Olesen Alexander Neergaard, Jennum Poul, Mignot Emmanuel, Sorensen Helge B D
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:99-103. doi: 10.1109/EMBC44109.2020.9176723.
Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.
由于各诊所记录设置存在差异，睡眠科学中的数据集给机器学习算法带来了挑战。对于两个数据集的设置不完全相同从而导致单通道脑电图模型性能下降的情况，我们研究了两种深度迁移学习策略来克服通道不匹配问题。具体而言，我们在多变量多导睡眠图数据上训练一个基线模型，随后替换前两层，为单通道脑电图数据准备架构。使用微调策略，我们的模型产生了与基线模型相似的性能（F1分别为0.682和0.694），并且明显优于可比的单通道模型。我们的结果对于使用小型数据库且希望使用在大型数据库上预训练的深度学习模型的研究人员来说很有前景。
