Decoding Event-related Potential from Ear-EEG Signals based on Ensemble Convolutional Neural Networks in Ambulatory Environment

TL;DR

This paper presents an ensemble convolutional neural network approach for decoding visual event-related potentials from ear-EEG signals in ambulatory settings, demonstrating robustness against movement artifacts and improved BCI performance.

Contribution

It introduces a novel ensemble CNN method tailored for ear-EEG signals in ambulatory environments, addressing movement artifacts and data imbalance issues.

Findings

BCI performance drops 3-14% during fast walking

Proposed method achieves 0.728 AUC on average

Method is robust to movement artifacts and data imbalance

Abstract

Recently, practical brain-computer interface is actively carried out, especially, in an ambulatory environment. However, the electroencephalography (EEG) signals are distorted by movement artifacts and electromyography signals when users are moving, which make hard to recognize human intention. In addition, as hardware issues are also challenging, ear-EEG has been developed for practical brain-computer interface and has been widely used. In this paper, we proposed ensemble-based convolutional neural networks in ambulatory environment and analyzed the visual event-related potential responses in scalp- and ear-EEG in terms of statistical analysis and brain-computer interface performance. The brain-computer interface performance deteriorated as 3-14% when walking fast at 1.6 m/s. The proposed methods showed 0.728 in average of the area under the curve. The proposed method shows robust to the ambulatory environment and imbalanced data as well.