stray: Anomaly Detection in High Dimensional and Temporal Data

This is a modification of 'HDoutliers' package. The 'HDoutliers' algorithm is a powerful unsupervised algorithm for detecting anomalies in high-dimensional data, with a strong theoretical foundation. However, it suffers from some limitations that significantly hinder its performance level, under certain circumstances. This package implements the algorithm proposed in Talagala, Hyndman and Smith-Miles (2019) <arXiv:1908.04000> for detecting anomalies in high-dimensional data that addresses these limitations of 'HDoutliers' algorithm. We define an anomaly as an observation that deviates markedly from the majority with a large distance gap. An approach based on extreme value theory is used for the anomalous threshold calculation.

Version: 0.1.1
Depends: R (≥ 3.4.0)
Imports: FNN, ggplot2, colorspace, pcaPP, stats, ks
Published: 2020-06-29
Author: Priyanga Dilini Talagala ORCID iD [aut, cre], Rob J Hyndman ORCID iD [ths], Kate Smith-Miles [ths]
Maintainer: Priyanga Dilini Talagala <pritalagala at gmail.com>
BugReports: https://github.com/pridiltal/stray/issues
License: GPL-2
NeedsCompilation: no
CRAN checks: stray results

Downloads:

Reference manual: stray.pdf
Package source: stray_0.1.1.tar.gz
Windows binaries: r-devel: stray_0.1.1.zip, r-release: stray_0.1.1.zip, r-oldrel: stray_0.1.1.zip
macOS binaries: r-release: stray_0.1.1.tgz, r-oldrel: stray_0.1.1.tgz
Old sources: stray archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=stray to link to this page.