Asymptotic smoothing errors for hidden markov models

Louis Shue; Brian D.O. Anderson; Franky De Bruyne

doi:10.1109/78.886992

Asymptotic smoothing errors for hidden markov models

Louis Shue, Brian D.O. Anderson, Franky De Bruyne

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

In this paper, the asymptotic smoothing error for hidden Markov models (HMMs) is investigated using hypothesis testing ideas. A family of HMMs is studied parametrised by a positive constant e, which is a measure of the frequency of change. Thus, when e -> 0, the HMM becomes increasingly slower moving. We show that the smoothing error is O(e). These theoretical predictions are confirmed by a series of simulations.

Original language	English
Pages (from-to)	3289-3302
Number of pages	14
Journal	IEEE Transactions on Signal Processing
Volume	48
Issue number	12
DOIs	https://doi.org/10.1109/78.886992
Publication status	Published - 2000

Access to Document

10.1109/78.886992

Cite this

@article{e77020e4e94946beb405f3c175604ef7,

title = "Asymptotic smoothing errors for hidden markov models",

abstract = "In this paper, the asymptotic smoothing error for hidden Markov models (HMMs) is investigated using hypothesis testing ideas. A family of HMMs is studied parametrised by a positive constant e, which is a measure of the frequency of change. Thus, when e -> 0, the HMM becomes increasingly slower moving. We show that the smoothing error is O(e). These theoretical predictions are confirmed by a series of simulations.",

keywords = "Asymptotic error, Hidden markov model, Smoothing",

author = "Louis Shue and Anderson, {Brian D.O.} and {De Bruyne}, Franky",

year = "2000",

doi = "10.1109/78.886992",

language = "English",

volume = "48",

pages = "3289--3302",

journal = "IEEE Transactions on Signal Processing",

issn = "1053-587X",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - Asymptotic smoothing errors for hidden markov models

AU - Shue, Louis

AU - Anderson, Brian D.O.

AU - De Bruyne, Franky

PY - 2000

Y1 - 2000

N2 - In this paper, the asymptotic smoothing error for hidden Markov models (HMMs) is investigated using hypothesis testing ideas. A family of HMMs is studied parametrised by a positive constant e, which is a measure of the frequency of change. Thus, when e -> 0, the HMM becomes increasingly slower moving. We show that the smoothing error is O(e). These theoretical predictions are confirmed by a series of simulations.

AB - In this paper, the asymptotic smoothing error for hidden Markov models (HMMs) is investigated using hypothesis testing ideas. A family of HMMs is studied parametrised by a positive constant e, which is a measure of the frequency of change. Thus, when e -> 0, the HMM becomes increasingly slower moving. We show that the smoothing error is O(e). These theoretical predictions are confirmed by a series of simulations.

KW - Asymptotic error

KW - Hidden markov model

KW - Smoothing

UR - http://www.scopus.com/inward/record.url?scp=0034429493&partnerID=8YFLogxK

U2 - 10.1109/78.886992

DO - 10.1109/78.886992

M3 - Article

SN - 1053-587X

VL - 48

SP - 3289

EP - 3302

JO - IEEE Transactions on Signal Processing

JF - IEEE Transactions on Signal Processing

IS - 12

ER -

Asymptotic smoothing errors for hidden markov models

Abstract

Access to Document

Other files and links

Fingerprint

Cite this