CNN-based Approaches For Cross-Subject Classification in Motor Imagery: From The State-of-The-Art to DynamicNet

TL;DR

This paper reviews recent deep learning methods for motor imagery EEG classification, introduces DynamicNet for flexible model implementation, and demonstrates EEGNet's superior cross-subject classification performance over traditional methods.

Contribution

It presents DynamicNet, a new flexible tool for deep learning in EEG classification, and shows EEGNet's improved cross-subject accuracy compared to FBCSP.

Findings

EEGNet outperforms FBCSP by about 25% in cross-subject classification.

DynamicNet enables quick implementation of CNN-based EEG classifiers.

Deep learning approaches enhance cross-subject MI classification performance.

Abstract

Motor imagery (MI)-based brain-computer interface (BCI) systems are being increasingly employed to provide alternative means of communication and control for people suffering from neuro-motor impairments, with a special effort to bring these systems out of the controlled lab environments. Hence, accurately classifying MI from brain signals, e.g., from electroencephalography (EEG), is essential to obtain reliable BCI systems. However, MI classification is still a challenging task, because the signals are characterized by poor SNR, high intra-subject and cross-subject variability. Deep learning approaches have started to emerge as valid alternatives to standard machine learning techniques, e.g., filter bank common spatial pattern (FBCSP), to extract subject-independent features and to increase the cross-subject classification performance of MI BCI systems. In this paper, we first present a review of the most recent studies using deep learning for MI classification, with particular attention to their cross-subject performance. Second, we propose DynamicNet, a Python-based tool for quick and flexible implementations of deep learning models based on convolutional neural networks. We show-case the potentiality of DynamicNet by implementing EEGNet, a well-established architecture for effective EEG classification. Finally, we compare its performance with FBCSP in a 4-class MI classification over public datasets. To explore its cross-subject classification ability, we applied three different cross-validation schemes. From our results, we demonstrate that DynamicNet-implemented EEGNet outperforms FBCSP by about 25%, with a statistically significant difference when cross-subject validation schemes are applied.