Deep Feature Learning and Visualization for EEG Recording Using Autoencoders
Deep Feature Learning and Visualization for EEG Recording Using Autoencoders
复制标题
使用自动编码器进行脑电图记录的深度特征学习和可视化
DOI：
10.1007/978-3-030-04239-4_50
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Tom Gedeon
中科院分区：
文献类型：
--
作者：
Yue Yao;J. Plested;Tom Gedeon
在这个深度学习和大数据时代，将生物医学大数据转化为可识别的模式是生物信息学的重要研究热点和巨大挑战。生物医学数据的一种重要形式是脑电图（EEG）信号，其通常受到噪声的强烈影响，并且存在显著的个体、环境和设备差异。在本文中，我们专注于学习鉴别特征的短时脑电信号。传统的图像压缩技术的启发，学习一个强大的图像表示，我们介绍和比较两种策略，从EEG学习功能，使用两个专门设计的自动编码器。逐帧自动编码器专注于每个通道中的特征，而逐帧图像自动编码器则从整个试验中学习特征。我们在UCI EEG数据集上的结果表明，使用智能和图像智能自动编码器在受试者内和跨受试者测试中均具有最先进的准确性，从而实现了分类问题的良好性能。使用共享权重的进一步实验表明，共享权重技术对学习的影响很小，但它显著减少了训练时间。
In this era of deep learning and big data, the transformation of biomedical big data into recognizable patterns is an important research focus and a great challenge in bioinformatics. An important form of biomedical data is electroencephalography (EEG) signals, which are generally strongly affected by noise and there exists notable individual, environmental and device differences. In this paper, we focus on learning discriminative features from short time EEG signals. Inspired by traditional image compression techniques to learn a robust representation of an image, we introduce and compare two strategies for learning features from EEG using two specifically designed autoencoders. Channel-wise autoencoders focus on features in each channel, while Image-wise autoencoders instead learn features from the whole trial. Our results on a UCI EEG dataset show that using both Channel-wise and Image-wise autoencoders achieve good performance for a classification problem with state of art accuracy in both within-subject and cross-subject tests. A further experiment using shared weights shows that the shared weights technique only slightly influenced learning but it reduced training time significantly.