Forward-backward smoothing for hidden Markov models of point pattern data

Nhan Dam, Dinh Phung, Ba Ngu Vo, Viet Huynh

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2017 International Conference on Data Science and Advanced Analytics, DSAA 2017
Subtitle of host publicationTokyo, Japan 19-21 October 2017
EditorsTakashi Washio, Joao Gama , Ying Li , Rajesh Parekh , Huan Liu , Albert Bifet , Richard D. De Veaux
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages252-261
Number of pages10
ISBN (Electronic)9781509050048
ISBN (Print)9781509050055
DOIs
Publication statusPublished - 2017
EventIEEE International Conference on Data Science and Advanced Analytics 2017 - Tokyo, Japan
Duration: 19 Oct 201721 Oct 2017
Conference number: 4th
http://www.dslab.it.aoyama.ac.jp/dsaa2017/

Conference

ConferenceIEEE International Conference on Data Science and Advanced Analytics 2017
Abbreviated titleDSAA 2017
CountryJapan
CityTokyo
Period19/10/1721/10/17
Internet address

Keywords

  • Discrete states
  • Hidden Markov models
  • Point pattern data
  • Point processes
  • Random finite sets
  • Sequential models
  • Set-valued data

Cite this