spectralAnomaly: Detect Anomalies Using the Spectral Residual Algorithm

Apply the spectral residual algorithm to data, such as a time series, to detect anomalies. Anomaly scores can be used to determine outliers based upon a threshold or fed into more sophisticated prediction models. Methods are based upon "Time-Series Anomaly Detection Service at Microsoft", Ren, H., Xu, B., Wang, Y., et al., (2019) <doi:10.48550/arXiv.1906.03821>.

Version: 0.1.1
Imports: stats, utils
Suggests: testthat (≥ 3.0.0)
Published: 2024-09-15
DOI: 10.32614/CRAN.package.spectralAnomaly
Author: Allen OBrien [aut, cre, cph]
Maintainer: Allen OBrien <allen.g.obrien at gmail.com>
BugReports: https://github.com/al-obrien/spectralAnomaly/issues
License: MIT + file LICENSE
URL: https://al-obrien.github.io/spectralAnomaly/, https://github.com/al-obrien/spectralAnomaly
NeedsCompilation: no
Materials: README NEWS
CRAN checks: spectralAnomaly results

Documentation:

Reference manual: spectralAnomaly.pdf

Downloads:

Package source: spectralAnomaly_0.1.1.tar.gz
Windows binaries: r-devel: spectralAnomaly_0.1.1.zip, r-release: spectralAnomaly_0.1.1.zip, r-oldrel: spectralAnomaly_0.1.1.zip
macOS binaries: r-release (arm64): spectralAnomaly_0.1.1.tgz, r-oldrel (arm64): spectralAnomaly_0.1.1.tgz, r-release (x86_64): spectralAnomaly_0.1.1.tgz, r-oldrel (x86_64): spectralAnomaly_0.1.1.tgz

Linking:

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