Method and system for heart rate estimation of a user

A system for heart rate estimation, comprising:

• one or more hardware processors;
• one or more communication interfaces;
• and
• one or more memory storing a plurality of instructions, wherein the plurality of instructions when executed cause the one or more hardware processors to:
• collect a Photoplethysmogram (PPG) signal over a plurality of fixed time windows from a user being monitored;
• determine whether the user was in motion in any of the plurality of time windows while the PPG signal was being collected, by performing a mobility detection;
• classify each of the plurality of time windows as belonging to one of a set of time windows in which user is determined as in motion and a set of time windows in which user is determined as not in motion;
• and
• perform the heart rate estimation for the PPG signal collected over each time window belonging to the set of time windows in which user is determined as in motion, by:
• estimating a noise signal by performing a Principle Component Analysis (PCA) of an accelerometer signal collected over each of the time windows in which the user is determined as being in motion;
• estimating value of a true cardiac signal for each of the time windows in which the user is determined as being in motion, comprising:
• obtaining a pre-defined number of spectra prior to a time window being considered, from a Clean Signal Buffer (CBF);
• and
• estimating the value of the true cardiac signal by taking a trimmed mean of the obtained pre-defined number of spectra;
• estimating spectrum of a clean PPG signal based on the estimated noise signal and the estimated value of the true cardiac signal, using a wiener filter;
• and
• estimating heart rate of the user based on the estimated spectrum of the clean PPG signal.

A non-transitory computer readable medium for heart rate estimation, wherein the non-transitory computer readable medium when executed by one or more hardware processors, cause the heart rate estimation by:

• collecting a Photoplethysmogram (PPG) signal over a plurality of fixed time windows from a user being monitored, via one or more hardware processors;
• determining whether the user was in motion in any of the plurality of time windows while the PPG signal was being collected, by performing a mobility detection, via the one or more hardware processors;
• classifying each of the plurality of time windows as belonging to one of a set of time windows in which user is determined as in motion and a set of time windows in which user is determined as not in motion;
• and
• performing the heart rate estimation for the PPG signal collected over each time window belonging to the set of time windows in which user is determined as in motion, via the one or more hardware processors, comprising:
• estimating a noise signal by performing a Principle Component Analysis (PCA) of an accelerometer signal collected over each of the time windows in which the user is determined as being in motion;
• estimating value of a true cardiac signal for each of the time windows in which the user is determined as being in motion, comprising:
• obtaining a pre-defined number of spectra prior to a time window being considered, from a Clean Signal Buffer (CBF);
• and
• estimating the value of the true cardiac signal by taking a trimmed mean of the obtained pre-defined number of spectra;
• estimating spectrum of a clean PPG signal based on the estimated noise signal and the estimated value of the true cardiac signal, using a wiener filter;
• and
• estimating heart rate of the user based on the estimated spectrum of the clean PPG signal.