Multivariate Time-Series Classification Using the Hidden-Unit Logistic Model

Journal Article (2018)
Author(s)

Wenjie Pei (TU Delft - Pattern Recognition and Bioinformatics)

Hamdi Dibeklioglu (TU Delft - Pattern Recognition and Bioinformatics)

David M.J. Tax (TU Delft - Pattern Recognition and Bioinformatics)

Laurens van der Maaten (TU Delft - Pattern Recognition and Bioinformatics)

DOI related publication
https://doi.org/10.1109/TNNLS.2017.2651018 Final published version
More Info
expand_more
Publication Year
2018
Language
English
Bibliographical Note
Accepted Author Manuscript
Journal title
IEEE Transactions on Neural Networks and Learning Systems
Issue number
4
Volume number
29
Pages (from-to)
920-931
Downloads counter
339
Collections
Institutional Repository
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

We present a new model for multivariate time-series classification, called the hidden-unit logistic model (HULM), that uses binary stochastic hidden units to model latent structure in the data. The hidden units are connected in a chain structure that models temporal dependencies in the data. Compared with the prior models for time-series classification such as the hidden
conditional random field, our model can model very complex decision boundaries, because the number of latent states grows exponentially with the number of hidden units. We demonstrate the strong performance of our model in experiments on a variety of (computer vision) tasks, including handwritten character recognition, speech recognition, facial expression, and action recognition. We also present a state-of-the-art system for facial
action unit detection based on the HULM.

Files

7688767_HULM.pdf
(pdf | 4.05 Mb)
License info not available