[Zurück]


Vorträge und Posterpräsentationen (mit Tagungsband-Eintrag):

S. Brodinova, T. Ortner, P. Filzmoser, M. Zaharieva, C. Breiteneder:
"Evaluation of robust PCA for supervised audio outlier detection";
Vortrag: 22nd International Conference on Computational Statistics (COMPSTAT), Oviedo, Spain; 23.08.2016 - 26.08.2016; in: "Proceeding of 22nd International Conference on Computational Statistics (COMPSTAT)", (2016), ISBN: 978-90-73592-36-0; 12 S.



Kurzfassung deutsch:
Outliers often reveal crucial information about the underlying data such as the presence of unusual observations that require for in-depth analysis. The detection of outliers is especially challenging in real-world application scenarios dealing with high-dimensional and flat data bearing different subpopulations of potentially varying data distributions. In the context of high-dimensional data, PCA-based methods are commonly applied to reduce dimensionality and to reveal outliers. Thus, a thorough empirical evaluation of various PCA-based methods for the detection of outliers in a challenging audio data set is provided. The various experimental data settings are motivated by the requirements of real-world scenarios, such as varying number of outliers, available training data, and data characteristics in terms of potential subpopulations.

Kurzfassung englisch:
Outliers often reveal crucial information about the underlying data such as the presence of unusual observations that require for in-depth analysis. The detection of outliers is especially challenging in real-world application scenarios dealing with high-dimensional and flat data bearing different subpopulations of potentially varying data distributions. In the context of high-dimensional data, PCA-based methods are commonly applied to reduce dimensionality and to reveal outliers. Thus, a thorough empirical evaluation of various PCA-based methods for the detection of outliers in a challenging audio data set is provided. The various experimental data settings are motivated by the requirements of real-world scenarios, such as varying number of outliers, available training data, and data characteristics in terms of potential subpopulations.

Schlagworte:
Outlier detection, Robust PCA, Audio data, Experiments


Elektronische Version der Publikation:
http://publik.tuwien.ac.at/files/PubDat_250911.pdf



Zugeordnete Projekte:
Projektleitung Maia Zaharieva:
Unusual sequences detection in very large video collections


Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.