Recursive Parameter Estimation and Its Convergence for Multivariate Normal Hidden Markov Inhomogeneous Models

Authors

  • Miftahul Fikri ᵃHigh Voltage and High Current Institute, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia; ᵇFaculty of Electricity and Renewable Energy, Institut Teknologi PLN,11750 Jakarta Barat, Jakarta, Indonesia;
  • Zulkurnain Abdul-Malek High Voltage and High Current Institute, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia
  • Mona Riza Mohd Esa High Voltage and High Current Institute, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Johor Bahru, Johor, Malaysia
  • Eko Supriyanto School of Biomedical Engineering and Health Sciences, Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 UTM Johor Bahru, Johor Malaysia

DOI:

https://doi.org/10.11113/mjfas.v19n5.3041

Keywords:

Hidden Markov model inhomogeneous, Multivariat normal, Likelihood function, Expectation Maximization, Monotone convergence.

Abstract

In this paper, will discussed parameter estimation and convergence analysis of multivariate normal hidden inhomogeneous Markov models. The results of this research show that by using the expectation maximization algorithm, a sequence of parameter estimators converges to a stationary point of the likelihood function in a monotonically increasing manner.

References

O. Cappe. (2005). Inference in Hidden Markov Models. Springer.

S. M. Ross. (2019). Introduction to Probability Models. Academic Press Elsevier. Doi: 10.1016/b978-0-12-814346-9.00006-8.

H. Tao and X. Lu. (2019). Smoke vehicle detection based on multi-feature fusion and hidden Markov model. J. Real-Time Image Process., 17(3), 745-758. Doi: 10.1007/s11554-019-00856-z.

R. Paroli and L. Spezia. (1999). Gaussian Hidden Markov Models: Parameters estimation and applications to air pollution data. Department of Statistical Science, Faculty of Economics, Univ. Cattol. Del Sacro Cuore.

D. Khiatani and U. Ghose. (2017).Weather forecasting using Hidden Markov Model. 2017 Int. Conf. Comput. Commun. Technol. Smart Nation, IC3TSN 2017. 220-225. Doi: 10.1109/IC3TSN.2017.8284480.

M. Fikri, Samsurizal, Christiono, and K. T. M. (2020). Pemodelan cuaca menggunakan Model Hidden Markov untuk pemanfaatan energi surya. Kiilat, 9(2), 217-224.

Y. Trichilli, M. Boujelbène Abbes, and A. Masmoudi. (2020). Predicting the effect of Googling investor sentiment on Islamic stock market returns: A five-state hidden Markov model. Int. J. Islam. Middle East. Financ. Manag., 13(2), 165-193. Doi: 10.1108/IMEFM-07-2018-0218.

M. Zhang, X. Jiang, Z. Fang, Y. Zeng, and K. Xu. (2019). High-order Hidden Markov Model for trend prediction in financial time series. Phys. A Stat. Mech. its Appl., 517, 1-12. Doi: 10.1016/j.physa.2018.10.053.

N. Nguyen. (2018). Hidden Markov Model for stock trading. Int. J. Financ. Stud., 6(36), 1-17. Doi: 10.3390/ijfs6020036.

P. Somani, S. Talele, and S. Sawant. (2014). Stock market prediction using hidden Markov Model. 2014 IEEE 7th Jt. Int. Inf. Technol. Artif. Intell. Conf. 89-92.

A. Gupta and B. Dhingra. (2012). Stock market prediction using Hidden Markov Models. Students Conf. Eng. Syst. 1-4.

L. R. Rabiner. (1989). A tutorial on Hidden Markov models and selected applications in Speech Re. Proc. IEEE, 77(2), 257-288. Doi: 10.25300/MISQ/2017/41.3.08.

M. Cutajar, E. Gatt, I. Grech, O. Casha, and J. Micallef. (2013). Comparative study of automatic speech recognition techniques. IET Signal Process., 7(1), 25-46. Doi: 10.1049/iet-spr.2012.0151.

B. Mouaz, B. H. Abderrahim, and E. Abdelmajid. (2019). Speech recognition of moroccan dialect using hidden markov models. IAES Int. J. Artif. Intell., 8(1), 7-13. Doi: 10.11591/ijai.v8.i1.pp7-13.

A. Luck, P. Giehr, K. Nordstrom, J. Walter, and V. Wolf. (2019). Hidden markov modelling reveals neighborhood dependence of dnmt3a and 3b activity. IEEE/ACM Trans. Comput. Biol. Bioinforma, 16(5), 1598-1609. Doi: 10.1109/TCBB.2019.2910814.

N. Zarrabi, P. Schluesche, M. Meisterernst, M. Börsch, and D. C. Lamb. (2018). Analyzing the dynamics of single TBP-DNA-NC2 complexes using hidden Markov Models. Biophys. J., 115(12), 2310-2326. Doi: 10.1016/j.bpj.2018.11.015.

