Abstract
Hidden Markov models (HMMs) usually assume that the state transition matrices and the output models are time-invariant. Without this assumption, the parameters in a HMM may not be identifiable. In this paper, we propose a HMM with multiple observers such that its parameters are local identifiable without the time-invariant assumption. We show a sufficient condition for local identifiability of parameters in HMMS.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ghahramani, Z.: An Introduction to Hidden Markov Models and Bayesian Networks. Hidden Markov Models: Applications in Computer Vision, pp. 9–42 (2001)
Goodman, L.A.: Exploratory Latent Structure Analysis Using Both Identifiable and Unidentifiable Models. Biometrika 61, 215–231 (1974)
Spezia, L.: Bayesian Analysis of Non-homogeneous Hidden Markov Models. Journal of Statistical Computation and Simulation 76, 713–725 (2006)
Van de Pol, F., Langeheine, R.: Mixed Markov Latent Class Models. In: Clogg, C.C. (ed.) Sociological Methodology, Blackwell, Oxford (1990)
Vermunt, J.K., Langeheine, R., Bockenholt, U.: Discrete-time Discrete-state Latent Markov Models with Time-constant and Time-varying Covariates. Journal of Educational and Behavioral Statistics 24, 179–207 (1999)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, H., Geng, Z., Jia, J. (2007). Hidden Markov Models with Multiple Observers. In: Huang, DS., Heutte, L., Loog, M. (eds) Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence. ICIC 2007. Lecture Notes in Computer Science(), vol 4682. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74205-0_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-74205-0_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74201-2
Online ISBN: 978-3-540-74205-0
eBook Packages: Computer ScienceComputer Science (R0)