LIBNOVA RESEARCH Labs
LIBNOVA has focused since its beginnings on developing the most advanced digital preservation platform: LIBSAFE.
In 2017, LIBNOVA RESEARCH LABS was created, to coordinate the lines of research to be followed in technological innovation within the company. The concluding research results have a direct impact on the digital preservation platform LIBSAFE.
Always focusing on the end-user, this laboratory aims to simplify the tasks of digital preservation by the application of Artificial Intelligence techniques such as the automation of ingesting processes, the creation of workflows, the analysis of the content of digital objects, etc.
The priority research lines of LIBNOVA Research Labs are:
- Artificial Intelligence – Machine Learning (Neural Networks).
- Intelligent Agents.
- Optimised Trustworthy Storage.
- Recommendation Engine.
Project: NEW CATALOGUING TECHNIQUES USING ARTIFICIAL INTELLIGENCE (CDTI IDI – 20180287)
The general objective of this project is to develop an advanced autonomous system for content analysis and automated classification of digital files.
This development will focus on algorithms based on the latest advances in Artificial Intelligence (AI) and on the use of artificial neural networks (ANN) for content classification, in such a way as to achieve full automation of the file ingestion workflow, in a Digital Preservation process.
The solution will allow the automatic classification of digital objects, especially those with visual or textual content, and with the capacity to generate the metadata that accompanies each object to proceed with its inclusion in the preservation system.
This system will include an automated analysis and classification process of the information that arrives both in the form of visual objects or images and in text files.
ARCHIVER Project: ARCHIVING AND PRESERVATION FOR RESEARCH ENVIRONMENTS – Grant agreement No 824516
The general objective of this project (a CERN-led consortium which includes several of the top European research-related organizations) is to build the next generation solution for research datasets archiving and preservation at the multi-petabyte scale.
Preserving research data has some unique challenges, making it really complex to achieve without proper processes and tools. Managing the provenance, solving the reproducibility problems, or aligning the data sets with the best practices are key areas to address, with many communities involved.
Building on top of our LIBSAFE platform and working together with the University of Barcelona, the Spanish National Research Council, and Giaretta Associates, our proposal has been selected to participate in the project (with 4,8M€ total funding for several years).
The resulting products will become part of the European Open Science Cloud catalogue (EOSC).