Khalighi Sirvan, Sousa Teresa, Nunes Urbano
Institute for Systems and Robotics, University of Coimbra, Coimbra, Portugal.
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:2259-62. doi: 10.1109/EMBC.2012.6346412.
Current automatic sleep stage classification (ASSC) methods that rely on polysomnographic (PSG) signals suffer from inter-subject differences that make them unreliable in facing with new and different subjects. A novel adaptive sleep scoring method based on unsupervised domain adaptation, aiming to be robust to inter-subject variability, is proposed. We assume that the sleep quality variants follow a covariate shift model, where only the sleep features distribution change in the training and test phases. The maximum overlap discrete wavelet transform (MODWT) is applied to extract relevant features from EEG, EOG and EMG signals. A set of significant features are selected by minimum-redundancy maximum-relevance (mRMR) which is a powerful feature selection method. Finally, an instance-weighting method, namely the importance weighted kernel logistic regression (IWKLR) is applied for the purpose of obtaining adaptation in classification. The classification results using leave one out cross-validation (LOOCV), show that the proposed method performs at the state-of-the art in the field of ASSC.
当前依赖多导睡眠图（PSG）信号的自动睡眠阶段分类（ASSC）方法存在个体差异问题，这使得它们在面对新的和不同的个体时不可靠。提出了一种基于无监督域适应的新型自适应睡眠评分方法，旨在对个体间的变异性具有鲁棒性。我们假设睡眠质量变量遵循协变量转移模型，其中仅睡眠特征分布在训练和测试阶段发生变化。应用最大重叠离散小波变换（MODWT）从脑电图（EEG）、眼电图（EOG）和肌电图（EMG）信号中提取相关特征。通过最小冗余最大相关性（mRMR）选择一组显著特征，mRMR是一种强大的特征选择方法。最后，为了在分类中获得适应性，应用了一种实例加权方法，即重要性加权核逻辑回归（IWKLR）。使用留一法交叉验证（LOOCV）的分类结果表明，所提出的方法在ASSC领域达到了当前的先进水平。
