Sparse Gaussian Markov Random Field Mixtures for Anomaly Detection

An implementation of sparse Gaussian Markov random field mixtures presented by Ide et al. (2016) . It provides a novel anomaly detection method for multivariate noisy sensor data. It can automatically handle multiple operational modes. And it can also compute variable-wise anomaly scores.


News

sGMRFmix 0.3.0

Improvements

  • Improve mode estimation

sGMRFmix 0.2.0

New features

  • Add k-means initializetion

Improvements

  • Automatically scale input (#2).
  • Refine plot_multivariate_data

Bug fixes

  • Allow to input tibble (#1).

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("sGMRFmix")

0.3.0 by Koji Makiyama, a year ago


Browse source code at https://github.com/cran/sGMRFmix


Authors: Koji Makiyama [cre, aut]


Documentation:   PDF Manual  


MIT + file LICENSE license


Imports ggplot2, glasso, mvtnorm, stats, tidyr, utils, zoo

Suggests dplyr, ModelMetrics, testthat, covr, knitr, rmarkdown


See at CRAN