An Exploration of Optimal Parameters for Efficient Blind Source Separation of EEG Recordings Using AMICA

TL;DR

This paper investigates how to optimally set parameters in the AMICA algorithm for EEG source separation, analyzing the impact on decomposition quality and runtime to improve practical application.

Contribution

It provides systematic analysis and recommendations for parameter selection in AMICA, enhancing its efficiency and effectiveness for EEG analysis.

Findings

Optimal parameter settings improve decomposition quality

Certain parameters significantly affect runtime and accuracy

Guidelines help users choose better initial parameters

Abstract

EEG continues to find a multitude of uses in both neuroscience research and medical practice, and independent component analysis (ICA) continues to be an important tool for analyzing EEG. A multitude of ICA algorithms for EEG decomposition exist, and in the past, their relative effectiveness has been studied. AMICA is considered the benchmark against which to compare the performance of other ICA algorithms for EEG decomposition. AMICA exposes many parameters to the user to allow for precise control of the decomposition. However, several of the parameters currently tend to be set according to "rules of thumb" shared in the EEG community. Here, AMICA decompositions are run on data from a collection of subjects while varying certain key parameters. The running time and quality of decompositions are analyzed based on two metrics: Pairwise Mutual Information (PMI) and Mutual Information Reduction (MIR). Recommendations for selecting starting values for parameters are presented.