2018
Autoencoders vs. others for anomaly detection
MIKLÁŠOVÁ, Kristína, Ondřej LOMIČ, Lukáš CÍSAR, Lubomír POPELÍNSKÝ, Veronika KREJČÍŘOVÁ et. al.Základní údaje
Originální název
Autoencoders vs. others for anomaly detection
Název česky
Autoencodery vs. jiné metody pro detekci anomálií
Autoři
MIKLÁŠOVÁ, Kristína (703 Slovensko), Ondřej LOMIČ (203 Česká republika), Lukáš CÍSAR (703 Slovensko), Lubomír POPELÍNSKÝ (203 Česká republika, garant, domácí) a Veronika KREJČÍŘOVÁ (203 Česká republika)
Vydání
Brno, DATA A ZNALOSTI & WIKT 2018, sborník konference, od s. 215-220, 6 s. 2018
Nakladatel
Vysoké učení technické v Brně
Další údaje
Jazyk
angličtina
Typ výsledku
Stať ve sborníku
Obor
10200 1.2 Computer and information sciences
Stát vydavatele
Česká republika
Utajení
není předmětem státního či obchodního tajemství
Forma vydání
elektronická verze "online"
Kód RIV
RIV/00216224:14330/18:00105831
Organizační jednotka
Fakulta informatiky
ISBN
978-80-214-5679-2
Klíčová slova česky
Autoencodery · Local Outlier Factor (LOF) · z-skore · anomalie · PascalVOC image dataset · extrakce rysů
Klíčová slova anglicky
Autoencoders · Local Outlier Factor (LOF) · z-score · anomalies · PascalVOC image dataset · feature extraction
Příznaky
Mezinárodní význam, Recenzováno
Změněno: 22. 1. 2019 22:40, doc. RNDr. Lubomír Popelínský, Ph.D.
V originále
The paper deals with a task of finding anomalies in the set of pictures using autoencoders and comparison of results with other methods searching for outliers, namely LOF and z-score. Outliers found by these methods are compared to outliers found by project team members. Process consists of preprocessing of pictures using pretrained deep neural nets (one at a time), reducing dimension using PCA, normalization of features and applying methods on pictures, either on a whole set or subsets divided by classes (dividing the pictures to groups by objects of interest that can be found in them). Output of methods with different attribute settings was compared to outliers found by team members using confusion matrix and F1-score. The results were not very positive, no significant relationships were found between anomalies found by team members and by anomalies found by individual methods. Possible reasons for this are discussed.
Česky
The paper deals with a task of finding anomalies in the set of pictures using autoencoders and comparison of results with other methods searching for outliers, namely LOF and z-score. Outliers found by these methods are compared to outliers found by project team members. Process consists of preprocessing of pictures using pretrained deep neural nets (one at a time), reducing dimension using PCA, normalization of features and applying methods on pictures, either on a whole set or subsets divided by classes (dividing the pictures to groups by objects of interest that can be found in them). Output of methods with different attribute settings was compared to outliers found by team members using confusion matrix and F1-score. The results were not very positive, no significant relationships were found between anomalies found by team members and by anomalies found by individual methods. Possible reasons for this are discussed.
Návaznosti
| MUNI/A/0854/2017, interní kód MU |
|