01 September 2020 → Ongoing
- Data mining
- Database systems and architectures
- Ontologies, data curation and text mining
- Information, knowledge and uncertainty
Nowadays, digital information sources are growing tremendously. A major problem is that 'Big Data' collections cannot always be handled efficiently by conventional information management systems. Possible reasons for this are that the data collection is too large, that the data are too complex or contain to many imperfections and that these data cannot be processed quickly enough. More and more organizations are making great efforts to efficiently collect, organize and manage their data. The research within DDCM (Database, Document and Content Management) is aimed at supporting these efforts. To achieve this goal, new technologies are being researched and developed with the aim to efficiently deal with the many data and database challenges arising from the challenges of the Big Data world and the natural, heterogeneous and imperfect/uncertain nature of information. An important part of the research focuses on the development of new techniques for measuring, improving and presenting thequality of data. Partial aspects are • linking and integration of data stemming from heterogeneous sources, • deduplication of data sources, • use of rules (edit rules, functional dependencies, ...) to ensure consistency, • techniques for data recovery (imputation, correction, …), • analysis of the quality of news sources, • handling context (e.g. in crowd-sourcing), • efficient storage of temporal data, • quality and ease of use of databases and database schemes, and • veracity of Big data. The group also has expertise in making databases, documents and multimedia archives better accessible. This part of the research deals, among others, with • efficient querying of Big Data, • flexible database querying, • data anonymization and pseudonymization, • linking and semantic analysis of textual data, and • measuring and improving FAIRness (Findability, Accessibility, Interoperability and Reusability) of data(bases). Finally, DDCM is expert in computational intelligence techniques for data management, data analysis and decision support. The research group has extensive experience with projects in the biomedical, pharmaceutical and legal domains.