Enhanced Onset Detection of EEG for Self-paced Brain-Computer Interface using Deep Oversampling
Enhanced Onset Detection of EEG for Self-paced Brain-Computer Interface using Deep Oversampling
复制标题
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
N. A. Moubayed;A. Mcgough
中科院分区：
文献类型：
--
作者：
N. A. Moubayed;A. Mcgough
研究了一种深度学习方法，用于对自定节奏手部运动过程中记录的脑电图（EEG）进行过采样，以改进脑电图分类，特别是发病检测。运动类的过采样显着提高了对12名参与者进行测试的发病检测系统的整体准确性。使用深度神经网络对数据建模不仅有助于对运动类进行过采样，而且可以帮助建立一个独立于主题的运动独立模型。在这项工作中，我们提出了该模型适用性的初步结果。
A deep learning approach for oversampling of electroencephalography (EEG) recorded during self-paced hand movement is investigated for the purpose of improving EEG classification in general and onset detection in particular. Oversampling of the movement class significantly enhances the overall accuracy of an onset detection system tested on 12 participants. Modelling the data using a deep neural network not only helps oversampling the movement class but also can help build a subject independent model of movement independent of the subject. In this work we present initial results on the applicability of this model.