arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11349cs.LGstat.ML
收藏

基于单夜数据的个性化自动睡眠分期:KL发散正则化的初步研究

Personalized Automatic Sleep Staging with Single-Night Data: a Pilot Study with KL-Divergence Regularization

Queen Mary University of London(伦敦玛丽女王大学);Aarhus University(奥胡斯大学);University of Oxford(牛津大学);University of Lübeck(吕贝克大学);KU Leuven(鲁汶大学)

Huy Phan, Kaare Mikkelsen, Oliver Y. Chén, Philipp Koch, Alfred Mertins, Preben Kidmose, Maarten De Vos

摘要:

脑电波因人而异。改善纵向睡眠监测的自动睡眠分期的一个明显方法是基于从第一晚数据中提取的个体特征的算法的个性化。由于一个晚上是一个非常小的数据量训练的睡眠分期模型,我们提出了一个Kullback-Leibler(KL)散度正则化迁移学习方法来解决这个问题。我们采用预训练的SeqSleepNet(即受试者独立模型)作为起点,并使用单晚个性化数据对其进行微调,以推导出个性化模型。这是通过在微调期间将对象独立模型的输出与个性化模型的输出之间的KL偏差添加到损失函数来完成的。实际上,KL-发散正则化防止个性化模型过度拟合到单夜数据,并且偏离受试者独立模型太远。在Sleep-EDF Expanded数据库中对75名受试者的实验结果表明,在所提出的KL发散正则化的帮助下,使用单夜数据的睡眠分期个性化是可能的。平均而言,我们实现了79.6%的个性化睡眠分期准确性,科恩的kappa值为0.706,宏观F1评分为73.0%,灵敏度为71.8%,特异性为94.2%。我们发现,该方法对过拟合具有鲁棒性,与非个性化相比,它将准确率提高了4.5个百分点,与没有正则化的个性化相比,提高了2.2个百分点。

英文摘要:

Brain waves vary between people. An obvious way to improve automatic sleep staging for longitudinal sleep monitoring is personalization of algorithms based on individual characteristics extracted from the first night of data. As a single night is a very small amount of data to train a sleep staging model, we propose a Kullback-Leibler (KL) divergence regularized transfer learning approach to address this problem. We employ the pretrained SeqSleepNet (i.e. the subject independent model) as a starting point and finetune it with the single-night personalization data to derive the personalized model. This is done by adding the KL divergence between the output of the subject independent model and the output of the personalized model to the loss function during finetuning. In effect, KL-divergence regularization prevents the personalized model from overfitting to the single-night data and straying too far away from the subject independent model. Experimental results on the Sleep-EDF Expanded database with 75 subjects show that sleep staging personalization with a single-night data is possible with help of the proposed KL-divergence regularization. On average, we achieve a personalized sleep staging accuracy of 79.6%, a Cohen's kappa of 0.706, a macro F1-score of 73.0%, a sensitivity of 71.8%, and a specificity of 94.2%. We find both that the approach is robust against overfitting and that it improves the accuracy by 4.5 percentage points compared to non-personalization and 2.2 percentage points compared to personalization without regularization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