• Home
  • Search
  • Multitask Gaussian processes for multivariate physiological time-series analysis.
  • Cite Icon164
  • https://doi.org/10.1109/tbme.2014.2351376Copy DOI Icon

Multitask Gaussian processes for multivariate physiological time-series analysis.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Gaussian process (GP) models are a flexible means of performing nonparametric Bayesian regression. However, GP models in healthcare are often only used to model a single univariate output time series, denoted as single-task GPs (STGP). Due to an increasing prevalence of sensors in healthcare settings, there is an urgent need for robust multivariate time-series tools. Here, we propose a method using multitask GPs (MTGPs) which can model multiple correlated multivariate physiological time series simultaneously. The flexible MTGP framework can learn the correlation between multiple signals even though they might be sampled at different frequencies and have training sets available for different intervals. Furthermore, prior knowledge of any relationship between the time series such as delays and temporal behavior can be easily integrated. A novel normalization is proposed to allow interpretation of the various hyperparameters used in the MTGP. We investigate MTGPs for physiological monitoring with synthetic data sets and two real-world problems from the field of patient monitoring and radiotherapy. The results are compared with standard Gaussian processes and other existing methods in the respective biomedical application areas. In both cases, we show that our framework learned the correlation between physiological time series efficiently, outperforming the existing state of the art.

Similar Papers
  • Conference Article
  • Citations22

Multi-task Gaussian process models for biomedical applications

  • Jun 01, 2014
  • Robert Durichen +4
  • Conference Article
  • Citations6

A New Approach to Building the Gaussian Process Model for Expensive Multi-objective Optimization

  • Aug 01, 2019
  • Jianping Luo +2
  • Research Article
  • Citations216

A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data

  • Feb 10, 2015
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Marzyeh Ghassemi +6
  • Preprint Article

Stacking Gaussian Processes to Improve pKa Predictions in the SAMPL7 Challenge

  • May 24, 2021
  • ChemRxiv
  • Robert Raddi +1
  • Research Article
  • Citations7

Stacking Gaussian processes to improve predictions in the SAMPL7 challenge.

  • Aug 07, 2021
  • Journal of computer-aided molecular design
  • Robert M Raddi +1
  • Book Chapter
  • Citations6

Physics-Aware Gaussian Processes for Earth Observation

  • Jan 01, 2017
  • Gustau Camps-Valls +6
  • Conference Article
  • Citations1

Machine-Learning Assisted X-Ray Spectroscopy for High- Throughput Characterization of Magnetic Materials

  • Apr 01, 2018
  • T Ueno +2
  • Book Chapter
  • Citations3

Closed-Loop Control with Evolving Gaussian Process Models

  • Jan 01, 2016
  • Juš Kocijan +1
  • Research Article
  • Citations106

Physics-aware Gaussian processes in remote sensing

  • Mar 22, 2018
  • Applied Soft Computing
  • Gustau Camps-Valls +7
  • Preprint Article

Advances in Gaussian Processes for Earth Sciences: Physics-aware, interpretability and consistency

  • Mar 23, 2020
  • Gustau Camps-Valls +5
  • Book Chapter

Prognosis Using Gaussian Process Model

  • Jan 07, 2022
  • Shiyu Zhou +1
  • Conference Article
  • Citations20

Evolving Gaussian process models for predicting chaotic time-series

  • Jun 01, 2014
  • Dejan Petelin +1
  • Conference Article
  • Citations11

Music genre classification using Gaussian Process models

  • Sep 01, 2013
  • Konstantin Markov +1
  • Conference Article
  • Citations37

Generalized Gaussian process models

  • Jun 01, 2011
  • Antoni B Chan +1
  • Research Article
  • Citations246

Quantitative prediction of subjective pain intensity from whole-brain fMRI data using Gaussian processes

  • Oct 29, 2009
  • NeuroImage
  • Andre Marquand +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.