CHARACTERISATION OF THE BARRIERS AND LIMITATIONS ON UTILISATION OF BIG DATA IN TRANSPORT: THE LEMO PROJECT
The transport sector has continuously collected and analysed massive amounts of data, such as data from timetables, traffic news and air schedules. However, recent developments in the quantity, complexity and availability of such big data collected from and about transport systems, together with advances in information and communication technology, are presenting new opportunities to create more efficient and smarter transport and traffic systems for people and freight (Akerkar 2013). Also, ‘opening up’ data in transport by making it more widely available, and linking it with data from other sectors, is the part of the European strategy to improve transparency and encourage economic growth (Akerkar 2018). In the transport sector, the volume of data has increased due primarily to the prevalent use of digital technologies inter alia to efficiently manage operations and improve customer experience (Teoh et al. 2018). For instance, the extensive use of mobile devices generates rich-locational data from the travellers themselves and the vehicles. Infrastructure, environmental and meteorological monitoring systems also produce data related to transport operations and users. The data velocity has increased because of advanced communications technology & media and its improved processing capability & speed. The variety of transport‐related data has significantly increased. Modern trains report internal system telemetry in real-time from anywhere, and it is possible to acquire information about all crew members and passengers. The veracity refers to the quality, provenance and trust of the data. For deriving knowledge out of volumes of data, the accuracy of the data sources needs to be evaluated as well. Lastly, the value is a potential gain for an organisation when exploiting the data.