Psychological acute stress measurement using a wireless sensor
A method and system for determining psychological acute stress are disclosed. In a first aspect, the method comprises detecting a physiological signal using a wireless sensor device, determining a stress feature using a normalized heart rate and a plurality of heart rate variability (HRV) features, wherein the normalized heart rate and the plurality of heart rate variability features are calculated using the detected physiological signal, and determining a stress level using the stress feature to determine the psychological acute stress. In a second aspect, the system comprises a wireless sensor device that 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 wireless sensor device to carry out the steps of the method.
1. A method for determining psychological acute stress, the method comprising:
detecting a physiological signal using a wireless sensor device;
calculating a normalized heart rate using the detected physiological signal by combining a continuous basal heart rate and an average heart rate using the equation: HRR=(HR−HR b )/(HR max −HR b ), wherein the HR b is the continuous basal heart rate, the HR is the average heart rate, and the HR max =(208−0.7*Age) or (220−Age);
calculating a plurality of heart rate variability (HRV) features using the detected physiological signal
determining a stress feature using the normalized heart rate and the plurality of heart rate variability (HRV) features,
wherein the plurality of HRV features include statistical HRV features, frequency-domain HRV features, and non-linear HRV features,
wherein the frequency-domain HRV features include a ratio of spectral band powers (LF/HF ratio), and
wherein the non-linear HRV features include an approximate entropy measuring complexity of HR time interval series data of the physiological signal; and
determining a stress level using the stress feature to determine the psychological acute stress.
2. The method of claim 1 , wherein the statistical HRV features include any of a standard deviation of HR intervals (SDNN) and a root mean square successive differences of HR intervals (RMSSD), wherein the frequency-domain HRV features further include a normalized spectral band powers, and wherein the non-linear HRV features further include Poincare plot measures.
3. The method of claim 1 , further comprising:
determining whether an activity level threshold is reached; and
wherein if the activity level threshold is reached, detecting another physiological signal prior to the determining of the stress feature.
4. The method of claim 1 , wherein the plurality of HRV features are calculated by:
performing peak detection on the physiological signal to provide a plurality of successive peaks;
calculating a heart rate interval series using the plurality of successive peaks;
removing artifacts from the heart rate interval series to provide pruned heart rate interval values; and
extracting features from the pruned plurality of HRV features to provide the plurality of HRV features.
5. The method of claim 4 , wherein the physiological signal is any of an electrocardiogram (ECG) signal and a photoplethysmogram (PPG) signal.
6. The method of claim 5 , wherein the peak detection detects R peaks of the ECG signal or systolic peaks of the PPG signal.
7. The method of claim 4 , wherein the extracting step further comprises:
determining the continuous basal heart rate using the pruned heart rate interval values;
determining the average heart rate using the pruned heart rate interval values; and
determining the plurality of HRV features using a calculation of the pruned heart rate interval values over a predetermined time period.
8. The method of claim 1 , wherein the determining of the stress level step further comprises:
determining a probability mass function for a detected posture;
calculating the stress level using both the stress feature and the probability mass function; and
providing the stress level as a stress index metric on a predetermined scale.
9. A wireless sensor device for determining psychological acute stress, the wireless sensor device including 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 wireless sensor device to:
detect a physiological signal using a wireless sensor device;
determine a stress feature using a normalized heart rate and a plurality of heart rate variability (HRV) features, wherein the normalized heart rate and the plurality of HRV features are calculated using the detected physiological signal,
wherein the plurality of HRV features include statistical HRV features, frequency-domain HRV features, and non-linear HRV features,
wherein the frequency-domain HRV features include a ratio of spectral band powers (LF/HF ratio), and
wherein the non-linear HRV features include an approximate entropy measuring complexity of HR time interval series data of the physiological signal; and
determine a stress level including:
determine the psychological acute stress using, the stress feature,
determine a probability mass function for a detected posture,
calculate the stress level using both the stress feature and the probability mass function, and
provide the stress level as a stress index metric on a predetermined scale.
10. The wireless sensor device of claim 9 , wherein the statistical HRV features include any of a standard deviation of HR intervals (SDNN) and a root mean square successive differences of HR intervals (RMSSD), wherein the frequency-domain HRV features include a normalized spectral band powers, and wherein the non-linear HRV features include Poincare plot measures.
11. The wireless sensor device of claim 9 , wherein the processor further causes the wireless sensor device to:
determine whether an activity level threshold is reached; and
wherein if the activity level threshold is reached, detect another physiological signal prior to the determining of the stress feature.
12. The wireless sensor device of claim 9 , wherein the plurality of HRV features are calculated by the processor further causing the wireless sensor device to:
perform peak detection on the physiological signal to provide a plurality of successive peaks;
calculate a heart rate interval series using the plurality of successive peaks;
remove artifacts from the heart rate interval series to provide pruned heart rate interval values; and
extract features from the pruned plurality of HRV features to provide the plurality of HRV features.
13. The wireless sensor device of claim 12 , wherein the physiological signal is any of an electrocardiogram (ECG) signal and a photoplethysmogram (PPG) signal.
14. The wireless sensor device of claim 13 , wherein the peak detection detects R peaks of the ECG signal or systolic peaks of the PPG signal.
15. The wireless sensor device of claim 12 , wherein to extract further comprises to:
determine a continuous basal heart rate using the pruned heart rate interval values;
determine an average heart rate using the pruned heart rate interval values; and
determine the plurality of HRV features using a calculation of the pruned heart rate interval values basal heart rate over a predetermined time period.
16. The wireless sensor device of claim 15 , wherein the calculation of the normalized heart rate comprises combining the continuous basal heart rate and the average heart rate using the equation: HRR=(HR−HR b )/(HR max −HR b ), where HR b is the continuous basal heart rate, HR is the average heart rate, and HR max =(208−0.7*Age) or (220−Age).