An Analysis of Two Common Reference Points for EEGs

TL;DR

This study compares two common EEG reference points, LE and AR, analyzing their statistical differences and impact on machine learning classification performance, revealing that training on LE data yields better results than AR.

Contribution

It provides a detailed statistical comparison of LE and AR EEG montages and evaluates their effects on machine learning classification accuracy.

Findings

LE-trained systems outperform AR-trained systems (77.2% vs. 61.4%)

Training on both datasets reduces performance (71.4%)

Statistical features like mean and variance influence performance, but cepstral mean subtraction does not improve results.

Abstract

Clinical electroencephalographic (EEG) data varies significantly depending on a number of operational conditions (e.g., the type and placement of electrodes, the type of electrical grounding used). This investigation explores the statistical differences present in two different referential montages: Linked Ear (LE) and Averaged Reference (AR). Each of these accounts for approximately 45% of the data in the TUH EEG Corpus. In this study, we explore the impact this variability has on machine learning performance. We compare the statistical properties of features generated using these two montages, and explore the impact of performance on our standard Hidden Markov Model (HMM) based classification system. We show that a system trained on LE data significantly outperforms one trained only on AR data (77.2% vs. 61.4%). We also demonstrate that performance of a system trained on both data sets is somewhat compromised (71.4% vs. 77.2%). A statistical analysis of the data suggests that mean, variance and channel normalization should be considered. However, cepstral mean subtraction failed to produce an improvement in performance, suggesting that the impact of these statistical differences is subtler.