Get a new perspective on EEG: Convolutional neural network encoders for parametric t-SNE.

Abstract

Backgroundt-distributed stochastic neighbor embedding (t-SNE) is a method for reducing high-dimensional data to a low-dimensional representation and is mostly used for visualizing data. In parametric t-SNE, a neural network learns to reproduce this mapping. When used for EEG analysis, the data is usually first transformed into a set of features, but it is not known which features are optimal. New methodThe principle of t-SNE was used to train convolutional neural network (CNN) encoders to learn to produce both a high- and a low-dimensional representation, eliminating the need for feature engineering. A simple neighbor distribution based on ranked distances was used for the high-dimensional representation instead of the traditional normal distribution. To evaluate the method, the Temple University EEG Corpus was used to create three datasets with distinct EEG characters: 1) wakefulness and sleep, 2) interictal epileptiform discharges, and 3) seizure activity. ResultsThe CNN encoders for the three datasets produced low-dimensional representations of the datasets with a global and local structure that conformed well to the EEG characters and generalized to new data. Comparison to existing methodsCompared to parametric t-SNE for either a short-time Fourier transforms or wavelet representation of the datasets, the developed CNN encoders performed equally well but generally produced a higher degree of clustering. ConclusionsThe developed principle is promising and could be further developed to create general tools for exploring relations in EEG data, e.g., visual summaries of recordings, and trends for continuous EEG monitoring. It might also be used to generate features for other types of machine learning.