Phan Huy, Andreotti Fernando, Cooray Navin, Oliver Chen Y, De Vos Maarten
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:453-456. doi: 10.1109/EMBC.2018.8512286.
We present in this paper an efficient convolutional neural network (CNN) running on time-frequency image features for automatic sleep stage classification. Opposing to deep architectures which have been used for the task, the proposed CNN is much simpler However, the CNN's convolutional layer is able to support convolutional kernels with different sizes, and therefore, capable of learning features at multiple temporal resolutions. In addition, the 1-max pooling strategy is employed at the pooling layer to better capture the shift-invariance property of EEG signals. We further propose a method to discriminatively learn a frequency-domain filter bank with a deep neural network (DNN) to preprocess the time-frequency image features. Our experiments show that the proposed 1-max pooling CNN performs comparably with the very deep CNNs in the literature on the Sleep- EDF dataset. Preprocessing the time-frequency image features with the learned filter bank before presenting them to the CNN leads to significant improvements on the classification accuracy, setting the state- of-the-art performance on the dataset.
在本文中，我们展示了一种高效的卷积神经网络（CNN），它基于时频图像特征运行，用于自动睡眠阶段分类。与已用于该任务的深度架构不同，所提出的CNN要简单得多。然而，CNN的卷积层能够支持不同大小的卷积核，因此能够在多个时间分辨率下学习特征。此外，池化层采用1-最大池化策略，以更好地捕捉脑电信号的平移不变性。我们还提出了一种方法，通过深度神经网络（DNN）有区别地学习频域滤波器组，以预处理时频图像特征。我们的实验表明，所提出的1-最大池化CNN在Sleep-EDF数据集上的表现与文献中非常深的CNN相当。在将时频图像特征呈现给CNN之前，用学习到的滤波器组对其进行预处理，可显著提高分类准确率，在该数据集上达到了当前的最佳性能。
