Modelling road congestion using ontologies for big data analytics in smart cities

Intelligent Transport Systems are a vital component within Smart Cities but rarely provide the context that is required by the road user or network manager that will help support decision making. Such systems need to be able to collect data from multiple heterogeneous sources and analyse this information, providing it to stakeholders in a timely manner. The focus of this work is to use Big Data analytics to gain knowledge about road accidents, which are a major contributor to non-recurrent congestion. The aim is to develop a model capable of capturing the semantics of road accidents within an ontology. With the support of the ontology, selective dimensions and Big Data sources will be chosen to populate a model of non-recurrent congestion. Initial Big Data analysis will be performed on the data collected from two different sensor types in Greater Manchester, UK to determine whether it is possible to identify clusters based on journey time and traffic volumes.