M. Fikri and Z. Abdul-Malek. (2023). Partial discharge diagnosis and remaining useful lifetime in XLPE extruded power cables under DC voltage: A review. Electr. Eng. Doi: 10.1007/s00202-023-01935-y.

M. Fikri et al. (2023). Clustering suara corona discharge berdasarkan tegangan menggunakan metode Fuzzy C-Mean. ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., 11(3), 609-624.

N. Pasra, M. Fikri, K. T. Mauriraya, T. Rijanto, and I. G. P. A. Buditjahjanto. (2023). Deteksi suara corona discharge berdasarkan noise menggunakan metode LPC dan Euclidean distance. ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., 11(1), 72-85.

M. Fikri, Christiono, and I. G. M. K. (2022). Clustering fenomena corona discharge berdasarkan suara menggunakan metode LPC dan Euclidean distance. ELKOMIKA J. Tek. Energi Elektr. Tek. Telekomun. Tek. Elektron., 10(3), 689-701.

V. S. Barbu and N. Limnios. (2009). Semi-Markov Chains and Hidden Semi-Markov Models Toward Applications. Springer.

L. Spezia. (2010). Bayesian analysis of multivariate Gaussian hidden Markov models with an unknown number of regimes. J. Time Ser. Anal., 31, 1-11. Doi: 10.1111/j.1467-9892.2009.00635.x.

L. Spezia, M. N. Futter, and M. J. Brewer. (2011). Periodic multivariate normal hidden Markov models for the analysis of water quality time series,”.nvironmetrics, 2010(July), 304-317. Doi: 10.1002/env.1051.

M. Fikri, Z. Abdul‐Malek, and K. Atmadja. (1990). Recursive parameter estimation and its convergence for multivariate normal hidden Markov Model.Thail. Stat.

J. D. Hamilton. (1990). Analysis of time series subject to changes in regime. J. Ecomometrics, 45, 39-70.

B. Setiawaty, D. H. Santoso, and N. K. K. Ardana. (2007). Pemodelan nilai tukar rupiah terhadap $Us menggunakan deret waktu hidden MARKOV satu waktu sebelumnya. J. Math. Its Appl.

L. E. Baum. (1972). An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov processes. Proc Third Symp. Inequalities, ed. O Shisha, 1-8.

I. L. Macdonald and Walter Zucchini. (1997). Hidden Markov and other models for discrete-valued time series. Chapman and Hall,

A. P. Dempster, N. M. Laird, and D. B. Rubin. (1977). Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B, 1-22. Doi: 10.1111/j.2517-6161.1977.tb01600.x.

M. Fikri, B. Setiawaty, and I. G. P. Purnaba. (2016). Pendugaan parameter dan kekonvergenan penduga parameter model poisson hidden Markov. J. Math. Its Appl., 15(1) 1-10.

M. Pourahmadi. (1999). Joint mean-covariance models with applications to longitudinal data: Unconstrained parameterisation. Biometrika, 86(3), 677-690.

O. Ledoit and M. Wolf. (2004). A well-conditioned estimator for large-dimensional covariance matrices. J. Multivar. Anal., 88, 365-411. Doi: 10.1016/S0047-259X(03)00096-4.

A. J. Rothman, E. Levina, and J. I. Zhu. (2010). A new approach to Cholesky-based covariance regularization in high dimensions. Biometrika, 97(3), 539-550. Doi: 10.1093/biomet/asq022.

Mohsen Pourahmadi. (2011). Covariance estimation: The GLM and regularization perspectives. Stat. Sci., 26(3), 369-387. Doi: 10.1214/11-STS358.

C. Lam. (2016). Nonparametric eigenvalue-regularized precision or covariance matrix estimator. Ann. Stat., 44(3), 928-953. Doi: 10.1214/15-AOS1393.

O. Ledoit and M. Wolf. (2020). Analytical nonlinear shrinkage of large-dimensional covariance matrices. Ann. Stat., 48(5), 3043-3065.

R. Paroli, G. Redaelli, and L. Spezia. (2000). Poisson hidden Markov Models for time series of overdispersed insurance counts. Astin Colloqium, 461-474.

J. D. Hamilton. (1994). Time Series Analysis. Princeton, New Jerse: Princeton University Press.

D. R. S. Geoffrey R. Grimmett. (2001). Probability and random processes. Oxford University Press.

L. E. Baum, T. Petrie, G. Soules, and N. Weiss. (1970). A maximization technique occuring in the statistical analysis of probabilistic functions of Markov chains. Ann. Math. Stat., 41(1), 64-171.

J. Wu. (1983). On the convergence properties of the EM algorithm. Ann. Stat., 11(1), 95-103.

W. I. Zangwill. (1969). Nonlinear Programming: A Unified Approach. New Jersey: Prentice Hall.

Downloads

Published

19-10-2023