Measuring psychological stress from cardiovascular and activity signals

1. A method to measure psychological stress by a cloud server, comprising:

receiving, by a cloud server, electrocardiogram (ECG) data from a wireless sensor;

receiving, by the cloud server, R-R intervals based on the ECG data;

receiving, by the cloud server, heart rate data based on the ECG data;

determining, by the cloud server, a standard deviation of the R-R intervals (SDNN) within a predetermined time period;

determining, by the cloud server, a stress feature (SF) using the SDNN by calculating a mean heart rate (HR) from the heart rate data 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, by the cloud server, adaptation to update a probability mass function (PMF); and

determining, by the cloud server, 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:

receiving, by the cloud server, posture data, wherein the psychological stress is not measured if a posture state is active; and

displaying the determined posture state to a user or another device.

3. The method of claim 2 , wherein the posture state includes any of active, sitting, standing, leaning, and lying down.

4. The method of claim 1 , wherein the performing adaptation to update the PMF 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 the adjusting the predetermined distribution according to the additional samples received 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 1 , wherein the 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. A system to measure psychological stress, comprising:

a wireless sensor device coupled to a user via at least one electrode, wherein the wireless sensor device includes a transmitter; and

a cloud server including: a processor, receiver, and memory device,

wherein the receiver receives electrocardiogram (ECG) data from the wireless sensor device and the R-R interval data based on the ECG data and heart rate data based on the ECG data,

wherein the memory device stores an application which, in response to being executed by the processor, causes the processor to:

determine the standard deviation of the R-R intervals (SDNN) within a predetermined time period;

determine a stress feature (SF) using the SDNN by calculating a mean heart rate (HR) from the heart rate data 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, 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.

10. The system of claim 9 , wherein the application further causes the processor to:

determine, by at least one of the wireless sensor device or cloud server, a posture state, wherein the psychological stress is not measured if the posture state is active; and

transmit the determined posture state to a device display.

11. The system of claim 10 , wherein the posture state includes any one of: active, sitting, standing, leaning and lying down.

12. The system of claim 9 , wherein the adaptation performance to update the PMF, includes:

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.

13. The system of claim 12 , wherein the adjustment of the predetermined distribution according to additional samples received, 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.

14. The system of claim 9 , wherein the determination of the stress level (SL) using the SF and the PMF, 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.

15. The system of claim 14 , wherein the application further causes the processor to:

add a fraction of a current bin to improve granularity.

16. A cloud server that determines psychological stress, comprising:

a receiver that receives electrocardiogram (ECG) data and R-R interval data that is calculated from the ECG data and heart rate data that is calculated from the ECG data from a wireless sensor device; and

a memory device that stores an application which, in response to being executed by a processor of a cloud server, causes the processor to:

determine the standard deviation of the R-R intervals (SDNN) within a predetermined time period;

determine a stress feature (SF) using the SDNN by calculating a mean heart rate (HR) from the heart rate data within the predetermined time period and calculating the SF utilizing an algorithm SF=HR+α*SDNN, wherein the a 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.

17. The cloud server of claim 16 , 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

wherein the posture state includes any one of: active, sitting, standing, leaning or lying down; and

transmit the determined SL to a device display.

18. The cloud server of claim 16 , wherein the adaptation performance to update the PMF, includes:

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, wherein the adjusting the predetermined distribution according to additional samples received includes:

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.

19. The cloud server of claim 16 ,

wherein the determination of the stress level (SL) using the SF and the PMF, 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, and

wherein the application further causes the processor to:

add a fraction of a current bin to improve granularity.

20. A method to measure psychological stress by a cloud server, comprising:

receiving, by a cloud server, electrocardiogram (ECG) data from a wireless sensor;

determining, by the cloud server, R-R intervals from the electrocardiogram (ECG) by detecting R peaks from the ECG data within a predetermined time period;

calculating, by the cloud server, a standard deviation of the R-R intervals (SDNN) using the detected R peaks

calculating a mean heart rate (HR) from the ECG data within the predetermined time period;

calculating, by the cloud server, a stress feature (SF) by 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, by the cloud server, adaptation to update a probability mass function (PMF); and

determining, by the cloud server, a stress level (SL) using the SF and the updated PMF to continuously measure the psychological stress.