Recursive Algorithms of Time Series Observations Recognition

Article type: Research Article

Authors: Shpilewski, Edward

Affiliations: Institute of Mathematics and Informatics, Goštauto 12, 2600 Vilnius, Lithuania. E-mail: edwszp@ktl.mii.lt

Abstract: The paper presents new method for sequential classification of the time series observations. Methods and algorithms of sequential recognition are obtained on the basis of the recursive equations for sufficient statistics. These recursive equations allow to construct algorithms of current classification of observable sequences in the rate of entering its values into the on-line operation. Classification algorithms are realized in the form of computer programs, including personal computers. They allow to build multi-channel conveyer computational structures for the sequential recognizers of time series observations.

Keywords: time series, processes classes, samples, sequential classification

DOI: 10.3233/INF-2000-11308

Journal: Informatica, vol. 11, no. 3, pp. 311-324, 2000