Decoding of Intuitive Visual Motion Imagery Using Convolutional Neural Network under 3D-BCI Training Environment

TL;DR

This paper presents a novel 3D-BCI platform utilizing visual motion imagery and CNNs to decode user intentions with promising accuracy, advancing intuitive BCI applications like neuroprostheses and robotic control.

Contribution

It introduces a 3D BCI training environment, selects optimal EEG channels via functional connectivity, and proposes a CNN architecture achieving 67.5% accuracy for visual motion imagery classification.

Findings

High correlation between prefrontal and occipital lobes during imagery.

Selected EEG channels improve decoding performance.

Achieved 67.5% classification accuracy across subjects.

Abstract

In this study, we adopted visual motion imagery, which is a more intuitive brain-computer interface (BCI) paradigm, for decoding the intuitive user intention. We developed a 3-dimensional BCI training platform and applied it to assist the user in performing more intuitive imagination in the visual motion imagery experiment. The experimental tasks were selected based on the movements that we commonly used in daily life, such as picking up a phone, opening a door, eating food, and pouring water. Nine subjects participated in our experiment. We presented statistical evidence that visual motion imagery has a high correlation from the prefrontal and occipital lobes. In addition, we selected the most appropriate electroencephalography channels using a functional connectivity approach for visual motion imagery decoding and proposed a convolutional neural network architecture for classification. As a result, the averaged classification performance of the proposed architecture for 4 classes from 16 channels was 67.50 % across all subjects. This result is encouraging, and it shows the possibility of developing a BCI-based device control system for practical applications such as neuroprosthesis and a robotic arm.