Projects

These are our ongoing projects:

Perception is the process by which an individual selects, organizes and interprets received stimuli to give them a meaning. This project addresses the selection, organization and interpretation of results of Big Data analysis through Semantics. The term "Big Data" refers to data that can not be processed or analyzed using traditional techniques. Big Data analysis allows to extract information from these data. Many software solutions around the Apache Hadoop project are solving encountered problems through this and other complementary projects. Ideally, these advances allow to easy the access o Big Data, bringing it closer to SMEs, but the rapid development of these technologies and the lack of qualified professionals currently make SMEs have difficulties to take advantage of those technologies. The building of framewoks aimed at Big Data analysis, which allow reusing of solutions and algorithms, will make these technologies more accessible. Business Intelligence or BI comprises a set of strategies and tools focused on managing and creating knowledge through the analysis of existing data in an organization. BI tools are based on the use of an information system that is built with different data from production process, with information related to the business and economic data. This set of tools and methodologies have in common information accessibility, decision-making support, and focus to the end user. The full interconnection between the results of Big Data analysis and BI has to deal with the problem of establishing the relationship between these results and the data models used by technical analysis and dashboards of BI applications. The automatic interpretation of results of the Big Data analysis, by exposing their semantics and preserving the context of how they have been produced, are some of the challenges to be addressed when trying to add these results to business processes. In this scenario, the concept of Smart Data emerges. It is defined as the result of the process of analysis performed to extract relevant information and knowledge from Big Data, including context information and using a standardized format. By context we mean all the relevant (meta) information to interpret the analysis results. This will lead to the enforceability of these results and thus facilitating their interpretation, the easy integration with other structured data, the integration of the Big Data analysis system with the BI systems, the interconnection (in a standardized way, at a lower cost and a higher accuracy and reliability) of third parties algorithms and services, etc. The PERCEPTION project proposed here aims at integrating the techniques and results of Big Data analysis with a metadata layer of the data being analyzed, of the analysis technique, and of the domain where this is applied, by introducing the concept of Smart Data as basic idea to break the barriers to access to Big Data technologies.
Resources: 
Research lines: 
(Smart) Big Data
Linked Data approach has its origin in Semantic Web, proposing a real and practical use of the Semantic Web technologies. This technology is producing large amounts of public data in domains sushc as Life Sciences. This project aims at taking advantage of such data for producing useful technology and tools for Systems Biology.
Resources: 
This project aims at developing a collaborative platform as a seed for the development of Big Data Analytics applications. The main aim of this platform is to put the Big Data technology closer to the developers and the SMEs.
Resources: 
Research lines: 
Big Data
E-COMPASS project offers to SME Associations an opportunity to provide to their online SME members real time and on-demand web-based applications that independent SMEs could not afford or have the business capacity for ordering customized applications from large IT and software providers. Objectives: - to extract generally-applicable patterns of fraudulent activity based on real transaction data available from online SME merchants. - to improve the transparency and readability of the automatic fraud detection process, so that the SMEs can easily interpret the final risk scoring of each order on the grounds of several suspicious characteristics or associations suggested by the system. - to create a dynamic fraud-detection framework being able to adapt to new, possibly unknown, types of malicious activities that are possible to occur during real-time operation - to develop a mathematical algorithm that classifies and links available products and services, pricing strategies, consumer habits and social reputation for fostering SME sales - to apply well-known statistical analysis, integrating three different sources of information: offer side, social side and consumer side.
Research lines: 
Big Data
Bioledge EU Project
The BIOLEDGE proposal is in response to the following topic of the 5th call for proposals in the EU FP7 Cooperation Work Programme: Food, agriculture and fisheries, and biotechnology: Increasing the accessibility, usability and predictive capacities of bioinformatics tools for biotechnology applications (KBBE-2011.3.6-01).
Research lines: 
Text Mining; Data Mining; Protein Production
AELID:Asociación Española para Linked Data
The Spanish Association for Linked Data tries to go further the state-of-art related to Linked Data in Spain and Europe. Moreover, it tries to contribute to a set of researchers and entrepeneurs in order to facilitate the exchange of knowledge, expertise, information and formation.