Ludwig-Maximilians-Universität München Institut für Informatik Lehr- und Forschungseinheit für Datenbanksysteme

University of Munich Institute for Computer Science Database and Information Systems

E nvironment for Deve L oping K DD-Applications Supported by  I ndex-Structures

[ Background | Release History | Bug Reports | Agenda | Contact | Contributors | Publications ]

Data mining research leads to many algorithms for similar tasks. A fair and useful comparison of these algorithms is difficult due to several reasons:

• Implementations of comparison partners are not at hand.
• If implementations of different authors are provided, an evaluation in terms of efficiency is biased to evaluate the efforts of different authors in efficient programming instead of evaluating algorithmic merits.

In ELKI, data mining algorithms and data management tasks are separated and allow for an independent evaluation. This separation makes ELKI unique among data mining frameworks like Weka or YALE and frameworks for index structures like GiST. At the same time, ELKI is open to arbitrary data types, distance or similarity measures, or file formats. The fundamental approach is the independence of file parsers or database connections, data types, distances, distance functions, and data mining algorithms. Helper classes, e.g. for algebraic or analytic computations are available for all algorithms on equal terms.

With the development and publication of ELKI, we humbly hope to serve the data mining and database research community beneficially. The framework is free for scientific, non-commercial usage. In case of application of ELKI in scientific publications, it should be cited with the most recent publication below (see publications).

0.2.1 (2009, July, 13)

bug-fix release for 0.2, solving an issue with running PreDeCon, FourC and COPAC.

• executable archive (contains source-code)
• documentation

requires Java SE 6

0.2 (2009, July, 6)

publication of an extended version (see publication P2),
including distance measures for time series and a visualization tool for kNN-queries on time series.

Substantial changes in the infrastructure, see documentation.

• executable archive (contains source-code)
• documentation

requires Java SE 6

0.1 (2008, July, 10)

first publication of the framework (see publication P1)

• executable archive (contains source-code)
• documentation

requires Java SE 6

Although the ELKI-Framework is work of some years, the development is effected along the way and is prone to bugs and errors. We welcome any bug-reports. We also appreciate any comments and suggestions. You can contact us by e-mail: elki (at) dbs ifi lmu de

• One of the major upcoming refactoring tasks will be the restructuring of the database layer and the index structure layer in preparation of a richer choice of index structures and their evaluation.

For questions and suggestions regarding ELKI you can write to elki (at) dbs ifi lmu de

You can also subscribe the mailing list for users of ELKI via https://tools.rz.ifi.lmu.de/mailman/listinfo/elki-user, to exchange questions and ideas among other users or to get announcements (e.g., new releases, major changes) by the ELKI team.

Development and Maintenance

The ELKI core team ( elki (at) dbs ifi lmu de ):
 

Elke Achtert	Erich Schubert	Arthur Zimek

Development Contributions

• Noemi Andor
• Thomas Bernecker
  
• Peer Kröger
  
• Simon Mittermüller
• Simon Paradies
• Lisa Reichert
• Steffi Wanka
  
• Remigius Wojdanowski
• Andreas Züfle