SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
SeqSleepNet: End-to-End Hierarchical Recurrent Neural Network for Sequence-to-Sequence Automatic Sleep Staging
复制标题
DOI：
10.1109/tnsre.2019.2896659
复制
发表时间：
2019-03-01
影响因子：
4.9
通讯作者：
De Vos, Maarten
中科院分区：
文献类型：
--
作者：
Huy Phan;Andreotti, Fernando;De Vos, Maarten
自动睡眠分期通常被认为是一个简单的分类问题，其目的是一次一个地确定单个目标多导睡眠图时期的标签。在本文中，我们将这一任务作为一个序列到序列的分类问题来处理，该问题接收一个多个历元的序列作为输入，并同时对它们的所有标签进行分类。为此，我们提出了一种分层递归神经网络SeqSleepNet(源代码可在http://github.com/pquochuy/SeqSleepNet).At的纪元处理层获得)，该网络由用于学习用于预处理的频域滤波器的滤波器层和用于短期序贯建模的基于注意力的递归层组成。在序列处理级别，在学习的时序特征之上放置一个递归层，用于对时序时序进行长期建模。然后在顶部递归层的每个时间步长对输出向量进行分类，以产生输出标签序列。尽管是分层的，但我们提出了以端到端的方式培训网络的策略。我们表明，所提出的网络的性能优于最先进的方法，在一个有200个主题的公开可用的数据集上，实现了总体准确率、宏观F1得分和科恩的kappa分别为87.1%、83.3%和0.815。
Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography epochs one at a time. In this paper, we tackle the task as a sequence-to-sequence classification problem that receives a sequence of multiple epochs as input and classifies all of their labels at once. For this purpose, we propose a hierarchical recurrent neural network named SeqSleepNet (source code is available at http://github.com/pquochuy/SeqSleepNet).At the epoch processing level, the network consists of a filterbank layer tailored to learn frequency-domain filters for preprocessing and an attention-based recurrent layer designed for shortterm sequential modeling. At the sequence processing level, a recurrent layer placed on top of the learned epoch-wise features for long-term modeling of sequential epochs. The classification is then carried out on the output vectors at every time step of the top recurrent layer to produce the sequence of output labels. Despite being hierarchical, we present a strategy to train the network in an end-to-end fashion. We show that the proposed network outperforms the state-of-the-art approaches, achieving an overall accuracy, macro F1-score, and Cohen's kappa of 87.1%, 83.3%, and 0.815 on a publicly available dataset with 200 subjects.