Login | Register

Data-free metrics for Dirichlet and generalized Dirichlet mixture-based HMMs - A practical study.


Data-free metrics for Dirichlet and generalized Dirichlet mixture-based HMMs - A practical study.

Bouguila, Nizar ORCID: https://orcid.org/0000-0001-7224-7940 and Epaillard, Elise ORCID: https://orcid.org/0000-0001-8777-0478 (2018) Data-free metrics for Dirichlet and generalized Dirichlet mixture-based HMMs - A practical study. Pattern Recognition . ISSN 00313203 (In Press)

[thumbnail of Bouguila 2018.pdf]
Text (application/pdf)
Bouguila 2018.pdf - Accepted Version
Available under License Spectrum Terms of Access.

Official URL: http://dx.doi.org/10.1016/j.patcog.2018.08.013


Approaches to design metrics between hidden Markov models (HMM) can be divided into two classes: data-based and parameter-based. The latter has the clear advantage of being deterministic and faster but only a very few similarity measures that can be applied to mixture-based HMMs have been proposed so far. Most of these metrics apply to the discrete or Gaussian HMMs and no comparative study have been led to the best of our knowledge. With the recent development of HMMs based on the Dirichlet and generalized Dirichlet distributions for proportional data modeling, we propose to design three new parametric similarity measures between these HMMs. Extensive experiments on synthetic data show the reliability of these new measures where the existing ones fail at giving expected results when some parameters vary. Illustration on real data show the clustering capability of these measures and their potential applications.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Concordia Institute for Information Systems Engineering
Item Type:Article
Authors:Bouguila, Nizar and Epaillard, Elise
Journal or Publication:Pattern Recognition
  • Natural Sciences and Engineering Research Council of Canada (NSERC)
Digital Object Identifier (DOI):10.1016/j.patcog.2018.08.013
Keywords:hidden Markov models; similarity measure; Dirichlet; generalized Dirichlet
ID Code:984282
Deposited By: ALINE SOREL
Deposited On:31 Aug 2018 19:31
Last Modified:27 Aug 2020 00:00


L.E. Baum, T. Petrie. Statistical inference for probabilistic functions of finite state Markov chains, The Ann. of Math. Stat., 37 (1966), pp. 1554-1563

O. Abdel-Hamid, H. Jiang. Fast speaker adaptation of hybrid NN/HMM model for speech recognition based on discriminative learning of speaker code, Acoust., Speech and Signal Proc., IEEE Int. Conf. on, Vancouver, BC, Canada, IEEE (2013), pp. 7942-7946

K. Tokuda, Y. Nankaku, T. Toda, H. Zen, J. Yamagishi, Y. Oura. Speech synthesis based on hidden Markov models, Proc. of the IEEE, 101 (2013), pp. 1234-1252

F. Alvaro, J.-A. Sanchez, J.-M. Benedi. Recognition of on-line handwritten mathematical expressions using 2D stochastic context-free grammars and hidden Markov models, Pattern Recognit. Lett., 35 (2014), pp. 58-67

J. Baumgartner, A.G. Flesia, J. Gimenez, J. Pucheta. A new image segmentation framework based on two-dimensional hidden Markov models, Integr. Comput.-Aided Eng., 23 (2016), pp. 1-13

L. Rossi, J. Chakareski, P. Frossard, S. Colonnese. A Poisson hidden Markov model for multiview video traffic, IEEE/ACM Trans. on Netw., 23 (2015), pp. 547-558

E. Epaillard, N. Bouguila. Proportional data modeling with hidden Markov models based on generalized Dirichlet and Beta-Liouville mixtures applied to anomaly detection in public areas, Pattern Recognit., 55 (2016), pp. 125-136

A. Soualhi, H. Razik, G. Clerc, D.D. Doan. Prognosis of bearing failures using hidden Markov models and the adaptive neuro-fuzzy inference system, IEEE Trans. on Ind. Electron., 61 (2014), pp. 2864-2874

Y. Cao, Y. Li, S. Coleman, A. Belatreche, T.M. McGinnity. Adaptive hidden Markov model with anomaly states for price manipulation detection, IEEE Trans. on Neural Netw. and Learn. Syst., 26 (2015), pp. 318-330

L.R. Rabiner, B.H. Juang. An introduction to hidden Markov models, IEEE ASSP Mag., 3 (1) (1986), pp. 4-16

E.L. Andrade, S. Blunsden, R.B. Fisher. Hidden Markov models for optical flow analysis in crowds, Pattern Recognit., 18th Int. Conf. on, IEEE (2006), pp. 460-463

M. Bicego, U. Castellani, V. Murino. A hidden Markov model approach for appearance-based 3d object recognition, Pattern Recognit. Lett., 26 (2005), pp. 2588-2599

F.B. Lung, M.H. Jaward, J. Parkkinen. Spatio-temporal descriptor for abnormal human activity detection, Mach. Vis. Appl., 14th IAPR Int. Conf. on, IEEE (2015), pp. 471-474

S.P. Chatzis, D.I. Kosmopoulos, T.A. Varvarigou. Robust sequential data modeling using an outlier tolerant hidden Markov model, IEEE Trans. on Pattern Anal. and Mach. Intell., 31 (2009), pp. 1657-1669

