EUBra-BIGSEA: Using Big Data to plan routes according to multiple criteria

The Polytechnic University of Valencia is at the helm of a joint project funded by the European Union and the Brazilian Ministry of Science, Technology and Innovation to harness the full potential of Big Data and provide tailor-made solutions that not only meet, but also anticipate an individual user’s changing needs.

A journey planner that considers factors such as cost, comfort, safety and duration, drawing on such as weather information and social media posts in real-time to recommend users the most efficient route.

This is one of the potential uses of the technology being developed in EUBra-BIGSEA, a European-Brazilian collaborative project led by the Universitat Politècnica de València (Polytechnic University of Valencia, UPV). Using the advanced cloud infrastructure management tools developed at the UPV’s Instituto I3M, BIGSEA will see the creation of a new Big Data analytics platform capable of processing large amounts of data in the shortest possible time and at minimum cost. The project’s case study is the aforementioned journey planner, designed specifically for the city of Curitiba, in the state of Paraná, Brazil, although the technology will be applicable to other cities and, indeed, other contexts. Specifically, the data processed in this case study includes geo-referenced meteorological data, information about transport links, motorway routes, as well as comments and posts from social networks, all of which are in constant flux.

Project coordinator and researcher at I3M, Ignacio Blanquer, explains: “The main challenge faced by the project is to get all of the information resources hosted in the cloud to [work together and] automatically adapt to the needs of the user […] We aim to offer a consistently high quality data processing service that will be the basis on which information is sent out to users in real-time”.

One step further

Beyond delivering information in real-time, though, BIGSEA has set itself an even bigger challenge: to get its cloud infrastructure to anticipate and adapt to changing user requirements before their needs even change, drawing on historic data on similar events in the past and machine learning models. This ensures that the information delivered to the user is of the highest possible quality at all times, by any standard.

As Blanquer points out, the main Brazilian project partner, Universidade Federal de Minas Gerais, stands alongside the world leaders in social media analysis. Brazil is also the second-highest ranked country in terms of how long its citizens spend on social media each day: around 3.3 hours per day on average, more than double that in Spain (1.6). Real-time social media mining is what will allow BIGSEA to stay ahead of user requirements, adapting the information sent to the user based on comments posted on social networks or any relevant behavioural patterns. Other European organisations taking part in BIGSEA alongside the UPV’s I3M research institute are: the Barcelona Supercomputing Center-Centro Nacional de Supercomputación (BSC), the Euro-Mediterranean Center on Climate Change (CMCC), Polytechnic University of Milan, the Univeristy of Coimbra and the British company Trust-It Services. Leading the Brazilian side of the collaboration we have the Universidade Federal de Minas Gerais, working with the participation of the Federal University of Campinha Grande, the Federal Technological University of Paraná, the State Univeristy of Campinas and IBM Research Brasil. EUBra-BIGSEA was one of the five projects selected from among 142 proposals submitted to the third joint Europe-Brazil call for proposals in Information and Communication Technologies, funded by the European Union and the National Network of Education and Research of Brazil (RNP).

Source: Universitat Politècnica de València