Abstract
We propose to apply the importance sampling and the antithetic variates statistical techniques to estimate steady-state quantities of an Hidden Markov chain (HMM) of which certain emissions are rarely generated. Compared to standard Monte Carlo simulation, the use of these techniques, allow a significant reduction in simulation time. Numerical Monte Carlo examples are studied to show the usefulness and efficiency of the proposed approach.
Acknowledgements
The authors wish to express their sincere gratitude to the Editor-in-Chief for following up on the paper, and gratefully acknowledge the many helpful suggestions and valuable comments of the Reviewers that lead to an improved paper.
References
[1] K. Aas, L. Eikvil and R. B. Huseby, Applications of hidden Markov chains in image analysis, Pattern Recognit. 32 (1999), no. 4, 703–713. 10.1016/S0031-3203(98)00109-5Search in Google Scholar
[2] T. Adam, R. Langrock and C. H. Weiß, Penalized estimation of flexible hidden Markov models for time series of counts, Metron 77 (2019), no. 2, 87–104. 10.1007/s40300-019-00153-6Search in Google Scholar
[3] J. Baker, The DRAGON system–An overview, IEEE Trans Acous. Speech Signal Process. 23 (1975), 24–29. 10.1109/TASSP.1975.1162650Search in Google Scholar
[4] F. Bartolucci, A. Farcomeni and F. Pennoni, Latent Markov Models for Longitudinal Data, CRC Press, Boca Raton, 2013. 10.1201/b13246Search in Google Scholar
[5] F. Bartolucci, S. Pandolfi and F. Pennoni, LMest: An R package for latent Markov models for longitudinal categorical data, J. Stat. Softw. 8 (2017), 1–38. 10.18637/jss.v081.i04Search in Google Scholar
[6] L. E. Baum, An inequality and associated maximization technique in statistical estimation for probabilistic functions of Markov processes, Inequalities III: Proceedings of the Third Symposium on Inequalities, Academic Press, New York (1972), 1–8. Search in Google Scholar
[7] L. E. Baum and J. A. Eagon, An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology, Bull. Amer. Math. Soc. 73 (1967), 360–363. 10.1090/S0002-9904-1967-11751-8Search in Google Scholar
[8] L. E. Baum and T. Petrie, Statistical inference for probabilistic functions of finite state Markov chains, Ann. Math. Statist. 37 (1966), 1554–1563. 10.1214/aoms/1177699147Search in Google Scholar
[9] L. E. Baum, T. Petrie, G. Soules and N. Weiss, A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains, Ann. Math. Statist. 41 (1970), 164–171. 10.1214/aoms/1177697196Search in Google Scholar
[10] L. E. Baum and G. R. Sell, Growth transformations for functions on manifolds, Pacific J. Math. 27 (1968), 211–227. 10.2140/pjm.1968.27.211Search in Google Scholar
[11] M. Bebbington, Identifying volcanic regimes using hidden Markov models, Geophys. J. Int. 171 (2007), no. 2, 921–942. 10.1111/j.1365-246X.2007.03559.xSearch in Google Scholar
[12] R. Billinton and A. Jonnavithula, Composite system adequacy assessment using sequential Monte Carlo simulation with variance reduction techniques, IEEE Proc. 144 (1997), 1–6. 10.1049/ip-gtd:19970763Search in Google Scholar
[13] M. Bishop and E. Thompson, Maximum likelihood alignment of DNA sequences, J. Molecular Biol. 190 (1986), no. 2, 159–165. 10.1016/0022-2836(86)90289-5Search in Google Scholar
[14] M. Y. Boudaren, E. Monfrini and W. Pieczynski, Unsupervised segmentation of random discrete data hidden with switching noise distributions, IEEE Signal Process. Lett. 19 (2012), no. 10, 619–622. 10.1109/LSP.2012.2209639Search in Google Scholar
[15] N. Bouleau, Processus stochastiques et applications, Hermann, Paris, 2000. Search in Google Scholar
[16] P. Brémaud, Markov Chains, Texts Appl. Math. 31, Springer, New York, 1999. 10.1007/978-1-4757-3124-8Search in Google Scholar
[17] H. Bunke and T. Caelli, Hidden Markov Models: Applications in Computer Vision, World Scientific, Singapore, 2001. 10.1142/4648Search in Google Scholar
[18] Q. Chen and L. Mili, Composite power system vulnerability evaluation to cascading failures using importance sampling and antithetic variates, IEEE Trans. Power Syst. 28 (2013), no. 3, 2321–2330. 10.1109/TPWRS.2013.2238258Search in Google Scholar
[19] W. Cho, S. W. Lee and J. H. Kim, Modeling and recognition of cursive words with hidden Markov models, Pattern Recognit. 28 (1995), no. 12, 1941–1953. 10.1016/0031-3203(95)00041-0Search in Google Scholar
[20] G. Churchill, Hidden Markov chains and the analysis of genome structure, Comput. Chem. 16 (1992), no. 2, 107–115. 10.1016/0097-8485(92)80037-ZSearch in Google Scholar
[21] M. DelRose, C. Wagner and P. Frederick, Evidence feed forward hidden Markov model: A new type of hidden Markov model, Int. J. Artificial Intelligence Appl. 2 (2011), 1–19. 10.5121/ijaia.2011.2101Search in Google Scholar