S.P. Chatzis. Hidden Markov models with nonelliptically contoured state densities, IEEE Trans. on Pattern Anal. and Mach. Intell., 32 (2010), pp. 2297-2304

A. Punzo, A. Maruotti. Clustering multivariate longitudinal observations: The contaminated Gaussian hidden Markov model, J. of Comput. and Graph. Stat., 25 (2016), pp. 1097-1116

L. Chen, D. Barber, J.-M. Odobez. Dynamical Dirichlet mixture model, IDIAP-RR, IDIAP (2007)

E. Epaillard, N. Bouguila. Hybrid hidden Markov model for mixed continuous/continuous and discrete/continuous data modeling, Multimed. Signal Proc., 17th IEEE Int. Workshop on, IEEE (2015), pp. 1-6

F. Cuzzolin, M. Sapienza. Learning pullback HMM distances, IEEE Trans. on Pattern Anal. and Mach. Intell., 36 (7) (2014), pp. 1483-1489

M.N. Do. Fast approximation of KullbackLeibler distance for dependence trees and hidden Markov models, IEEE Signal Proc. Lett., 10 (4) (2003), pp. 115-118

L. Chen, H. Man. st schemes for computing similarities between Gaussian HMMs and their applications in texture image classification, EURASIP J. on Appl. Signal Proc., 13 (2005), pp. 1984-1993

C.R. Wren, D.C. Minnen, S.G. Rao. Similarity-based analysis for large networks of ultra low resolution sensors, Pattern Recognition, 39 (10) (2006), pp. 1918-1931

D. Garcia-Garcia, E. Parrado-Hernandez, F. Diaz-de Maria. State-space dynamics distance for clustering sequential data, Pattern Recognition, 44 (5) (2011), pp. 1014-1022

S.M.E. Sahraeian, B.-J. Yoon. A novel low-complexity HMM similarity measure, IEEE Signal Proc. Lett., 18 (2) (2011), pp. 87-90

J. Zeng, J. Duan, C. Wu. A new distance measure for hidden Markov models, Expert Syst. with Appl., 37 (2010), pp. 1550-1555

B.-H. Juang, L.R. Rabiner. A probabilistic distance measure for hidden Markov models, AT&T Tech. J., 64 (2) (1985), pp. 391-408

E. Epaillard, N. Bouguila, D. Ziou. Classifying textures with only 10 visual-words using hidden Markov models with Dirichlet mixtures, Adapt. and Intell. Syst. - Proc. of the 3rd Int. Conf., Bournemouth, UK, Springer (2014), pp. 20-28

E. Epaillard, N. Bouguila. Hidden Markov models based on generalized Dirichlet mixtures for proportional data modeling, Artif. Neural Netw. in Pattern Recognit. - Proc. of the 6th IAPR TC3 Int. Workshop, 2014, Montreal, QC, Canada, Springer (2014), pp. 71-82

T. Jebara, R. Kondor. Bhattacharyya and expected likelihood kernels, B. Schölkopf, M.K. Warmuth (Eds.), 16th Annu. Conf. on Learn. Theory and 7th Kernel Workshop, Proc., Vol 2777 of Lecture Notes in Computer Science, Springer Berlin Heidelberg (2003), pp. 57-71

N. Bouguila, D. Ziou. High-dimensional unsupervised selection and estimation of a finite generalized Dirichlet mixture model based on minimum message length, IEEE Trans. on Pattern Anal. and Mach. Intell., 29 (2007), pp. 1716-1731

T.-T. Wong. Parameter estimation for generalized Dirichlet distributions from the sample estimates of the first and the second moments of random variables, Comput. Stat. and Data Anal., 54 (7) (2010), pp. 1756-1765

R. Jonker, A. Volgenant. A shortest augmenting path algorithm for dense and spare linear assignment problems, Comput., 38 (1987), pp. 325-340

J.R. Hershey, P.A. Olsen. Approximating the Kullback Leibler divergence between Gaussian mixture models, Acoust., Speech and Signal Proc., IEEE Int. Conf. on, 4, IEEE (2007), pp. 317-320

W. Masoudimansour, N. Bouguila. Generalized Dirichlet mixture matching projection for supervised linear dimensionality reduction of proportional data, Multimed. Signal Proc., IEEE 18th Int. Workshop on, IEEE (2016), pp. 1-6

S. Merugu, J. Ghosh. A privacy-sensitive approach to distributed clustering, Pattern Recognition Letters, 26 (4) (2005), pp. 399-410

Y. Yang, J. Jiang. Bi-weighted ensemble via hmm-based approaches for temporal data clustering, Pattern Recognition, 76 (2018), pp. 391-403

V. Mahadevan, W. Li, V. Bhalodia, N. Vasconcelos. Anomaly detection in crowded scenes, Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on (2010), pp. 1975-1981

A. Zaharescu, R. Wildes. Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event-driven processing. K. Daniilidis, P. Maragos, N. Paragios (Eds.), ECCV (1), Lecture Notes in Computer Science, 6311, Springer (2010), pp. 563-576

k-medoids implementation. URL http://www.mathworks.com/matlabcentral/fileexchange/28860-kmedioids
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top