Forward-Backward Smoothing for Hidden Markov Models of Point Pattern Data

This paper considers a discrete-time sequential latent model for point pattern data, specifically a hidden Markov model (HMM) where each observation is an instantiation of a random finite set (RFS). This so-called RFS-HMM is worthy of investigation since point pattern data are ubiquitous in artificial intelligence and data science. We address the three basic problems typically encountered in such a sequential latent model, namely likelihood computation, hidden state inference, and parameter estimation. Moreover, we develop algorithms for solving these problems including forward-backward smoothing for likelihood computation and hidden state inference, and expectation-maximisation for parameter estimation. Simulation studies are used to demonstrate key properties of RFS-HMM, whilst real data in the domain of human dynamics are used to demonstrate its applicability.

[1]  R. Mahler.  Multitarget Bayes filtering via first-order multitarget moments , 2003 .

[2]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[3]  Dinh Q. Phung,et al.  Learning Latent Activities from Social Signals with Hierarchical Dirichlet Processes , 2014 .

[4]  Dinh Q. Phung,et al.  Clustering for point pattern data , 2017, 2016 23rd International Conference on Pattern Recognition (ICPR).

[5]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[6]  Dinh Q. Phung,et al.  Model-based classification and novelty detection for point pattern data , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[7]  Daryl J. Daley,et al.  An Introduction to the Theory of Point Processes , 2013 .

[8]  D. Stoyan,et al.  Stochastic Geometry and Its Applications , 1989 .

[9]  Ronald P. S. Mahler,et al.  Statistical Multisource-Multitarget Information Fusion , 2007 .

[10]  Fanglin Chen,et al.  StudentLife: assessing mental health, academic performance and behavioral trends of college students using smartphones , 2014, UbiComp.

[11]  Vikram Krishnamurthy,et al.  A Bayesian EM algorithm for optimal tracking of a maneuvering target in clutter , 2002, Signal Process..

[12]  Svetha Venkatesh,et al.  Learning Hierarchical Hidden Markov Models with General State Hierarchy , 2004, AAAI.

[13]  Yanning Zhang,et al.  Hybrid Deep Neural Network--Hidden Markov Model (DNN-HMM) Based Speech Emotion Recognition , 2013, 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction.

[14]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[15]  Ba-Ngu Vo,et al.  Bayesian Filtering With Random Finite Set Observations , 2008, IEEE Transactions on Signal Processing.

[16]  Scott A. Sisson,et al.  Statistical Inference and Simulation for Spatial Point Processes , 2005 .

[17]  Svetha Venkatesh,et al.  MCNC: Multi-Channel Nonparametric Clustering from heterogeneous data , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[18]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[19]  Ba-Ngu Vo,et al.  A random finite set model for data clustering , 2014, 17th International Conference on Information Fusion (FUSION).

[20]  Ba-Ngu Vo,et al.  The Cauchy-Schwarz divergence for poisson point processes , 2014, 2014 IEEE Workshop on Statistical Signal Processing (SSP).

[21]  Ba-Ngu Vo,et al.  Closed-Form Solutions to Forward–Backward Smoothing , 2012, IEEE Transactions on Signal Processing.

[22]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[23]  Ronald P. S. Mahler,et al.  Advances in Statistical Multisource-Multitarget Information Fusion , 2014 .

[24]  V. Krishnamurthy,et al.  On maneuvering target tracking via the PMHT , 1997, Proceedings of the 36th IEEE Conference on Decision and Control.

[25]  A. Doucet,et al.  Sequential Monte Carlo methods for multitarget filtering with random finite sets , 2005, IEEE Transactions on Aerospace and Electronic Systems.

[26]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).