Two-branch 3D convolutional neural network for motor imagery EEG decoding

Jul 26, 2021Journal of neural engineering

Using a two-part 3D neural network to decode brain signals from imagined movement

AI simplified

Circadian Biology on OpenScience ↗PubMed ↗DOI ↗

Abstract

The proposed two-branch 3D CNN method improves MI-EEG decoding accuracy by 4.42% compared to the best existing methods.

A concise 3D representation for MI-EEG data is utilized to enhance spatial feature extraction.
Two separate branches in the CNN focus on extracting spatial and temporal features, minimizing interference between them.
The introduction of central loss within the framework aims to further boost decoding accuracy.
A new 3D data augmentation technique using cyclic translation of the time dimension is implemented to reduce overfitting.
Experiments on the BCI competition IV 2a dataset validate the effectiveness of the proposed decoding method.

AI simplified

The original motor imagery electroencephalography (MI-EEG) data contains not only temporal features but also a large number of spatial features related to the distribution of electrodes on the brain. However, in the process of MI-EEG decoding, most of the current convolutional neural network (CNN) based methods do not make the utmost of the spatial features related to electrode distribution.In this study, we adopt a concise 3D representation for the MI-EEG data to take full advantage of the spatial features and propose a two-branch 3D CNN (TB-3D CNN) for the 3D representation of MI-EEG data. First, the spatial and temporal features of the input 3D samples are extracted by the spatial and temporal feature learning branches, respectively, to avoid the mutual interference between the temporal and spatial features. Then, the central loss is introduced into the TB-3D CNN framework to further improve the MI-EEG decoding accuracy. And a 3D data augmentation method based on the cyclic translation of time dimension is proposed for the 3D representation method to alleviate the overfitting problem.Some experiments are conducted on the famous BCI competition IV 2a dataset to evaluate the effectiveness of the proposed MI-EEG decoding method. The experimental results comparison with some state-of-the-art methods demonstrates that the average accuracy of our method is 4.42% higher than that of the best of the comparative methods.The proposed MI-EEG decoding method has great promise to improve the performance of motor imagery brain-computer interface system. Objective. Approach. Main results. Significance.

Full Text

Full text is available at the source.

View full text (HTML) ↗View full text (PDF) ↗

Two-branch 3D convolutional neural network for motor imagery EEG decoding

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief

Abstract

Full Text

Related papers

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the circadian biology brief