Open AccessJournal Article
Hidden Markov mixtures of experts with an application to EEG recordings from sleep
Citations
More filters
Proceedings Article
A Dynamic HMM for On-line Segmentation of Sequential Data
Jens Kohlmorgen,Steven Lemm +1 more
TL;DR: The main idea of the approach is to track and segment changes of the probability density of the data in a sliding window on the incoming data stream using an HMM with a dynamically changing number of states and an on-line variant of the Viterbi algorithm that performs an unsupervised segmentation and classification of theData on-the-fly.
Journal ArticleDOI
Identification of nonstationary dynamics in physiological recordings.
TL;DR: A novel framework for the analysis of time series from dynamical systems that alternate between different operating modes by using predictive models, which has a high temporal resolution and reveals previously unclassified details of the transitions.
Journal ArticleDOI
Automatic detection of spindles and K-complexes in sleep EEG using switching multiple models
TL;DR: This work investigates the use of switching linear Gaussian state space models for the segmentation and automatic labelling of Stage 2 sleep EEG data characterised by spindles and K-complexes, and proposes a novel semi-supervised model allocation approach, allowing new unknown modes to be learnt in real time.
Journal ArticleDOI
Modelling nonlinear count time series with local mixtures of Poisson autoregressions
TL;DR: A novel class of nonlinear models is studied based on local mixtures of autoregressive Poisson time series, which are a special case of the mixtures-of-experts class of models, which is considerably flexible in modelling the conditional mean function.
Journal ArticleDOI
On geometric ergodicity of CHARME models
TL;DR: In this paper, the authors consider a CHARME model, a class of generalized mixture of nonlinear nonparametric AR-ARCH time series, and apply the theory of Markov models to derive asymptotic stability of this model.