Attribute Relationship Analysis in Outlier Mining and Stream Processing
Abstract:
The main theme of this thesis is to unite two important fields of data analysis, outlier mining and attribute relationship analysis. In this work we establish the connection between these two fields. We present techniques which exploit this connection, allowing to improve outlier detection in high dimensional data. In the second part of the thesis we extend our work to the emerging topic of data streams.
| Zugehörige Institution(en) am KIT | Institut für Programmstrukturen und Datenorganisation (IPD) |
| Publikationstyp | Hochschulschrift |
| Publikationsjahr | 2015 |
| Sprache | Englisch |
| Identifikator | urn:nbn:de:swb:90-487901 KITopen-ID: 1000048790 |
| Verlag | Karlsruher Institut für Technologie (KIT) |
| Art der Arbeit | Dissertation |
| Fakultät | Fakultät für Informatik (INFORMATIK) |
| Institut | Institut für Programmstrukturen und Datenorganisation (IPD) |
| Prüfungsdaten | 01.07.2015 |
| Schlagwörter | Outlier Mining, Correlation Analysis, Subspace Search, Stream Processing |
| Referent/Betreuer | Böhm, K. |