Measuring psychological stress from cardiovascular and activity signals
A method and system for measuring psychological stress disclosed. In a first aspect, the method comprises determining R-R intervals from an electrocardiogram (ECG) to calculate a standard deviation of the R-R intervals (SDNN) and determining a stress feature (SF) using the SDNN. In response to reaching a threshold, the method includes performing adaptation to update a probability mass function (PMF). The method includes determining a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress. In a second aspect, the system comprises a wireless sensor device coupled to a user via at least one electrode, wherein the wireless sensor device includes a processor and a memory device coupled to the processor, wherein the memory device stores an application which, when executed by the processor, causes the processor to carry out the steps of the method.
1. A method for measuring psychological stress, the method comprising:
determining R-R intervals from an electrocardiogram (ECG) to calculate a standard deviation of the R-R intervals (SDNN);
determining a stress feature (SF) using the SDNN, wherein the determining SF using the SDNN comprises:
calculating a mean heart rate (HR) from the ECG within a predetermined time period; and
calculating the SF utilizing an algorithm SF=HR+α*SDNN, wherein α is predetermined negative variable that allows for combining HR and SDNN;
in response to reaching a threshold, updating performing adaptation to update a probability mass function (PMF) via an adaptation function; and
determining a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress.
2. The method of claim 1 , further comprising:
determining a posture state, wherein the psychological stress is not measured if the posture state is active; and
displaying the determined SL to a user or another device.
3. The method of claim 2 , wherein the posture state includes any of active, sitting, and standing.
4. The method of claim 1 , wherein determining R-R intervals from the ECG to calculate the SDNN further comprises:
detecting R peaks from a measured ECG within the predetermined time period; and
calculating R-R intervals using the detected R peaks.
5. The method of claim 4 , wherein performing adaptation to update the PMF further comprises:
grouping data into a predetermined distribution;
calibrating the predetermined distribution according to a detected resting heart rate; and
adjusting the predetermined distribution according to additional samples received.
6. The method of claim 5 , wherein adjusting the predetermined distribution according to additional samples received further comprises:
in response to data arriving, multiplying all bins of the predetermined distribution by 1-ε, wherein ε is a parameter for how much the PMF is changed with each adaptation; and
adding ε to a bin corresponding to the data.
7. The method of claim 5 , wherein determining the stress level (SL) using the SF and the PMF further comprises:
adding all bins below a bin corresponding to the SF; and
computing the SL utilizing an algorithm that includes a probability mass function for a given posture (PMF posture ), the SF, and the added bins.
8. The method of claim 7 , further comprising:
adding a fraction of a current bin to improve granularity.
9. The method of claim 1 , further comprising:
tracking both a mean and a standard deviation of a probability distribution as the probability distribution adapts over time; and
combining the mean and the standard deviation to measure long-term stress.
10. The method of claim 1 , wherein the application further causes the processor to:
track both a mean and a standard deviation of a probability distribution as the probability distribution adapts over time; and
combine the mean and the standard deviation to measure long-term stress.