An unsupervised subject identification technique using EEG signals

In this work, EEG spectral features of different subjects are uniquely mapped into a 2D feature space. Such distinctive 2D features pave the way to identify subjects from their EEG spectral characteristics in an unsupervised manner without any prior knowledge. First, we extract power spectral density of EEG signals in different frequency bands. Next, we use t-distributed stochastic neighbor embedding to map data points from high dimensional space in a visible 2D space. Such non-linear data embedding method visualizes different subjects' data points as well-separated islands in two dimensions. We use a fuzzy c-means clustering technique to identify different subjects without any prior knowledge. The experimental results show that our proposed method efficiently (precision greater than 90%) discriminates 10 subjects using only the spectral information within their EEG signals.