Decoding index finger position from EEG using random forests

TL;DR

This study demonstrates that non-invasive EEG signals can be used to decode the position of an individual's index finger on a keyboard, with high beta power over sensorimotor cortex being most informative.

Contribution

It shows for the first time that non-invasive EEG can differentiate finger positions with cross-subject generalization using machine learning.

Findings

High beta power over sensorimotor cortex is most informative.

Random forests achieve above-chance decoding accuracy.

Finger position decoding generalizes across individuals.

Abstract

While invasively recorded brain activity is known to provide detailed information on motor commands, it is an open question at what level of detail information about positions of body parts can be decoded from non-invasively acquired signals. In this work it is shown that index finger positions can be differentiated from non-invasive electroencephalographic (EEG) recordings in healthy human subjects. Using a leave-one-subject-out cross-validation procedure, a random forest distinguished different index finger positions on a numerical keyboard above chance-level accuracy. Among the different spectral features investigated, high $\beta$-power (20-30 Hz) over contralateral sensorimotor cortex carried most information about finger position. Thus, these findings indicate that finger position is in principle decodable from non-invasive features of brain activity that generalize across individuals.