Dmitry Pavlyuk
In: Kabashkin I., Yatskiv I., Prentkovskis O. (eds) Reliability and Statistics in Transportation and Communication. RelStat 2017. Lecture Notes in Networks and Systems, vol 36. Springer, Cham
DOI: 10.1007/978-3-319-74454-4_22
Keywords: Spatiotemporal big data, Urban traffic flows, Modelling, Forecasting
Available at Springer: REQUEST FULL TEXT Export citation: BibTeX RIS
Abstract
This paper contains a survey of spatiotemporal big data challenges in the area of urban traffic flow analysis. Existing sources and types of traffic flow data were reviewed and evidences that traffic flow data can be considered as spatiotemporal big data were provided. Current trends in spatiotemporal big data analytics and in urban traffic flow modelling and forecasting were consolidated and a list of joint emerging challenges was composed. The stated challenges cover different spatiotemporal aspects of big data and are linked to optimal time and space data resolution, spatial and temporal relationships in traffic data, computational complexity of spatiotemporal algorithms, fusion of traffic data from heterogeneous data sources into a single predictive scheme, and development of responsive streaming algorithms. The raised challenges are supported by an extensive literature review, and suggestions for future work are offered.