CPC A61B 5/4812 (2013.01) [A61B 5/02405 (2013.01); A61B 5/4848 (2013.01); A61B 5/7221 (2013.01); A61B 5/7267 (2013.01); G16H 20/10 (2018.01); G16H 40/67 (2018.01); G16H 50/20 (2018.01); G16H 50/30 (2018.01)] | 17 Claims |
1. A method of sleep stage detection, the method comprising:
receiving a first vital sign feature derived from a photoplethysmography (PPG) signal, the first vital sign feature including a plurality of first feature values corresponding to respective ones of a plurality of epochs;
performing a first logistic regression operation to calculate a first indication value for each intermediate one of the epochs based on the corresponding first feature value and those of preceding and succeeding ones of the epochs that precede and succeed, respectively, the corresponding intermediate epoch, the first indication value being descriptive of a sleep stage of the corresponding intermediate epoch; and
detecting the sleep stage of the corresponding intermediate epoch based on the first indication value for the corresponding intermediate epoch,
wherein the first logistic regression operation is performed using a machine learning classifier model.
|