Authors: Wenxi Chen Masumi Kitazawa Tatsuo Togawa
Publish Date: 2009/06/24
Volume: 37, Issue: 9, Pages: 1827-1838
Abstract
This paper proposes a method to estimate a woman’s menstrual cycle based on the hidden Markov model HMM A tiny device was developed that attaches around the abdominal region to measure cutaneous temperature at 10min intervals during sleep The measured temperature data were encoded as a twodimensional image QR code ie quick response code and displayed in the LCD window of the device A mobile phone captured the QR code image decoded the information and transmitted the data to a database server The collected data were analyzed by three steps to estimate the biphasic temperature property in a menstrual cycle The key step was an HMMbased step between preprocessing and postprocessing A discrete Markov model with two hidden phases was assumed to represent higher and lowertemperature phases during a menstrual cycle The proposed method was verified by the data collected from 30 female participants aged from 14 to 46 over six consecutive months By comparing the estimated results with individual records from the participants 716 of 190 menstrual cycles were correctly estimated The sensitivity and positive predictability were 918 and 966 respectively This objective evaluation provides a promising approach for managing premenstrual syndrome and birth controlThis study was supported in part by the Innovation Technology Development Research Program under JST Japan Science and Technology Agency grant H170318 GrantsInAid for Scientific Research under No 20500601 and the competitive research funding from the University of Aizu The authors would like to thank all the anonymous participants for their enduring efforts in longterm data collection
Keywords: