Big data challenges in transportation: A case study of traffic volume count from massive radio frequency identification (RFID) data.

Abstract

We are in an advancing stage of data acquisition and an even greater dynamic stage of dealing with big data. Data sizes have evolved over the years from a few kilobytes to Exabyte. The transportation engineer has also been caught up in the big data era and to efficiently analyze this massive data for maximum benefits, various challenges relating to data acquisition, data storage, data cleaning, data analysis and visualization has to be overcome. In this paper, we discuss these challenges and approaches to managing them with respect to massive Radio Frequency Identification data for traffic volume count in Nanjing, China. We recommended software, use analytical and visualization techniques like aggregation, graduated circular symbols and traffic count map to overcome big data challenges to produce peak hour, offpeak hour traffic volume counts and traffic count maps showing locations of low and high volume traffic. The paper, therefore, contributes to the management of big data by transportation engineers for traffic volume and congestion analysis.