Estimation of phase in EEG rhythms for real-time applications

TL;DR

This paper introduces machine learning methods to accurately estimate the phase of EEG alpha rhythms in real-time and offline scenarios, overcoming challenges posed by non-stationarity and noise.

Contribution

It presents novel machine learning approaches that mimic non-causal signal processing causally, improving phase estimation accuracy in EEG analysis.

Findings

Higher accuracy than standard methods in phase estimation

Effective in real-time and offline EEG analysis

Minimal pre-processing required for accurate estimation

Abstract

Objective. We identify two linked problems related to estimating the phase of the alpha rhythm when the signal after a specific event is unknown (real-time case), or corrupted (offline analysis). We propose methods to estimate the phase prior to such events. Approach. Machine learning is used to mimic a non-causal signal-processing chain with a purely causal one. Main results. We demonstrate the ability of these methods to estimate instantaneous phase from an electroencephalography signal subjected to very minor pre-processing with higher accuracy than more standard signal-processing methods. Significance. Phase estimation of EEG-rhythms is a challenge due to non-stationarity and low signal to noise ratio. The methods presented enable scientists and engineers to achieve relatively low error by optimizing causal phase estimation on a non-causally processed signal for a real-time experiments and offline analysis.