Anomaly detection by bagging

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00211170" target="_blank" >RIV/68407700:21230/13:00211170 - isvavai.cz</a>
Result on the web
<a href="http://ama.imag.fr/COPEM/copem2013_proceedings.pdf" target="_blank" >http://ama.imag.fr/COPEM/copem2013_proceedings.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Anomaly detection by bagging
Original language description
Many contemporary domains, e.g. network intrusion detection, fraud detection, etc., call for an anomaly detector processing a continuous stream of data. This need is driven by the high rate of their acquisition, by limited resources for storing them, orby privacy issues. The data can be also non-stationary requiring the detector to continuously adapt to their change. A good detector for these domains should therefore have a low training and classification complexity, on-line training algorithm, and, ofcourse, a good detection accuracy. This paper proposes a detector trying to meet all these criteria. The detector consists of multiple weak detectors, each implemented as a one dimensional histogram. The one-dimensional histogram was chosen because it can be efficiently created on-line, and probability estimates can be efficiently retrieved from it. This construction gives the detector linear complexity of training and classification with respect to the input dimension, number of sample
Czech name
—
Czech description
—

Project
<a href="/en/project/GPP103%2F12%2FP514" target="_blank" >GPP103/12/P514: Real-time detection of anomalous events in a non-stationary environment</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)