Using Dynamic Bayesian Networks for modeling EEG topographic sequences

Abstract

In this work we present a methodology for modeling the trajectory of EEG topography over time, using Dynamic Bayesian Networks (DBNs). Based on the microstate model we are using DBNs to model the evolution of the EEG topography. Analysis of the microstate model is being usually limited in the wide band signal or an isolated band. We are using Coupled Hidden Markov Models (CHMM) and a two level influence model in order to model the temporal evolution and the coupling of the topography states in three bands, delta, theta and alpha. We are applying this methodology for the classification of target and non-target single trial from a visual detection task. The results indicate that taking under consideration the interaction among the different bands improves the classification of single trials.

A primer on coupled state-switching models for multiple interacting time series

“…The explicit modelling of dependencies between the state variables can increase estimation accuracy, may decrease state classification error and generally provide new opportunities for meaningful inference related to the correlation between processes. The potential of CHMMs has already been recognised in particular in engineering, where these models have been applied in various classification and signal processing tasks such as action recognition (Brand et al, 1997), audio-visual speech recognition (Nefian et al, 2002, bearing fault recognition (Zhou et al, 2016), and EEG, ECG and PCG classification (Michalopoulos and Bourbakis, 2014;Oliveira et al, 2002). Due to technological advances for example in animal tracking and in EHRs (as illustrated in Section 4), and generally the rapid growth in the amount of multi-stream data collected, we anticipate CHMMs to gain popularity also in other statistical modelling tasks such as forecasting or general inference on data-generating processes.…”

“…Coupled hidden Markov models (CHMMs) extend the basic HMM framework by assuming distinct but correlated state sequences that underlie the observed variables, hence 'coupling' the state processes. Since their first appearance in Brand (1997), they have been further developed and applied, for example, to classify electroencephalography data (Michalopoulos and Bourbakis, 2014), to model interactions of suspects in forensics (Brewer et al, 2006) and to detect bradycardia events from electrocardiography data (Ghahjaverestan et al, 2016). CHMMs can be considered as established tools within the engineering literature, where they are commonly applied in classification tasks, for example, emotion recognition from audio-visual signals (Lin et al, 2012) or gesture recognition from hand tracking data (Brand et al, 1997).…”

Tractable Maximum Likelihood Estimation for Latent Structure Influence Models With Applications to EEG & ECoG Processing

“…The re-estimation transformation is derived by applying (12) to individual auxiliary functions Q πc (λ, πc ),…”

“…Study [12] demonstrates a CHMM-based methodology for modeling the trajectory of EEG topography over time. This methodology classifies single trials from visual detection tasks as target and non-target.…”