By way of example: every week, more than one thousand new papers reach the database of the European Laboratory for Particle Physics (CERN in French), in Switzerland, near Geneva, and considered nowadays to be an international model of scientific collaboration and one of the most important research centres in the world.
This fact has caused the search of new automatic multi-labelling classification systems to speed up the documentation process in databases as large as that of the CERN.
This is the case of the system created by Arturo Montejo Ráez, researcher of the Department of Computer Languages and Systems of the University of Granada [http://www.ugr.es] and professor of the Department of Computing of the University of Jaén whose work has been the object of a doctoral thesis supervised by professors Luis Alfonso Ureña López and Ralf Steinberger.
Montejo has proposed a solution based on techniques of Information Retrieval and Automatic Learning to solve the problem of multi-labelling in digital collections. His research work has focused on in documents of the field of High Energies Physics, creating a new documentation system which could be applied to other digital libraries.
The researcher centred on text categorization and classification, considering predefined key words to be categories assigned to the documents according to their semantic content. During the development of their work, carried out at the European Laboratory for Nuclear Research, the collection of documents revealed the existence of problems which had not been previously covered by the specialized literature.
“Base binary classifier”
The automatic assignment of key words to documents opens new possibilities in documental exploration, and has aroused the interest of the international scientific community. The system proposed by the researcher of the UGR [http://www.ugr.es] is a strategy of multi-labelling classification that can be constructed from automatic learning algorithms known as “base binary classifiers”. Besides, his fieldwork validates the hypothesis of that the integration of the bibliographical information available in digital libraries improves classification systems.
The algorithm proposed by Montejo is being applied by the CERN in their documental server [http://cds.cern.ch]. Other important digital libraries of certain international organizations have showed interest in using and integrating the system, due to the great amount of applications offered by automatic multi-labelling systems.
The European Laboratory for Particle Physics was founded in 1954 by twelve European countries, and at present has 20 member states. Apart from the scientists from the member states, scientists of 220 institutes and universities of non-member states are using their installations.
The member states are Austria, Belgium, Bulgaria, Czech Republic, Denmark, Finland, France, Germany, Greece, Hungary, Italy, the Netherlands, Norway, Poland, Portugal, Slovak, Spain, Sweden, Switzerland and the United Kingdom. The observer countries and organizations are the European Commission, India, Israel, Japan, Russia, Turkey, the UNESCO and the United States. The list of non-member countries involved in programs of the CERN are Algeria, Argentina, Armenia, Australia, Azerbaijan, Belarus, Brazil, Canada, People's Republic of China, Croatia, Cyprus, Estonia, Georgia, Iceland, Iran, Ireland, Mexico, Morocco, Pakistan, Peru, Romania, Serbia, Slovenia, South Africa, South Korea, Taiwan and Ukraine.
Antonio Marín Ruiz | alfa
Deep Learning predicts hematopoietic stem cell development
21.02.2017 | Helmholtz Zentrum München - Deutsches Forschungszentrum für Gesundheit und Umwelt
Sensors embedded in sports equipment could provide real-time analytics to your smartphone
16.02.2017 | University of Illinois College of Engineering
13.02.2017 | Event News
10.02.2017 | Event News
09.02.2017 | Event News
24.02.2017 | Life Sciences
24.02.2017 | Life Sciences
24.02.2017 | Trade Fair News