Deep learning based on Batch Normalization for P300 signal detection
Deep learning based on Batch Normalization for P300 signal detection
复制标题
基于 Batch Normalization 的深度学习用于 P300 信号检测
DOI：
10.1016/j.neucom.2017.08.039
复制
发表时间：
2018-01-31
期刊：
影响因子：
6
通讯作者：
Li, Yuanqing
中科院分区：
文献类型：
--
作者：
Liu, Mingfei;Wu, Wei;Li, Yuanqing
P300拼写器是一种基于oddball范式的脑-机接口（brain-computer interface，BCI）系统，它允许用户通过简单地控制眼睛注视来输入信息，从EEG中检测P300信号是建立P300拼写器的关键。卷积神经网络（CNN）是一种实现良好P300检测性能的方法。然而，标准CNN可能易于过度拟合并且收敛可能缓慢。为了解决这些问题，我们开发了一种新的CNN，称为BN 3，用于检测P300信号，其中在输入层和卷积层中引入了批量归一化以减轻过度拟合，并在卷积层中采用了整流线性单元（ReLU）以加速训练。由于我们的模型是完全数据驱动的，它能够自动捕获的P300信号的歧视性时空特征。在先前的BCI竞赛P300数据集上获得的结果表明，BN 3既达到了最先进的字符识别性能，又优于现有的具有小闪烁时期数的检测方法。BN 3可用于提高P300拼写系统中的字符识别性能。(c)2017爱思唯尔B. V.保留所有权利。
Detecting P300 signals from electroencephalography (EEG) is the key to establishing a P300 speller, which is a type of brain-computer interface (BCI) system based on the oddball paradigm that allows users to type messages simply by controlling eye-gazes. The convolutional neural network (CNN) is an approach that has achieved good P300 detection performances. However, the standard CNN may be prone to over-fitting and the convergence may be slow. To address these issues, we develop a novel CNN, termed BN3, for detecting P300 signals, where Batch Normalization is introduced in the input and convolutional layers to alleviate over-fitting, and the rectified linear unit (ReLU) is employed in the convolutional layers to accelerate training. Since our model is fully data-driven, it is capable of automatically capturing the discriminative spatio-temporal features of the P300 signal. The results obtained on previous BCI competition P300 data sets show that BN3 both achieves the state-of-the-art character recognition performance and that it outperforms existing detection approaches with small flashing epoch numbers. BN3 can be used to improve the character recognition performance in P300 speller systems. (c) 2017 Elsevier B.V. All rights reserved.