Artificial Intelligence Group (Prof. Stuckenschmidt)

Our group conducts fundamental and applied research in knowledge representation formalisms with a focus on reasoning techniques for information extraction and integration. Our work is centered around:

  • Standard reasoning including description logic reasoning and non-standard reasoning techniques (explanations and debugging techniques)
  • Combining Probabilistic reasoning and Utility Theory with Description Logics
  • Applications in various domains (web data integration and management, semantic web, ontology matching, context-aware applications, Business Process Management etc.)  

People

Professors

Postdoctoral Researchers

Researchers

PhD Students

Alumni

Selected Publications

Markov Logic Reasoning:

  • Melisachew Wudage Chekol, Jakob Huber, Christian Meilicke, Heiner Stuckenschmidt : Markov Logic Networks with Numerical Constraints. In: Proceedings of the 22nd European Conference on Artificial Intelligence (ECAI 2016), The Hague, Netherlands.
  • Jan Noessner, Mathias Niepert and Heiner Stuckenschmidt. RockIt: Exploiting Parallelism and Symmetry for MAP Inference in Statistical Relational Models. In: Proceedings of the Twenty-Seventh AAAI Conference on Artificial Intelligence, July 14-18, 2012, Bellevue, Washington, USA; 739-745. AAAI Press, Menlo Park, Calif., 2013

 

Activitity Recognition:

  • Daniele Riboni, Timo Sztyler, Gabriele Civitarese and Heiner Stuckenschmidt: Unsupervised Recognition of Interleaved Activities of Daily Living through Ontological and Probabilistic Reasoning. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '2016), Heidelberg, Germany.
  • Rim Helaoui, Daniele Riboni and Heiner Stuckenschmidt. A probabilistic ontological framework for the recognition of multilevel human activities. In: The 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp '13, Zurich, Switzerland, September 8-12, 2013; 345-354. ACM, New York, NY, 2013.

Ontology Matching:

Projects

  • MWK Project: A Virtual Open Science Collaboration Environment
  • ZIM Project: A motio-visual Sensor System for Spare Part Logstics
  • DFG Project: Matching Representations at different Levels of Granularity
  • SFB 884: Political Economy of Reforms
  • Different Industry Projects

Software and Data

  • ALCOMO (a tool for repairing ontology alignments)
  • Rockit (a query engine for Markov Logic)
  • ELOG (a reasoner for log-linear description logics)
  • NELL2DBpedia (an evaluation gold standard for linking NELL entities to DBPedia instances)

Publications

Dissertation

  1. Arnab Kumar Dutta. Automated Knowledge Base Extension Using Open Information. Dissertation, , Mannheim, 2016.
  2. Rim Helaoui. On Leveraging Statistical and Relational Information for the Representation and Recognition of Complex Human Activities. Dissertation, , Mannheim, Germany, 2016.

Conference Item

  1. Nico Potyka, Erman Acar, Matthias Thimm and Heiner Stuckenschmidt. Group decision making via probabilistic belief merging. In: 25th International Joint Conference on Artificial Intelligence, New York, USA, 9-15 July 2016 [?]; tba. AAAI Press, New York, NY, 2016.
  2. Timo Sztyler and Heiner Stuckenschmidt. On-body localization of wearable devices : an investigation of position-aware activity recognition. In: 2016 IEEE International Conference on Pervasive Computing and Communications : PerCom 2016, Sydney, Australia, March 14-19, 2016; 1-9. IEEE Computer Society, Piscataway, NJ, 2016.

Master and Bachelor Theses

The DFG funds a new research project "Matching Representations at different levels of granularity" with approx. 270.000,- Euro over the next 3 years....

more

We are looking for Master candidates that would be interested in writing their Master thesis in the field of innovative technologies in logistics.  ...

more

Im Rahmen der Veranstaltung KI werden unter anderem grundlgende Verfahren zur Entwicklung einer Spiele KI vorgestellt. Wer die Veranstaltung besucht...

more