OFFER DEADLINE14/06/2019 12:00 - Europe/Brussels
EU RESEARCH FRAMEWORK PROGRAMMEH2020 / Marie Skłodowska-Curie Actions
ORGANISATION/COMPANYUniversidad de Jaén
DEPARTMENTTIC-207 Intelligent Systems and Data Mining (SIMIDAT)
Description of Hosting Institution (UJA – Spain)
Jaén University (UJA) was created in 1993 and is in the Top 50 of the world’s best young universities according to THE (Times Higher Education). This ranking analyzes aspects such as teaching, research work, the university’s international outreach, or integration into industry. Besides, the UJA has received the distinction of Campus of International Excellence in the fields of Agrifood (CEIA3) and Climate Change (CamBio), plus it also leads the Andalusian CEI project on historical heritage PatrimoniUN10.
Jaén University has five faculties (Social and Legal Sciences; Humanities and Education Sciences; Health Sciences; Experimental Sciences and Social Work) and two higher polytechnic schools for engineering (Linares and Jaén). In turn, these centers are organized into 35 departments. It also has three Postgraduate educational centers (Doctorate School, Advanced Study Center in Modern Languages and Postgraduate Study Center).
In regards to its research, there are five specialized centers at Jaén University. Besides, the full picture of the over 100 UJA groups covers the following research fields of expertise (https://www.ujaen.es/servicios/ofipi/uja-ri-expertise): Agrifood (AGR); Biology (BIO); Health (CTS); Social Sciences, Business, Law (SEJ); Physics, Chemistry, Mathematics (FQM); Humanities (HUM); Natural Resources and Environmental Sciences (RNM); Information and Communications Technology (TIC); and Engineering Production Technology (TEP).
As far the UJA hosting offer is concerned, Prof. MARÍA JOSÉ DEL JESÚS DÍAZ (firstname.lastname@example.org) would be willing to host post-doctoral researchers that are eventually funded through the H2020 MSCA-IF 2019 call for applications to be part of the following research team:
UJA hosting research group (https://bit.ly/2V7RH6Q)
SIMIDAT research group consists of Computer Science Department staff researching on the develop of intelligent systems for the extraction of useful knowledge from large data bases using fuzzy systems, neural networks, evolutionary systems and hybrid systems:
- Predictive data mining (classification, regression, modelling, temporal series).
- Descriptive data mining (pattern or trend detection, association rules, subgroup discovery, clustering).
- Web mining.
SIMIDAT develops applications for medicine, economics, marketing, banking, agroindustry and the web, among other areas.
The research group is trained to face problems of extracting interesting and novel information in large databases using fuzzy systems, neural networks, evolutionary and hybrid systems. In Medicine, allows the extraction of information that relates patients’ symptoms with diagnoses, detection of outlier groups, or characterization of similar groups, exceptional groups or emerging patterns for medical study. In engineering, data mining methods are used to face modelling or optimization problems. In economics and finance, allows to characterize customers in order to study their suitability for certain financial products, or help in decision-making processes. Web mining methods allow to extract useful information to characterize customers browsing e-commerce sites or web pages, with the aim of structuring information in the most appropriate way to the user.
Progress in devices for the generation and transmission of information makes data grow in volume and complexity. Therefore Data Science methods must advance towards new proposals in classification, time series prediction and subgroup description, towards developments for tasks as emerging pattern mining and exceptions, and also towards proposals that properly face more complex problems, such as data streaming, unbalanced data or multilabel data.
Computational intelligence techniques have been profusely applied in Data Science for representation and knowledge extraction or optimization: Fuzzy rule based systems, evolutionary learning or neural networks, to mention some examples of paradigms that allow the design of knowledge extraction algorithms, both independently and in combination. The problems addressed in Data Science, especially in real data analysis, usually represent a higher level of complexity. In these situations, Deep Learning is a technique with current factors that enhance its use in the development of new Data Science models: the development of hardware and software technologies for the distributed processing of information, the increase in the generation and storage of huge volumes of data, and the advances in information processing.
This project focuses in the development of Data Science models for complex problems including unbalanced classification, multilabel, data stream analysis and massive data, using Computational Intelligence techniques and including learning architectures from Deep Learning.
Special attention will be paid to the transfer of the methods developed, applying them to problems in areas such as biomedicine, biotechnology, renewable energy and business.
CV, Motivation letter and Summary of project proposal (250 words) by 14th June 2019 to email@example.com. Further information regarding the application requirements can be found at https://ec.europa.eu/research/mariecurieactions/actions/individual-fellowships_en & https://ec.europa.eu/info/funding-tenders/opportunities/portal/screen/opportunities/topic-details/msca-if-2019.
The responsibility for the hosting offers published on this website, including the hosting description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.