Local Pattern Detection

Local patterns are a phenomenon observable in many different domains. A global model explains most of the data sufficiently well, but fails for some local subspaces, which cannot simply be explained by noise. One way to design models in such domains is to use a composition of a global model and one or more local models. The latter are valid only for subsets of the data, for which they differ significantly from the global model. A major advantage of such composed models lies in their higher interpretability compared to refined and hence more complex global models.

Projects

SFB 475 subproject A4

Staff

Rüping, Stefan

Past Master Thesis

• Entdeckung häufiger Episoden und repräsentativer Episode-Regeln in Ereignis-Sequenzen (Shaabani, Nuhad)
• Lokale Modelle in Jahresabschlussdaten (Liebe, Miguel)
• Lokalle Modellierung zur Zeitreihenprognose (Scheidler, Anne)

Publications

Liebe/2008a	Liebe, Miguel. Lokale Modelle in Jahresabschlussdaten. Technische Universität Dortmund, 2008.
Mierswa/etal/2008a	Mierswa, Ingo and Morik, Katharina and Wurst, Michael. Handling Local Patterns in Collaborative Structuring. In Masseglia, Florent and Poncelet, Pascal and Teisseire, Maguelonne (editors), Successes and New Directions in Data Mining, pages 167 -- 186, IGI Global, 2008.
Berthold/etal/2007a	Berthold, Michael and Morik, Katharina and Siebes, Arno. Introduction -- Parallel Universes and Local Patterns. In Berthold, Michael and Morik, Katharina and Siebes, Arno (editors), Parallel Universes and Local Patterns, No. 07181, Internationales Begegnungs- und Forschungszentrum für Informatik (IBFI), Schloss Dagstuhl, Germany, 2007.
Morik/Wurst/2007a	Morik, Katharina and Wurst, Michael. Multi-Aspect Tagging for Collaborative Structuring. In Michael R. Berthold and Katharina Morik and Arno Siebes (editors), Parallel Universes and Local Patterns, No. 07181, Internationales Begegnungs- und Forschungszentrum für Informatik (IBFI), Schloss Dagstuhl, Germany, 2007.
Morik/etal/2005c	Morik, Katharina and Boulicaut, Jean-François and Siebes, Arno. Local Pattern Detection. Vol. 3539, Springer, 2005.
Morik/Koepcke/2005a	Morik, Katharina and Köpcke, Hanna. Features for Learning Local Patterns in Time-Stamped Data. In Katharina Morik and Jean-Francois Boulicaut and Arno Siebes (editors), Local Pattern Detection: International Seminar, Dagstuhl Castle, Germany, April 12-16, 2004, Revised Selected Papers, Vol. LNCS 3539, pages 98--114, Springer, 2005.
Rueping/2005c	Rüping, Stefan. Learning with Local Models. In Local Pattern Detection, pages 153-170, Springer, 2005.
Scholz/2005a	Scholz, Martin. Knowledge-Based Sampling for Subgroup Discovery. In Morik, Katharina and Boulicaut, Jean-Francois and Siebes, Arno (editors), Local Pattern Detection, Vol. LNAI 3539, pages 171--189, Springer, 2005.
Morik/2002a	Morik, Katharina. Detecting Interesting Instances. In Hand, David J. and Adams, Niall M. and Bolton, Richard J. (editors), Proceedings of the ESF Exploratory Workshop on Pattern Detection and Discovery, Vol. 2447, pages 13-23, Berlin, Springer, 2002.