A methodological trajectory has been described dealing with the `novelty' or `surprise' issue in time series records arising from real world complex systems. It is based on extracting regularity (or scaling) characteristics of non-differentiable time series with wavelet transform, on modelling the complex system using multi-fractal properties and on investigating novelty in the context of the possible non-stationarity of such a model.
|MODELS AND PRINCIPLES (acm H.1), PATTERN RECOGNITION (acm I.5), MISCELLANEOUS (acm J.m), PHYSICAL SCIENCES AND ENGINEERING (acm J.2), DATA STORAGE REPRESENTATIONS (acm E.2)|
|Fractals (msc 28A80), Pattern recognition, speech recognition (msc 68T10), Searching and sorting (msc 68P10)|
|Information (theme 2)|
|Information Systems [INS]|
Struzik, Z.R. (2002). Taming surprises. Information Systems [INS]. CWI.