Cloud Data Mining
Head of the Research Line
The work carried out in this research line exploits the cloud as a technological infrastructure that enables data exploration using advanced mining approaches. The cloud opens an array of possibilities in terms of algorithms and data processing, such as distributed, elastic and parallel processing. The big advantage lies in the large amount of data that will be possible to process. The areas that will be addressed include structured data (e.g., databases and OLAP cubes) as well as unstructured data (e.g., text and biological data). On the one hand, the advancement of data mining methods for cloud and big data will be pursued, and on the other hand, new products and services, with high industrial value, will be developed.
List of WPs
WP 3.1 | Data Mining for Systematic Reviews and Meta-Analyses in Health Sciences
The work carried out in this WP involves R&D activities in the field of evidence-based medicine, including topics such as systematic reviews and meta-analyses in several fields of health sciences, through data mining of biomedical literature and databases. The work will be carried out in close collaboration with the Mathematics and Medical Sciences departments at UBI, and associated health institutions.
WP Leader | Luísa Pereira
WP 3.2 | Big Text to Knowledge (BText2K)
The work carried out in this WP targets the extraction of knowledge from unstructured text, especially the huge amounts of text (“Big Text”) stored in, or flowing through, large infrastructures like a cloud or the Web. In particular, there is a high interest in the extraction of binary relations between named-entities and relations that characterize entities. This kind of relations are of great relevance, being fundamental for multiple advancements in Natural Language Processing, and also with many interesting applications in different areas of Artificial Intelligence.
WP Leader | João Cordeiro
WP 3.3 | Omics Data Analysis
The work carried out in this WP involves R&D activities in the field of health sciences in close collaboration with CICS-UBI, including multi-disciplinary projects addressing omics data, including genomics, transcriptomics, proteomics and metabolomics.
WP Leader | Manuel C. Lemos
WP 3.4 | Machine Learning Algorithms to Detect Disease Risk Factors
The work carried out in this WP is about using Cloud distributed Machine Learning algorithms to detect disease risk factors. The goal of the project consists of using both (Big Data) genetic and clinical information of patients to create prediction models, using state of-the-art algorithms (e.g. deep learning), that can accurately detect high-risk patients.