18th AIAI 2022, 17 - 20 June 2022, Greece

Equilibrium Resolution for Epoch Partitioning

Wojciech Wisniewski, Yuri Kalnishkan, David Lindsay, Sian Lindsay


  This paper proposes a method for determining the resolution for the processing of irregularly-sampled time series data to provide a balanced perspective of agents' behaviour. The behaviour is described as a collection of prolonged events, which are characterised by start/open and end/close times in addition to other useful attributes. We propose the definition of an equilibrium resolution and carry out its analysis based on probabilistic assumptions. The resulting methods of determining the equilibrium resolution are tested on real-life time series data sets from the Financial and Travel problem domains.  

*** Title, author list and abstract as seen in the Camera-Ready version of the paper that was provided to Conference Committee. Small changes that may have occurred during processing by Springer may not appear in this window.