Pages about teaching are available in German only Zurück zu der Liste der Abschlussarbeiten

Clustering with k-nearest neighbor consistency

Title Clustering with k-nearest neighbor consistency

The objective is to add an efficient implementation of the following algorithm into the ELKI data mining framework (this requires good Java knowledge):

Ding, C., & He, X. (2004, March). K-nearest-neighbor consistency in data clustering: incorporating local information into global optimization. In Proceedings of the 2004 ACM symposium on Applied computing (pp. 584-589).

and study the result quality compared to existing algorithms in ELKI. It is required that the implementation follows the object-oriented design patterns of ELKI, i.e., reusability and modularity. This likely requires the method to be implemented in two parts: the knn-based evaluation measure as well as the k-means-based optimization algorithm. The algorithm must be tested with appropriate unit tests.


This is only suitable as a Bachelor thesis topic.

Good Java programming skills

Good understanding of data mining algorithms

Good statistical knowledge

Thesistype Bachelorthesis
Second Tutor Lang, Andreas
Professor Schubert, Erich
Assigned To Strahmann, Niklas
Status Bearbeitung
Registered On Sep 26, 2022 3:27:00 PM