EM algorithms of Gaussian Mixture Model and Hidden Markov Model

被引：0

作者：

Xuan, GR ^{[1
]}

Zhang, W ^{[1
]}

Chai, PQ ^{[1
]}

机构：

[1] Tongji Univ, Dept Comp Sci, Shanghai 200092, Peoples R China

来源：

2001 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL I, PROCEEDINGS | 2001年

关键词：

Expectation-Maximum (EM); Hidden Markov Model (HMM); Gaussian Mixture Model (GMM); Maximum Likelihood Estimation (MLE); GMM based on sample; GMM based on symbol;

D O I：

暂无

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

The HMM (Hidden Markov Model) is a probabilistic model of the joint probability of a collection of random variables with both observations and states. The GMM (Gaussian Mixture Model) is a finite mixture probability distribution model. Although the two models have a close relationship, they are always discussed independently and separately. The EM (Expectation-Maximum) algorithm is a general method to improve the descent algorithm for finding the Maximum Likelihood Estimation. The EM of HMM and the EM of GMM have similar formula. Two points are proposed in this paper. One is that the EM of GMM can be regarded as a special EM of HMM. The other is that the EM algorithm of GMM based on symbol is faster in implementation than EM algorithm of GMM based on sample (or on observation) traditionally.

引用

页码：145 / 148

页数：4

共 50 条

[31] A Mixture Hidden Markov Model to Mine Students' University Curricula
Bacci, Silvia
Bertaccini, Bruno
DATA, 2022, 7 (02)
[32] Computing the observed information in the hidden Markov model using the EM algorithm
Hughes, JP
STATISTICS & PROBABILITY LETTERS, 1997, 32 (01) : 107 - 114
[33] COMPOSITE LIKELIHOOD EM ALGORITHM WITH APPLICATIONS TO MULTIVARIATE HIDDEN MARKOV MODEL
Gao, Xin
Song, Peter X. -K.
STATISTICA SINICA, 2011, 21 (01) : 165 - 185
[34] Image recovery from the magnitude of the Fourier transform using a Gaussian mixture with hidden Potts-Markov model
Chama, Z
Belbachir, MF
Humblot, F
Mohammad-Djafari, A
Bayesian Inference and Maximum Entropy Methods in Science and Engineering, 2005, 803 : 239 - 246
[35] High Performance Image Compression Based on Optimized EZW Using Hidden Markov Chain and Gaussian Mixture Model
Sadaghiani, AbdolVahab Khalili
Sheilkhai, Samad
Forouzandeh, Behjat
2020 28TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE), 2020, : 637 - 641
[36] A uniform initialization Gaussian mixture model-based guided wave-hidden Markov model with stable damage evaluation performance
Yuan, Shenfang
Zhang, Jinjin
Chen, Jian
Qiu, Lei
Yang, Weibo
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2019, 18 (03): : 853 - 868
[37] Algorithms for optimal scheduling and management of Hidden Markov model sensors
Krishnamurthy, V
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (06) : 1382 - 1397
[38] A Mixture Model and a Hidden Markov Model to Simultaneously Detect Recombination Breakpoints and Reconstruct Phylogenies
Boussau, Bastien
Gueguen, Laurent
Gouy, Manolo
EVOLUTIONARY BIOINFORMATICS, 2009, 5 : 67 - 79
[39] Model choice for binned-EM algorithms of fourteen parsimonious Gaussian mixture models by BIC and ICL criteria
Wu, Jingwen
Hamdan, Hani
IEEE INTERNATIONAL CONFERENCE ON SYSTEM SCIENCE AND ENGINEERING (ICSSE 2013), 2013, : 351 - 356
[40] Sequential EM for Unsupervised Adaptive Gaussian Mixture Model Based Classifier
Hasan, Bashar Awwad Shiekh
Gan, John Q.
MACHINE LEARNING AND DATA MINING IN PATTERN RECOGNITION, 2009, 5632 : 96 - 106

← 1 2 3 4 5 →