当前位置: X-MOL 学术arXiv.cs.OH › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
FBCNet: A Multi-view Convolutional Neural Network for Brain-Computer Interface
arXiv - CS - Other Computer Science Pub Date : 2021-03-17 , DOI: arxiv-2104.01233
Ravikiran Mane, Effie Chew, Karen Chua, Kai Keng Ang, Neethu Robinson, A. P. Vinod, Seong-Whan Lee, Cuntai Guan

Lack of adequate training samples and noisy high-dimensional features are key challenges faced by Motor Imagery (MI) decoding algorithms for electroencephalogram (EEG) based Brain-Computer Interface (BCI). To address these challenges, inspired from neuro-physiological signatures of MI, this paper proposes a novel Filter-Bank Convolutional Network (FBCNet) for MI classification. FBCNet employs a multi-view data representation followed by spatial filtering to extract spectro-spatially discriminative features. This multistage approach enables efficient training of the network even when limited training data is available. More significantly, in FBCNet, we propose a novel Variance layer that effectively aggregates the EEG time-domain information. With this design, we compare FBCNet with state-of-the-art (SOTA) BCI algorithm on four MI datasets: The BCI competition IV dataset 2a (BCIC-IV-2a), the OpenBMI dataset, and two large datasets from chronic stroke patients. The results show that, by achieving 76.20% 4-class classification accuracy, FBCNet sets a new SOTA for BCIC-IV-2a dataset. On the other three datasets, FBCNet yields up to 8% higher binary classification accuracies. Additionally, using explainable AI techniques we present one of the first reports about the differences in discriminative EEG features between healthy subjects and stroke patients. Also, the FBCNet source code is available at https://github.com/ravikiran-mane/FBCNet.

中文翻译:

FBCNet:用于脑机接口的多视图卷积神经网络

缺乏足够的训练样本和嘈杂的高维特征是基于脑电图(EEG)的脑机接口(BCI)的运动图像(MI)解码算法所面临的主要挑战。为了解决这些挑战,受MI的神经生理学特征的启发,本文提出了一种用于MI分类的新型Filter-Bank卷积网络(FBCNet)。FBCNet使用多视图数据表示,然后进行空间滤波以提取光谱空间上的区别性特征。即使在有限的训练数据可用的情况下,这种多阶段方法也可以对网络进行有效的训练。更重要的是,在FBCNet中,我们提出了一个新颖的方差层,可以有效地聚合EEG时域信息。通过此设计,我们将FBCNet与最新的(SOTA)BCI算法在四个MI数据集上进行了比较:BCI竞争IV数据集2a(BCIC-IV-2a),OpenBMI数据集和两个来自慢性中风患者的大型数据集。结果表明,通过达到76.20%的4类分类准确性,FBCNet为BCIC-IV-2a数据集设置了新的SOTA。在其他三个数据集上,FBCNet的二进制分类精度提高了8%。此外,使用可解释的AI技术,我们提供了有关健康受试者与中风患者之间区别性EEG特征差异的第一份报告之一。另外,可以从https://github.com/ravikiran-mane/FBCNet获得FBCNet源代码。在其他三个数据集上,FBCNet的二进制分类精度提高了8%。此外,使用可解释的AI技术,我们提供了有关健康受试者与中风患者之间区别性EEG特征差异的第一份报告之一。另外,可以从https://github.com/ravikiran-mane/FBCNet获得FBCNet源代码。在其他三个数据集上,FBCNet的二进制分类精度提高了8%。此外,使用可解释的AI技术,我们提供了有关健康受试者与中风患者之间区别性EEG特征差异的第一份报告之一。另外,可以从https://github.com/ravikiran-mane/FBCNet获得FBCNet源代码。
更新日期:2021-04-06
down
wechat
bug