Evaluating Subspace Search Methods with Hidden Outlier: Unterschied zwischen den Versionen

Aus SDQ-Institutsseminar
(Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Marcel Hiltscher |email=marcelhiltscher@outlook.de |vortragstyp=Bachelorarbeit |betreuer=Georg Steinbuss |termin=Institutsseminar/2019-…“)
 
Keine Bearbeitungszusammenfassung
 
Zeile 4: Zeile 4:
|vortragstyp=Bachelorarbeit
|vortragstyp=Bachelorarbeit
|betreuer=Georg Steinbuss
|betreuer=Georg Steinbuss
|termin=Institutsseminar/2019-02-15
|termin=Institutsseminar/2019-02-15 Zusatztermin
|kurzfassung=In today’s world, most datasets do not have only a small number of attributes. The high
|kurzfassung=In today’s world, most datasets do not have only a small number of attributes. The high
number of attributes, which are referred to as dimensions, hinder the search of objects
number of attributes, which are referred to as dimensions, hinder the search of objects

Aktuelle Version vom 11. Februar 2019, 15:38 Uhr

Vortragende(r) Marcel Hiltscher
Vortragstyp Bachelorarbeit
Betreuer(in) Georg Steinbuss
Termin Fr 15. Februar 2019
Vortragsmodus
Kurzfassung In today’s world, most datasets do not have only a small number of attributes. The high

number of attributes, which are referred to as dimensions, hinder the search of objects that normally not occur. For instance, consider a money transaction that has been not legally carried out. Such objects are called outlier. A common method to detect outliers in high dimensional datasets are based on the search in subspaces of the dataset. These subspaces have the characteristics to reveal possible outliers. The most common evaluation of algorithms searching for subspaces is based on benchmark datasets. However, the benchmark datasets are often not suitable for the evaluation of these subspace search algorithms. In this context, we present a method that evaluates subspace search algorithms without relying on benchmark datasets by hiding outliers in the result set of a subspace search algorithm.