The Classification of Noisy Sequences Generated by Similar HMMs

  • A. A. Popov
  • T. A. Gultyaeva
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6744)


The method for classification performance improvement using hidden Markov models (HMM) is proposed. The k-nearest neighbors (kNN) classifier is used in the feature space produced by these HMM. Only the similar models with the noisy original sequences assumption are discussed. The research results on simulated data for two-class classification problem are presented.


Hidden Markov Model Derivation k Nearest Neighbors 


  1. 1.
    Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proc. IEEE 77(2), 257–285 (1989)CrossRefGoogle Scholar
  2. 2.
    Cappé, O.: Ten years of HMMs. CNRS, LTCI & ENST, Dpt. TSI,
  3. 3.
    Mottl, V.V., Muchnik, I.B.: Hidden Markov Models in Structural Signal Analysis Moscow, Russia (1999) (in Russian)Google Scholar
  4. 4.
    Zagorujko, N.G.: Applied methods of analysis of data and knowledge. Novosibirsk, Russia (1999) (in Russian)Google Scholar
  5. 5.
    Chen, L., Man, H.: Combination of Fisher Scores and Appearance Based by Features For Face. In: Proc. of the 2003 ACM SIGMM Workshop on Biometrics Methods and Applications, Berkeley, California, USA, pp. 74–81 (2003)Google Scholar
  6. 6.
    Aran, O., Akarun, L.: Recognizing Two Handed Gestures with Generative, Discriminative and Ensemble Methods Via Fisher Kernels. In: Gunsel, B., Jain, A.K., Tekalp, A.M., Sankur, B. (eds.) MRCS 2006. LNCS, vol. 4105, pp. 159–166. Springer, Heidelberg (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • A. A. Popov
    • 1
  • T. A. Gultyaeva
    • 1
  1. 1.Department of Software and Database EngineeringNovosibirsk State Technical UniversityRussia

Personalised recommendations