Density-Based Outlier Detection Benchmark on Synthetic Data: Unterschied zwischen den Versionen

Aus IPD-Institutsseminar
Zur Navigation springen Zur Suche springen
(Die Seite wurde neu angelegt: „{{Vortrag |vortragender=Lena Witterauf |email=uxegn@student.kit.edu |vortragstyp=Proposal |betreuer=Georg Steinbuss |termin=Institutsseminar/2019-01-18 |kurzfa…“)
 
Zeile 6: Zeile 6:
 
|termin=Institutsseminar/2019-01-18
 
|termin=Institutsseminar/2019-01-18
 
|kurzfassung=Outlier detection algorithms are widely used in application fields such as image processing and fraud detection. Thus, during the past years, many different outlier detection algorithms were developed. While a lot of work has been put into comparing the efficiency of these algorithms, comparing methods in terms of effectiveness is rather difficult. One reason for that is the lack of commonly agreed-upon benchmark data.
 
|kurzfassung=Outlier detection algorithms are widely used in application fields such as image processing and fraud detection. Thus, during the past years, many different outlier detection algorithms were developed. While a lot of work has been put into comparing the efficiency of these algorithms, comparing methods in terms of effectiveness is rather difficult. One reason for that is the lack of commonly agreed-upon benchmark data.
In this thesis the effectiveness of density based outlier detection algorithms (such as knn, lof and related methods) are compared on entirely synthetically generated data, using its underlying density as ground truth.
+
In this thesis the effectiveness of density-based outlier detection algorithms (such as knn, lof and related methods) are compared on entirely synthetically generated data, using its underlying density as ground truth.
 
}}
 
}}

Version vom 15. Januar 2019, 16:59 Uhr

Vortragende(r) Lena Witterauf
Vortragstyp Proposal
Betreuer(in) Georg Steinbuss
Termin Fr 18. Januar 2019
Vortragsmodus
Kurzfassung Outlier detection algorithms are widely used in application fields such as image processing and fraud detection. Thus, during the past years, many different outlier detection algorithms were developed. While a lot of work has been put into comparing the efficiency of these algorithms, comparing methods in terms of effectiveness is rather difficult. One reason for that is the lack of commonly agreed-upon benchmark data.

In this thesis the effectiveness of density-based outlier detection algorithms (such as knn, lof and related methods) are compared on entirely synthetically generated data, using its underlying density as ground truth.