arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05111cs.CVeess.SPstat.APstat.ML
收藏

深度迁移学习用于改进单脑电唤醒检测

Deep transfer learning for improving single-EEG arousal detection

Technical University of Denmark(丹麦技术大学);Stanford University(斯坦福大学);University Hospital Copenhagen(哥本哈根大学医院)

Alexander Neergaard Olesen, Poul Jennum, Emmanuel Mignot, Helge B. D. Sorensen

摘要:

睡眠科学中的数据集对机器学习算法提出了挑战,因为不同诊所的记录设置存在差异。我们研究了两种深度迁移学习策略,用于克服两个数据集不包含完全相同的设置导致单EEG模型性能下降的情况下的通道失配问题。具体来说,我们训练多变量多导睡眠图数据的基线模型,并随后取代前两层,以准备单通道脑电图数据的架构。使用微调策略,我们的模型产生类似的性能基线模型(F1=0.682和F1=0.694,分别),并显着优于可比的单通道模型。我们的研究结果对于那些希望使用在大型数据库上预先训练的深度学习模型的小型数据库研究人员来说是有希望的。

英文摘要:

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.

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。

↑