Towards Smart Data Selection From Time Series Using Statistical Methods

Transmitting and storing large volumes of dynamic / time series data collected by modern sensors can represent a significant technological challenge. A possibility to mitigate this challenge is effectively select subset points in order reduce without sacrificing the quality results subsequent analysis. This paper proposes method for adaptively identifying optimal point selection algorithms sensor on window-by-window basis. Thus, contribution focuses quantifying effect application windows. The proposed approach first used multiple synthetically generated obtained concatenating sources one after other, then validated entire UCR public archive.