HMM-based estimation of menstrual cycle from skin temperature during sleep

An HMM-based method is proposed to estimate biphasic property in female menstrual cycle. A tiny device is developed to measure skin temperature change during sleep. Data are collected from 30 female participants for 6 months. Raw data are preprocessed to remove obvious outliers and clamped between 34 and 42 degree Celsius. A two hidden states HMM-based algorithm was applied to estimate the biphasic property in menstrual cycle. The results showed that the number of correctly detected menstrual cycle is 159 among 173 in 30 participants during 6 months. Overall sensitivity reaches 92.0%.