Analyzing EEG Data with Machine and Deep Learning: A Benchmark

TL;DR

This paper presents a comprehensive benchmark of machine and deep learning models for EEG signal classification, comparing common architectures to identify effective starting points for future EEG analysis research.

Contribution

It introduces the first benchmark study comparing four widespread models for EEG classification, guiding future model selection and development.

Findings

CNN and LSTM perform best for EEG classification

Multilayer perceptron is a simple baseline

Gated recurrent units offer competitive performance

Abstract

Nowadays, machine and deep learning techniques are widely used in different areas, ranging from economics to biology. In general, these techniques can be used in two ways: trying to adapt well-known models and architectures to the available data, or designing custom architectures. In both cases, to speed up the research process, it is useful to know which type of models work best for a specific problem and/or data type. By focusing on EEG signal analysis, and for the first time in literature, in this paper a benchmark of machine and deep learning for EEG signal classification is proposed. For our experiments we used the four most widespread models, i.e., multilayer perceptron, convolutional neural network, long short-term memory, and gated recurrent unit, highlighting which one can be a good starting point for developing EEG classification models.