Publikationsansicht

Principle Components and Importance Ranking of Distributed Anomalies (2004)

Abstract
Correlations between locally averaged host observations, at different times and places, hint at information about the associations between the hosts in a network. These smoothed, pseudo-continuous time-series imply relationships with entities in the wider environment. For anomaly detection, mining this information might provide a valuable source of observational experience for determining comparative anomalies or rejecting false anomalies. The di#culties with distributed analysis lie in collating the distributed data and in comparing observables on di#erent hosts, in di#erent frames of reference. In the present work, we examine two methods (Principle Component Analysis and Eigenvector Centrality) that shed light on the usefulness of comparing data destined for di#erent locations in a network.

Details der Publikation
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.3276
Quelle http://www.iu.hio.no/~mark/papers/corr.pdf
Mitarbeiter CiteSeerX
Archiv CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Keywords Machine learning, anomaly detection
Typ text
Sprache Englisch
Verknüpfungen 10.1.1.120.3875, 10.1.1.31.1768, 10.1.1.55.3577, 10.1.1.1.4175, 10.1.1.108.6299, 10.1.1.125.7410, 10.1.1.1.1699, 10.1.1.117.9232, 10.1.1.89.4842, 10.1.1.128.7359