; Reliability analysis; Statistical inference; Traffic data; Traffic flow; Traffic information; Traffic management; Trajectory analysis
• ISSN: 1547-2450; 1547-2442
• DOI: 10.1080/15472450.2019.1632707

Recently, traffic agencies have implemented Bluetooth detection systems (BDS) on arterials to collect traffic data and purchased data from private sector companies such as HERE, INRIX, and TomTom for real-time traffic monitoring and long-term traffic system management and performance evaluation. However, the quality and reliability of the aforementioned two data sources are subject to rigorous evaluation. This study utilized high-resolution GPS trajectory to evaluate data from private sector, HERE and BDS of a principal arterial corridor in Orlando, FL, USA. The results showed that the accuracy and reliability of BDS data are better than private sector data on the study corridor, which might be credited to a better presentation of the bimodal traffic flow pattern on signalized arterials. In order to improve the quality of private sector data, information about bimodal traffic flow was extracted by a finite mixture model from historical BDS data and incorporated with the real-time private sector data by a Bayesian inference framework. The evaluation of the augmented data showed that the augmentation framework is effective for the most part of the corridor except for segments highly influenced by traffic from or to the expressway ramps where evaluation datasets might have some bias.