Prediction of Synchrostate Transitions in EEG Signals Using Markov Chain Models

TL;DR

This study models EEG synchrostate transitions during face perception tasks using Markov chains, estimating transition probabilities and comparing prediction accuracies to understand brain state dynamics.

Contribution

It introduces a Markov chain-based stochastic model for predicting EEG synchrostate transitions, a novel approach in analyzing brain state dynamics during cognitive tasks.

Findings

First and second order Markov models yield comparable prediction accuracies.

Transition probability matrices effectively characterize synchrostate dynamics.

Model predictions improve understanding of brain state transitions during face perception.

Abstract

This paper proposes a stochastic model using the concept of Markov chains for the inter-state transitions of the millisecond order quasi-stable phase synchronized patterns or synchrostates, found in multi-channel Electroencephalogram (EEG) signals. First and second order transition probability matrices are estimated for Markov chain modelling from 100 trials of 128-channel EEG signals during two different face perception tasks. Prediction accuracies with such finite Markov chain models for synchrostate transition are also compared, under a data-partitioning based cross-validation scheme.