Main research areas spanned in our investigation
Machine Learning & Inductive Reasoning
Machine Learning methods and systems based on symbolic and numerical approaches.
Integration in different fragments of first order logic for the
development of reasoning techniques under uncertainty.
Inductive Logic Programming:
Incremental and Multistrategy Learning: integration of induction, abduction, abstraction
Inductive methods for ontologies and Semantic Web representations (founded in description logics).
Similarity-based methods: distance and (dis)similarity measures: Nearest Neighbor, Kernels for structured representations.
Inductive frameworks for hybrid representation systems: DL+LP.
- Intelligent document processing: paper document acquisition and document image
understanding. Document understanding and text summarization.
- Machine learning and ontologies: Ontology learning: construction, refinement.
Inductive Methods for the Semantic Web: semantic web mining.
(Semantic) Web Services: discovery and retrieval
- Inductive methods for Bioinformatics
Data Mining & Knowledge Discovery in Databases
Analysis and synthesis of algorithms for inductive inference: classification and regression trees, causal inference, and induction of logic theories from numeric/symbolic data.
Knowledge discovery in databases.
Mining of Association rules.
- Intelligent document processing
- Trend Discovery, Sequence Mining, Temporal Associations
- Object-oriented databases maintenance: Map interpretation and spatial data mining
- Web mining and Intelligent interfaces
Knowledge Management & Personalization
Enterprise Content Management: RDF Knowledge Bases.
Information Retrieval: Text Mining and Categorization
Web-based applications. Personalization: user Profiling and recommendation.
- Digital libraries
- Internet and electronic commerce
- Content-based user profiling
- Personalization and e-Learning