Measuring psychological stress from cardiovascular and activity signals

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), wherein the determining the R-R intervals from the ECG to calculate the SDNN further comprises:

detecting R peaks from a measured ECG within a predetermined time period, and

calculating the R-R intervals using the detected R peaks;

determining a stress feature (SF) using the SDNN, wherein the determining the stress feature (SF) using the SDNN further comprises:

calculating a mean heart rate (HR) from the ECG within the predetermined time period, and

calculating the SF utilizing an algorithm SF=HR+α*SDNN, wherein the α includes a predetermined negative variable that allows for combining the HR and the SDNN;

in response to reaching a threshold, performing adaptation to update a probability mass function (PMF); 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 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.

5. The method of claim 4 , 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; and

adding ε to a bin corresponding to the data, wherein the ε includes a forgetting parameter for how much the PMF changes with each adaptation run.

6. The method of claim 4 , 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.

7. The method of claim 6 , further comprising:

adding a fraction of a current bin to improve granularity.

8. 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.

9. 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.

10. A system for measuring psychological stress, the system comprising:

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:

determine R-R intervals from an electrocardiogram (ECG) to calculate a standard deviation of the R-R intervals (SDNN), wherein the to determine the R-R intervals from the ECG to calculate the SDNN further comprises:

detect R peaks from a measured ECG within a predetermined time period, and

calculate the R-R intervals using the detected R peaks;

determine a stress feature (SF) using the SDNN, wherein the to determine the stress feature (SF) using the SDNN further comprises:

calculate a mean heart rate (HR) from the ECG within the predetermined time period, and

calculate the SF utilizing an algorithm SF=HR+α*SDNN, wherein the α includes a predetermined negative variable that allows for combining the HR and the SDNN;

in response to reaching a threshold, perform adaptation to update a probability mass function (PMF); and

determine a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress.

11. The system of claim 10 , wherein the application further causes the processor to:

determine a posture state, wherein the psychological stress is not measured if the posture state is active; and

display the determined SL to a user or another device.

12. The system of claim 11 , wherein the posture state includes any of active, sitting, and standing.

13. The system of claim 10 , wherein to perform adaptation to update the PMF further comprises to:

group data into a predetermined distribution;

calibrate the predetermined distribution according to a detected resting heart rate; and

adjust the predetermined distribution according to additional samples received.

14. The system of claim 13 , wherein to adjust the predetermined distribution according to additional samples received further comprises to:

in response to data arriving, multiply all bins of the predetermined distribution by 1−ε; and

add ε to a bin corresponding to the data, wherein the ε includes a forgetting parameter for how much the PMF changes with each adaptation run.

15. The system of claim 13 , wherein to determine the stress level (SL) using the SF and the PMF further comprises to:

add all bins below a bin corresponding to the SF; and

compute the SL utilizing an algorithm that includes a probability mass function for a given posture (PMF posture ), the SF, and the added bins.

16. The system of claim 15 , wherein the application further causes the processor to:

add a fraction of a current bin to improve granularity.