Event Detection Framework

Detect events in time-series data. Combines multiple well-known R packages like 'forecast' and 'neuralnet' to deliver an easily configurable tool for multivariate event detection.


TODO / Upcoming:

  • Data Preparation might be done outside of buildEDModel so that for example NAs can be removed from the whole data set
  • Tests for different model types and functionality of 'detectEvents'
  • ?changable dynamic threshold classification?
  • useNormalization parameter in preprocessing cntrl list

NEWS: V0.3.1 - Added more Forecast models, added ed.print V0.3.0 - Added eventDetect automatic movingWindow based event detection over a whole dataset

Reference manual

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


0.3.5 by Sowmya Chandrasekaran, a year ago


Report a bug at https://github.com/frehbach/EventDetectR/issues

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

Authors: Margarita Rebolledo [aut] , Sowmya Chandrasekaran [aut, cre] , Frederik Rehbach [aut] , Steffen Moritz [aut]

Documentation:   PDF Manual  

GPL-3 license

Imports imputeTS, forecast, ggplot2, gridExtra, neuralnet

Suggests testthat, utils, caret, e1071

Imported by EventDetectGUI.

See at CRAN