A Multi-Scale Activity Transition Network for Data Translation in EEG Signals Decoding
- Authors
- Lin, Bo; Deng, Shuiguang; Gao, Honghao; Yin, Jianwei
- Issue Date
- Sep-2021
- Publisher
- IEEE COMPUTER SOC
- Keywords
- Electroencephalography; Convolution; Brain modeling; Recurrent neural networks; Decoding; Brain-computer interfaces; Electroencephalogram; convolutional neural networks; invariance; data translation; pyramid of activity states
- Citation
- IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, v.18, no.5, pp.1699 - 1709
- Journal Title
- IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
- Volume
- 18
- Number
- 5
- Start Page
- 1699
- End Page
- 1709
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/82476
- DOI
- 10.1109/TCBB.2020.3024228
- ISSN
- 1545-5963
- Abstract
- Electroencephalogram (EEG) is a non-invasive collection method for brain signals. It has broad prospects in brain-computer interface (BCI) applications. Recent advances have shown the effectiveness of the widely used convolutional neural network (CNN) in EEG decoding. However, some studies reveal that a slight disturbance to the inputs, e.g., data translation, can change CNN's outputs. Such instability is dangerous for EEG-based BCI applications because signals in practice are different from training data. In this study, we propose a multi-scale activity transition network (MSATNet) to alleviate the influence of the translation problem in convolution-based models. MSATNet provides an activity state pyramid consisting of multi-scale recurrent neural networks to capture the relationship between brain activities, which is a translation-invariant feature. In the experiment, Kullback-Leibler divergence is applied to measure the degree of translation. The comprehensive results demonstrate that our method surpasses the AUC of 0.0080, 0.0254, 0.0393 in 1, 5, and 10 KL divergence compared to competitors with various convolution structures.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - ETC > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/82476)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.