Next Article in Journal
Augmented Reality: A Systematic Review of Its Benefits and Challenges in E-learning Contexts
Next Article in Special Issue
Automatic Segmentation of Macular Edema in Retinal OCT Images Using Improved U-Net++
Previous Article in Journal
Structural, Magnetic and Mechanical Properties of Nd16 (Fe76−xCox)B8 0 ≤ x ≤ 25 Alloys
Previous Article in Special Issue
Total Variation-Based Noise Reduction Image Processing Algorithm for Confocal Laser Scanning Microscopy Applied to Activity Assessment of Early Carious Lesions
Open AccessArticle

Decoding Visual Motions from EEG Using Attention-Based RNN

College of Intelligence Science and Technology, National University of Defense Technology, Changsha 410073, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(16), 5662; https://doi.org/10.3390/app10165662
Received: 13 July 2020 / Revised: 8 August 2020 / Accepted: 11 August 2020 / Published: 14 August 2020
(This article belongs to the Special Issue Image Processing Techniques for Biomedical Applications)
The main objective of this paper is to use deep neural networks to decode the electroencephalography (EEG) signals evoked when individuals perceive four types of motion stimuli (contraction, expansion, rotation, and translation). Methods for single-trial and multi-trial EEG classification are both investigated in this study. Attention mechanisms and a variant of recurrent neural networks (RNNs) are incorporated as the decoding model. Attention mechanisms emphasize task-related responses and reduce redundant information of EEG, whereas RNN learns feature representations for classification from the processed EEG data. To promote generalization of the decoding model, a novel online data augmentation method that randomly averages EEG sequences to generate artificial signals is proposed for single-trial EEG. For our dataset, the data augmentation method improves the accuracy of our model (based on RNN) and two benchmark models (based on convolutional neural networks) by 5.60%, 3.92%, and 3.02%, respectively. The attention-based RNN reaches mean accuracies of 67.18% for single-trial EEG decoding with data augmentation. When performing multi-trial EEG classification, the amount of training data decreases linearly after averaging, which may result in poor generalization. To address this deficiency, we devised three schemes to randomly combine data for network training. Accordingly, the results indicate that the proposed strategies effectively prevent overfitting and improve the correct classification rate compared with averaging EEG fixedly (by up to 19.20%). The highest accuracy of the three strategies for multi-trial EEG classification achieves 82.92%. The decoding performance for the methods proposed in this work indicates they have application potential in the brain–computer interface (BCI) system based on visual motion perception. View Full-Text
Keywords: electroencephalography; attention mechanisms; recurrent neural networks; data augmentation; brain–computer interface; visual motion perception electroencephalography; attention mechanisms; recurrent neural networks; data augmentation; brain–computer interface; visual motion perception
Show Figures

Graphical abstract

MDPI and ACS Style

Yang, D.; Liu, Y.; Zhou, Z.; Yu, Y.; Liang, X. Decoding Visual Motions from EEG Using Attention-Based RNN. Appl. Sci. 2020, 10, 5662.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop