Electrical and Computer Engineering in Medicine Group, the University of British Columbia, Vancouver, BC V6T 1Z4, Canada.
IEEE Trans Biomed Eng. 2011 Apr;58(4):920-6. doi: 10.1109/TBME.2010.2097261. Epub 2010 Dec 17.
Sleep/wake classification systems that rely on physiological signals suffer from intersubject differences that make accurate classification with a single, subject-independent model difficult. To overcome the limitations of intersubject variability, we suggest a novel online adaptation technique that updates the sleep/wake classifier in real time. The objective of the present study was to evaluate the performance of a newly developed adaptive classification algorithm that was embedded on a wearable sleep/wake classification system called SleePic. The algorithm processed ECG and respiratory effort signals for the classification task and applied behavioral measurements (obtained from accelerometer and press-button data) for the automatic adaptation task. When trained as a subject-independent classifier algorithm, the SleePic device was only able to correctly classify 74.94 ± 6.76% of the human-rated sleep/wake data. By using the suggested automatic adaptation method, the mean classification accuracy could be significantly improved to 92.98 ± 3.19%. A subject-independent classifier based on activity data only showed a comparable accuracy of 90.44 ± 3.57%. We demonstrated that subject-independent models used for online sleep-wake classification can successfully be adapted to previously unseen subjects without the intervention of human experts or off-line calibration.
依赖生理信号的睡眠/觉醒分类系统存在个体间差异，这使得使用单一的、与个体无关的模型进行准确分类变得困难。为了克服个体间变异性的限制，我们提出了一种新的在线自适应技术，该技术可以实时更新睡眠/觉醒分类器。本研究的目的是评估一种新开发的自适应分类算法的性能，该算法被嵌入到一个名为 SleePic 的可穿戴睡眠/觉醒分类系统中。该算法处理 ECG 和呼吸努力信号进行分类任务，并应用行为测量（从加速度计和按钮数据中获得）进行自动适应任务。当作为一个独立于个体的分类器算法进行训练时，SleePic 设备只能正确分类 74.94±6.76%的人类评定的睡眠/觉醒数据。通过使用建议的自动适应方法，平均分类准确性可以显著提高到 92.98±3.19%。基于活动数据的独立于个体的分类器显示出相当的准确性，为 90.44±3.57%。我们证明了用于在线睡眠/觉醒分类的独立于个体的模型可以成功地适应以前未见过的个体，而无需人类专家的干预或离线校准。
