Package: AnomalyScore 0.1

Guillermo Granados

AnomalyScore: Anomaly Scoring for Multivariate Time Series

Compute an anomaly score for multivariate time series based on the k-nearest neighbors algorithm. Different computations of distances between time series are provided.

Authors:Guillermo Granados [aut, cre]

AnomalyScore_0.1.tar.gz
AnomalyScore_0.1.tar.gz(r-4.5-noble)AnomalyScore_0.1.tar.gz(r-4.4-noble)
AnomalyScore_0.1.tgz(r-4.4-emscripten)AnomalyScore_0.1.tgz(r-4.3-emscripten)
AnomalyScore.pdf |AnomalyScore.html✨
AnomalyScore/json (API)

# Install 'AnomalyScore' in R:

install.packages('AnomalyScore', repos = c('https://cran.r-universe.dev', 'https://cloud.r-project.org'))

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

1.70 score 574 downloads 29 exports 33 dependencies

Last updated 4 months agofrom:a7a41fd001. Checks:1 OK, 2 NOTE. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Mar 22 2025
R-4.5-linux	NOTE	Mar 22 2025
R-4.4-linux	NOTE	Mar 22 2025

Exports:all_bands Anomalyscoresframe Cort DEcort DEcortNorm distance_matrix_banddepth distance_matrix_CGCI distance_matrix_coherence distance_matrix_cort distance_matrix_cortNorm distance_matrix_dtw distance_matrix_mahalanobis distance_matrix_mvLWS distance_matrix_PDC distance_matrix_PMIME distance_matrix_RGPDC distance_matrix_wasserstein DTWcort dxy_bands informative_bands kneighbors_distance_docall matrix_PDC mBTS mBTS_Af_mat mBTSCGCI mBTSRGPDC multilagmatrix PMIME sqnorms

Dependencies:astsa class curl data.table dotCall64 dtw fields jsonlite lattice leaps locfit maps marima MASS Matrix mgcv mvLSW nlme proxy quadprog quantmod RANN Rcpp RcppEigen spam transport TSA tseries TTR viridisLite wavethresh xts zoo

Citation

To cite package ‘AnomalyScore’ in publications use:

Granados G (2024). AnomalyScore: Anomaly Scoring for Multivariate Time Series. R package version 0.1, https://CRAN.R-project.org/package=AnomalyScore.

Corresponding BibTeX entry:

  @Manual{,
    title = {AnomalyScore: Anomaly Scoring for Multivariate Time
      Series},
    author = {Guillermo Granados},
    year = {2024},
    note = {R package version 0.1},
    url = {https://CRAN.R-project.org/package=AnomalyScore},
  }

Readme and manuals

Anomaly scoring for multivariate time series

This Package helps to compute anomaly scores for multivariate time series. The scores are defined based on a KNN algorithm using different approaches to determine distances between time series.

The last version of the package can be installed via:

devtools::install_github("Cuauhtemoctzin/AnomalyScore")

The development of this package was supported by the UK Research and Innovation (UKRI) Engineering and Physical Sciences Research Council (EPSRC) under the project titled "Reducing End Use Energy Demand in Commercial Settings Through Digital Innovation," grant number EP/T025964/1.

Help Manual

Help page	Topics
Pairwise band generation in a multivariate time series	all_bands
Anomaly score computation for a set of distances	Anomalyscoresframe
Temporal correlation coefficient	Cort
Distance based on value and behavior of the time series	DEcort
Normalized version of the Cort distance the modification is based on using the coefficient of variation rather than euclidean distance, performed by normalizing by the absolute value of the total differences of the series.	DEcortNorm
Pairwise distance matrix based on the band depth distance	distance_matrix_banddepth
Pairwise distance matrix based on the conditional Granger causality index	distance_matrix_CGCI
Distance matrix from a coherence measure	distance_matrix_coherence
Distance matrix from a pattern recognition distance	distance_matrix_cort
Normalized distance matrix from a pattern recognition distance	distance_matrix_cortNorm
Normalized distance matrix from dynamic time-warping distance	distance_matrix_dtw
Pairwise distance matrix based on the mahalanobis distance	distance_matrix_mahalanobis
Pairwise distance matrix based on the multivariate locally wavelet partial coherence	distance_matrix_mvLWS
Distance matrix from a partial directed coherence measure (PDC)	distance_matrix_PDC
Pairwise distance matrix based on the partial mutual information of mixed embedings (PMIME) method	distance_matrix_PMIME
Pairwise distance matrix based on the restricted generalized partial directed coherence	distance_matrix_RGPDC
Distance matrix from based on the Wasserstein distance	distance_matrix_wasserstein
Extention of the dynamic time warping distance	DTWcort
Band depth distance between 2 time series given a set of bands	dxy_bands
indexes where a series is within a specific band	informative_bands
K-Nearest neighbors algorithm to compute an anomaly score	kneighbors_distance_docall
Partial directed coherence matrix	matrix_PDC
modified Back-in-time Selection for vector AR parameters estimation	mBTS
mBTS Vector Autoregressive coefficients fourier transform	mBTS_Af_mat
computation of the conditional Granger causality index	mBTSCGCI
Restricted Generalized Partial Directed Coherence	mBTSRGPDC
multilagmatrix	multilagmatrix
PMIME Partial mutual information from mixed embedding	PMIME
Quadratic multiplication of a matrix M with respect to a matrix A: Conj(M) A M, where Conj() is the complex conjugate function	sqnorms