EEG Correlation at a Distance: A Re-Analysis of Two Studies Using a Machine Learning Approach
16 Pages Posted: 14 Jan 2019
Date Written: December 16, 2018
In this study, data from two studies relative to the relationship between the EEG activities of two isolated and physically separated subjects were re-analyzed using machine-learning algorithms. The first group of data consisted of 25 pairs of participants and the stimulation of one member of each pair consisted of continuous visual and auditory 500 Hz signals of 1 second duration, applied simultaneously. The other group of data consisted of 20 pairs of participants and one member of each pair received 900 Hz visual and auditory stimuli of 1 second duration with on-off modulation at 10, 12, and 14 Hz. When a ‘linear discriminant classifier’ was applied, it was possible in the first group of data to correctly classify 50.74% of the EEG activity of non-stimulated participants as correlated to the remote sensorial stimulation. In the second data group the percentage of correctly classified non-stimulated EEG activity was 51.17%, 50.45% e 51.91% respectively for the 10, 12, and 14 Hz stimulations. The analysis of EEG activity using machine-learning algorithms has produced advances in the study of the connection between the EEG activities of the stimulated partner and the isolated distant partner, proving that a relationship also exists regarding the stimulation frequency. Phenomenon will open new insight into the possibility of non-conventional connection of physically separated EEG signals.
Keywords: EEG, Correlation at Distance, Machine Learning, Linear Discrimination Analysis
Suggested Citation: Suggested Citation