Visualizing States of Time-Series Data by Autoregressive Gaussian Process Dynamical Models
- 20 September 2017
- journal article
- Published by Fuji Technology Press Ltd. in Journal of Advanced Computational Intelligence and Intelligent Informatics
- Vol. 21 (5), 825-831
- https://doi.org/10.20965/jaciii.2017.p0825
Abstract
Gaussian process dynamical models (GPDMs) are used for nonlinear dimensionality reduction in time series by means of Gaussian process priors. An extension of GPDMs is proposed for visualizing the states of time series. The conventional GPDM approach associates a state with an observation value. Therefore, observations changing over time cannot be represented by a single state. Consequently, the resulting visualization of state transition is difficult to understand, as states change when the observation values change. To overcome this issue, autoregressive GPDMs, called ARGPDMs, are proposed. They associate a state with a vector autoregressive (VAR) model. Therefore, observations changing over time can be represented by a single state. The resulting visualization is easier to understand, as states change only when the VAR model changes. We demonstrate experimentally that the ARGPDM approach provides better visualization compared with conventional GPDMs.Keywords
This publication has 9 references indexed in Scilit:
- Gaussian Process Dynamical Models for hand gesture interpretation in Sign LanguagePattern Recognition Letters, 2011
- Generating Video Textures by PPCA and Gaussian Process Dynamical ModelLecture Notes in Computer Science, 2009
- Time Series AnalysisWiley Series in Probability and Statistics, 2008
- Multiple Human Tracking Using Particle Filter with Gaussian Process Dynamical ModelEURASIP Journal on Image and Video Processing, 2008
- Gaussian Process Dynamical Models for Human MotionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- 3D People Tracking with Gaussian Process Dynamical ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Gaussian Processes for Machine LearningPublished by MIT Press ,2005
- Self-Organizing MapsPublished by Springer Science and Business Media LLC ,2001
- A scaled conjugate gradient algorithm for fast supervised learningNeural Networks, 1993