arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01233cs.OHcs.AIcs.LGeess.SP
收藏

FBCNet：一种用于脑机接口的多视图卷积神经网络

FBCNet: A Multi-view Convolutional Neural Network for Brain-Computer Interface

Nanyang Technological University（南洋理工大学）；National University Hospital（国立大学医院）；Tan Tock Seng Hospital（陈笃生医院）；Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)（新加坡资讯通信研究院（新加坡科技研究局））；Indian Institute of Technology, Palakkad（印度理工学院巴拉卡德分校）；Korea University（高丽大学）

Ravikiran Mane, Effie Chew, Karen Chua, Kai Keng Ang, Neethu Robinson, A. P. Vinod, Seong-Whan Lee, Cuntai Guan

备注：
This work has been submitted to the IEEE for possible publication
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出多视图滤波器组卷积网络FBCNet，通过空间滤波与Variance层聚合EEG时频空特征，在有限训练数据下提升MI解码性能并取得SOTA。

摘要：

缺乏足够的训练样本以及含噪的高维特征，是基于脑电图（EEG）的脑机接口（BCI）中运动想象（MI）解码算法面临的关键挑战。为应对这些挑战，受运动想象的神经生理特征启发，本文提出了一种用于MI分类的新型滤波器组卷积网络（Filter-Bank Convolutional Network，FBCNet）。FBCNet采用多视图数据表示，随后进行空间滤波，以提取具有频谱-空间判别性的特征。这种多阶段方法即使在训练数据有限的情况下也能实现网络的高效训练。更重要的是，在FBCNet中，我们提出了一个新型Variance层，可有效聚合EEG时域信息。基于该设计，我们在四个MI数据集上将FBCNet与最先进（SOTA）BCI算法进行比较：BCI竞赛IV数据集2a（BCIC-IV-2a）、OpenBMI数据集，以及来自慢性卒中患者的两个大型数据集。结果表明，FBCNet通过达到76.20%的四分类准确率，在BCIC-IV-2a数据集上创下新的SOTA。在另外三个数据集上，FBCNet的二分类准确率最高高出8%。此外，利用可解释AI技术，我们率先报告了健康受试者与卒中患者在判别性EEG特征方面的差异之一。FBCNet源代码可在https://github.com/ravikiran-mane/FBCNet获取。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