EEG-based intention recognition with deep recurrent-convolution neural network: Performance and channel selection by Grad-CAM
EEG-based intention recognition with deep recurrent-convolution neural network: Performance and channel selection by Grad-CAM
复制标题
基于 EEG 的深度循环卷积神经网络意图识别：Grad-CAM 的性能和通道选择
DOI：
10.1016/j.neucom.2020.07.072
复制
发表时间：
2020-11-20
期刊：
影响因子：
6
通讯作者：
Du, Min
中科院分区：
文献类型：
--
作者：
Li, Yurong;Yang, Hao;Du, Min
基于脑电(EEG)的脑机接口(BCI)使受试者能够在不经过肌肉和神经的情况下，利用大脑信号与外界或控制设备进行交流。近年来，许多研究人员对非侵入性脑-机接口系统进行了研究。然而，由于脑电信号具有随机性、非平稳性和低信噪比等特点，影响了意图解码算法的效率。此外，通道选择是BCI系统意图识别中的另一个重要问题。在BCI系统的意图识别过程中，冗余电极产生的不必要信息会影响译码速度，消耗系统资源。本文提出了一种递归-卷积神经网络模型，通过学习分解的时空表征进行意图识别。我们将新的梯度类激活映射(Grad-CAM)可视化技术应用到通道选择中。Grad-CAM使用任何分类的梯度，流入最后一卷积层以产生粗略的定位图。由于定位图的像素对应于电极放置的空间区域，因此我们选择对决策更重要的通道。我们使用公共运动图像脑电数据集EEGMMIDB进行了实验。实验结果表明，我们的方法在全信道上的准确率达到了97.36%，优于许多最新的模型和基线模型。虽然我们的模型与最好的模型相比译码率相同，但是我们的模型参数更少，训练时间更快。在信道选择后，我们的模型保持了92.31%的意图译码性能，同时将信道数量减少了近一半，节省了系统资源。该方法实现了EEG意图解码的性能和电极通道数之间的最优折衷。(C)2020爱思唯尔B.V.保留所有权利。
Electroencephalography (EEG) based Brain-Computer Interface (BCI) enables subjects to communicate with the outside world or control equipment using brain signals without passing through muscles and nerves. Many researchers in recent years have studied the non-invasive BCI systems. However, the efficiency of the intention decoding algorithm is affected by the random non-stationary and low signal-to-noise ratio characteristics of the EEG signal. Furthermore, channel selection is another important issue in BCI systems intention recognition. During intention recognition in BCI systems, the unnecessary information produced by redundant electrodes affects the decoding rate and deplete system resources. In this paper, we introduce a recurrent-convolution neural network model for intention recognition by learning decomposed spatio-temporal representations. We apply the novel Gradient-Class Activation Mapping (Grad-CAM) visualization technology to the channel selection. Grad-CAM uses the gradient of any classification, flowing into the last convolutional layer to produce a coarse localization map. Since the pixels of the localization map correspond to the spatial regions where the electrodes are placed, we select the channels that are more important for decision-making. We conduct an experiment using the public motor imagery EEG dataset EEGMMIDB. The experimental results demonstrate that our method achieves an accuracy of 97.36% at the full channel, outperforming many state-of-the-art models and baseline models. Although the decoding rate of our model is the same as the best model compared, our model has fewer parameters with faster training time. After the channel selection, our model maintains the intention decoding performance of 92.31% while reducing the number of channels by nearly half and saving system resources. Our method achieves an optimal trade-off between performance and the number of electrode channels for EEG intention decoding. (C) 2020 Elsevier B.V. All rights reserved.