[22] S. L. DeRuiter, R. Langrock, T. Skirbutas, J. A. Goldbogen, J. Calambokidis, A. S. Friedlaender and B. L. Southall, A multivariate mixed hidden Markov model for blue whale behaviour and responses to sound exposure, Ann. Appl. Stat. 11 (2017), no. 1, 362–392. 10.1214/16-AOAS1008Search in Google Scholar
[23] R. Durbin, S. Eddy, A. Krogh and G. Mitchison, Biological Sequence Analysis: Probabilistic Models of Proteins and Nucleic Acids, Cambridge University, Cambridge, 1998. 10.1017/CBO9780511790492Search in Google Scholar
[24] R. Durrett, Probability Models for DNA Sequence Evolution, Probab. Appl. (New York), Springer, New York, 2002. 10.1007/978-1-4757-6285-3Search in Google Scholar
[25] S. N. Ethier and T. G. Kurtz, Markov Processes, Wiley Ser. Probab. Math. Stat., John Wiley & Sons, New York, 1986. 10.1002/9780470316658Search in Google Scholar
[26] W. J. Ewens, Mathematical Population Genetics. I. Theoretical Introduction, 2nd ed., Interdiscip. Appl. Math. 27, Springer, New York, 2004. 10.1007/978-0-387-21822-9Search in Google Scholar
[27] A. Gupta and B. Dhingra, Stock market prediction using hidden Markov models, Students Conference on Engineering and Systems, IEEE Press, Piscataway (2012), 1–4. 10.1109/SCES.2012.6199099Search in Google Scholar
[28] J. M. Hammersley and D. C. Handscomb, Monte Carlo Methods, John Wiley and Sons, New York, 1964. 10.1007/978-94-009-5819-7Search in Google Scholar
[29] D. He and C. H. Chen, Antithetic Variates, Wiley, New York, 2011. 10.1002/9780470400531.eorms0031Search in Google Scholar
[30] X. Huang, A. Acero, H.-W. Hon and R. Reddy, Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Vol. 95, Prentice Hall, Upper Saddle River, 2001. Search in Google Scholar
[31] X. Huang, Y. Ariki and M. A. Jack, Hidden Markov Models for Speech Recognition, Edinburgh University, Edinburgh, 1990. Search in Google Scholar
[32] F. Jelinek, L. Bahl and R. Mercer, Design of a linguistic statistical decoder for the recognition of continuous speech, IEEE Trans. Inform. Theory 21 (1975), no. 3, 250–256. 10.1109/TIT.1975.1055384Search in Google Scholar
[33] J. H. Matis and T. R. Kiffe, Stochastic Population Models. A Compartmental Perspective, Lect. Notes Stat. 145, Springer, New York, 2000. 10.1007/978-1-4612-1244-7Search in Google Scholar
[34] A. Nasroallah, Simulation de chaînes de Markov et techniques de réduction de la variance, Thèse de Doctorat IRISA, Rennes, 1991. Search in Google Scholar
[35] O. Netzer, J. M. Lattin and V. Srinivasan, A hidden Markov model of customer relationship dynamics, Marketing Sci. 27.2 (2008), 185–204. 10.1287/mksc.1070.0294Search in Google Scholar
[36] J. R. Norris, Markov Chains, Camb. Ser. Stat. Probab. Math. 2, Cambridge University, Cambridge, 1998. Search in Google Scholar
[37] L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, IEEE Proc. 77 (1989), no. 2, 257–286. 10.1016/B978-0-08-051584-7.50027-9Search in Google Scholar
[38] S. M. Ross, Extending simulation uses of antithetic variables: Partially monotone functions, random permutations, and random subsets, Math. Methods Oper. Res. 62 (2005), no. 3, 351–356. 10.1007/s00186-005-0038-0Search in Google Scholar
[39] R. Y. Rubinstein, Simulation and the Monte Carlo Method, John Wiley & Sons, New York, 1981. 10.1002/9780470316511Search in Google Scholar
[40] P. C. Sotirios and Y. Demiris, A reservoir-driven non-stationary hidden Markov model, Pattern Recogn. 45 (2012), no. 11, 3985–3996. 10.1016/j.patcog.2012.04.018Search in Google Scholar
[41] P. C. Sotirios and K. Dimitrios, Visual workflow recognition using a variational Bayesian treatment of multistream fused hidden Markov models, IEEE Trans. Circuits Syst. Video Technol. 22 (2012), no. 7, 1076–1086. 10.1109/TCSVT.2012.2189795Search in Google Scholar
[42] R. L. Stratonovič, Conditional Markov processes, Theory Probab. Appl. 5 (1960), 156–178. 10.1137/1105015Search in Google Scholar
[43] B. Tuffin, Variance reduction applied to product form multiclass queuing networks, ACM Trans. Model. Comput. Simul. 7 (1997), no. 4, 478–500. 10.1145/268403.268419Search in Google Scholar
[44] M. N. M. van Lieshout, Markov Point Processes and Their Applications, Imperial College Press, London, 2000. 10.1142/p060Search in Google Scholar
[45] C. J. Wellekens, J. Kangasharju and C. Milesi, The use of meta-HMM in multi-stream HMM training for automatic speech recognition, Proceedings of the 5th International Conference on Spoken Language, ISCA, Sydney (1998), 2991–2994. 10.21437/ICSLP.1998-193Search in Google Scholar
[46] J. R. Wilson, Proof of the antithetic-variates theorem for unbounded functions, Math. Proc. Cambridge Philos. Soc. 86 (1979), no. 3, 477–479. 10.1017/S0305004100056334Search in Google Scholar
[47] B. Ycart, Modèles et algorithmes Markoviens, Math. Appl.(Berlin) 39, Springer, Berlin, 2002. Search in Google Scholar
© 2022 Walter de Gruyter GmbH, Berlin/Boston