Computational methods for discrete hidden semi-Markov chains (Q4512134)

From MaRDI portal

!

This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:

scientific article; zbMATH DE number 1524242
Language Label Description Also known as
default for all languages
No label defined
    English
    Computational methods for discrete hidden semi-Markov chains
    scientific article; zbMATH DE number 1524242

      Statements

      0 references
      1 November 2000
      0 references
      counting distributions
      0 references
      hidden semi-Markov chain
      0 references
      interval distributions
      0 references
      renewal theory
      0 references
      Computational methods for discrete hidden semi-Markov chains (English)
      0 references
      Hidden Markov chains emerged in the 1970s in engineering and have since become a major tool for both pattern recognition applications such as speech or handwriting recognition or biological sequence analysis. Semi-Markov processes (or Markov renewal processes) have been applied for a long time in such diverse fields as biostatistics, operations research, reliability, queueing theory or manpower planning. Hidden semi-Markov chains with non-parametric state occupancy distributions were first proposed in the field of speech recognition by Ferguson at the beginning of the 1980s [see, for example, \textit{J. D. Ferguson} (ed.), Proc. Symp. on the Applications of Hidden Markov Models to Text and Speech (Princeton, NJ, 1980)]. A computational approach for implementing discrete hidden semi-Markov chains is proposed. A discrete hidden semi-Markov chain is composed of a non-observable or hidden process which is a finite semi-Markov chain and a discrete observable process. Hidden semi-Markov chains possess both the flexibility of hidden Markov chains for approximating complex probability distributions and the flexibility of semi-Markov chains for representing temporal structures. Efficient algorithms for computing characteristic distributions organized according to the intensity, interval and counting points of view are described. The proposed computational approach in conjunction with statistical inference algorithms previously proposed makes discrete hidden semi-Markov chains a powerful model for the analysis of samples of nonstationary discrete sequences.
      0 references

      Identifiers