<abstract xmlns="http://www.w3.org/1999/xhtml"><p>The method of change (or anomaly) detection in high-dimensional discrete-time processes using a multivariate Hotelling chart is presented. We use normal random projections as a method of dimensionality reduction. We indicate diagnostic properties of the Hotelling control chart applied to data projected onto a random subspace of Rn. We examine the random projection method using artificial noisy image sequences as examples.</p></abstract>

The method of change (or anomaly) detection in high-dimensional discrete-time processes using a multivariate Hotelling chart is presented. We use normal random projections as a method of dimensionality reduction. We indicate diagnostic properties of the Hotelling control chart applied to data projected onto a random subspace of Rn. We examine the random projection method using artificial noisy image sequences as examples.

Random projections and Hotelling’s  <italic>T<sub>2</sub></italic> statistics for change detection in high-dimensional data streams

Institute of Computer Engineering, Automation and Robotics Technical University of Wrocław, Wybrze˙ze Wyspia´nskiego 27, 50-370 Wrocław, Poland

International Journal of Applied Mathematics and Computer Science

Random projections and Hotelling’s   statistics for change detection in high-dimensional data streams

The method of change (or anomaly) detection in high-dimensional discrete-time processes using a multivariate Hotelling chart is presented. We use normal random...

Random projections and Hotelling’s T₂ statistics for change detection in high-dimensional data streams

Publié en ligne: 28 juin 2013

Pages: 447 - 461

DOI: https://doi.org/10.2478/amcs-2013-0034

This content is open access.

Random projections and Hotelling’s T2 statistics for change detection in high-dimensional data streams

Publié en ligne: 28 juin 2013

Pages: 447 - 461

DOI: https://doi.org/10.2478/amcs-2013-0034

This content is open access.

Random projections and Hotelling’s T₂ statistics for change detection in high-dimensional data streams