Application Fields


Transportation is a crucial sector for the society, both for citizens and the business sector. Regarding the transportation in the business world, the rapid advance of technology has made the logistic increasingly important in this area. The fact that anyone in the world can be well connected has led transport networks to be very demanding, something that was less important in the past. Today, a competitive logistic network can make the difference between some companies and others.

On the other hand, public transport is used by almost all the population and it directly affects the life quality of the people. In addition, there are different kinds of public transportation systems, each one with its own characteristics. Nonetheless, all of them share the same disadvantages, which are the finite capacity of the vehicles, the geographical area of coverage, and the service schedules and frequencies.

In the Joint Research Lab, we have a group of researchers with a wide experience in the design and development of ICT services for transportation. One of the most interesting services is the traffic prediction, both in short and long terms. In this sense, the traffic forecasting has a huge importance and utility for the current society, helping in different aspects of transportation and logistic, such as the relieve of traffic congestion, the reduction of pollutant gases emission, or the reduction of driving time. For facing this problem, we work with different data types and different development tools. We have expertise on the design and implementation of machine learning algorithms for dealing with this crucial aspect of the day to day transportation.

An additional aspect in which we have widely worked is the route plannification, both for public and private transport systems. In this regard, we work with different development tools such as Open Traffic or Open Trip Planner (both of the Open Source and working under Open Street Maps), and with different route planning algorithms. Regarding these algorithms, we have experience in the develpment of different kinds of heuristics, metaheuristics and hyperheuristics.


Due to the role of Big Data Analytics in the Industry 4.0 paradigm, our research interests also gravitate on the use of Machine Learning techniques to help early detection of defects and production failures, and thereby enabling their prevention and increasing productivity, quality, and agility benefits that have significant impact and competitive value. Under this paradigm, we mainly focused on some of its characteristics, such as Connection (sensors and networks), Cyber (model and memory), Content/Context (meaning and correlation), and Customization (personalization and value).


With the advent of Social Networks, the spectrum of tools and techniques capable of achieving insights from the interrelations between their users has increased considerably in the last decade. The acquired knowledge by virtue of such methods range from the quantification of the level of influence of a node within the network (centrality) to the discovery of shortest paths between a given pair of nodes, or the derivation of enriched ways to visualize a network given the weight distribution of its edges. Many of the functionalities that Social Network users enjoy nowadays build upon this algorithmic portfolio, with a late prominence noted around other practical goals (e.g. child abuse or the detection of radicalization risk).

Thus, finding groups from a set of interconnected nodes is a recurrent paradigm in a variety of practical problems that can be modeled as a graph, as those emerging from Social Networks. However, finding an optimal partition of a graph is a computationally complex task, calling for the development of approximative heuristics. While existing techniques for each of such tasks are manifold, the JRL has a valuable experience on the use of Evolutionary Computation and Swarm Intelligence as efficient algorithmic means to undertake new formulations of the aforementioned tasks and/or to deal with graph instances of unprecedented complexity. Community detection (clustering) over graphs is arguably one of the problems best exemplifying the upsurge of EC and SI to cope with their increasingly complex nature.


The industry in the Basque Country is the sector with the highest energy consumption with a consumption of 40% of the total (5.034ktep) in 2015, ahead of the transport sector that accounted for 38.2%. In addition, in the industry, the electricity vector accounted for 36.7% of energy consumption and natural gas in that year, 45.3%. The producing companies in the industry are therefore great consumers of energy. The progressive incorporation of Information and Communication Technologies (ICT) in industrial environments, in an Industry 4.0 scheme, is favoring learning about the implications of industrial operation processes in energy consumption. Plant managers, energy efficiency experts, energy service companies, systems integration engineers, suppliers of industrial equipment and other actors in the industrial sector are challenged to make the most of the Industry 4.0 paradigm that is being Deploying, applying Energy Efficiency Strategies, sponsored by the Regulation and Regulation such as Energy Efficiency Directive, or the deployment of smart electric and thermal meters.

In this regard, there are increasingly developments and implementations of solutions based on ICT technology towards the reduction of energy consumption, with the consequent reduction of fixed and variable productive costs, the improvement of the performance of equipment and processes, technological innovation, optimization and allocation of resources and increased competitiveness. The objective is to integrate the full potential from data analytics capabilities in the productive processes to promote energy efficiency in industrial environments, acquire knowledge on how energy is used by the consumers, industrial or household to better plan the estimation of the Energy Demand by identifying the load patterns, load peaks, peak shitable power, … Through the application of advanced data analytics techniques (real-time time series prediction on GPU, tensorflow, SPARK, docker containers), advanced visualization techniques (Dataviz, D3.js), and whatever comes up enable a wide range of new value-added services for the entire energy demand and supply value chain. The data insights will unlock savings opportunities and help businesses provide greater value.


Organizations today are inundated with myriads of network connections and traffic flows, as well as Cybersecurity events that require analysis and potentially, remediation. The sheer volume of traffic and events as well as the complexity of today’s hybrid cloud networks makes it impractical to have human beings attempting to analyze all the network and cybersecurity data being collected and making decisions based on this data.

This way, Cybersecurity is one of the main aspects to consider in the development of new technologies that process such sensitive data as personal information, control commands of a production plant or bank transactions. Hackers use their knowledge of technology to exploit resources, attack the system in order to make it fall or adquire personal data from webs and enterprises. Although there are several ways to detect attacks, hackers are not usually predictable. In fact, one of the main problems is that they are very sophisticated and do not use any attack pattern, making the model unable to work correctly. In addition, the lack of labeled attack data makes their detection a difficult task to carry out.

At the Joint Research Lab our goal is to develop an artificial intelligence capable to detect real-time attacks sensitive to changes over time, making the system self-sufficient to apply the most suitable action for each attack type. Otherwise, the wide use of artificial intelligence models open up to hackers a new way to detect and exploit their weaknesses, making them fail or cheating the input in order to obtain the desired output. In this field we developed many works looking into how the models could be improved and reach more robust and efficient performance.