Stress Measurement

1) Biological signal-based measurements

The SLTLab Wellness App estimates the user's stress levels by analyzes the user's heart rate variability (HRV) using ECG signals obtained from the user's Apple Watch.

Various features are extracted from the ECG signal through signal processing,1-4 and those correlated to stress are selected.5-7 Then, SLTLab’s Wellness App evaluates the stress using machine learning algorithms using the selected features.8-9 

In addition, SLTLab's Wellness App measures stress using two HRV features acquired from Apple Watch's optical heart sensor for users who cannot use ECG signals provided by Apple Watch. With a small number of HRV features used for stress measurements, machine learning uses multiple assumptions and predicated data, which may result in lower accuracy than the stress measurement technique using ECG sensors.

Stress Measure(1) - Biological signal-based measurements

2) Survey-Based Measurement

SLTLab's Wellness App uses a questionnaire to assess stress levels reflecting the user's subjective perceptions and environmental factors together with the biological signals measured from the Apple Watch's sensors. The survey content and stress measurement methods were developed by the Survivability Signal Intelligence Research Center (CRC), funded by the National Research Foundation of Korea.

The Survey Questions are as follows. 
Question Number

Question Text


I don’t have time or money for leisure activities.

2 I don’t have very many close relationships with other people.
3 When faced with competition, my relationships with others become strained.
4 I think I am suffering from depression.
5 I’m worried about my drinking habits.
6 I’m worried about my health.
7 I don’t feel that I am handling everything well.
8 I feel nervous or stressed.
9 I feel that too many difficult things have piled up, and I cannot overcome them. 
10 I feel that things aren't going as well as I'd hoped. 

The responses are scored according to the following scale.


Strongly disagree




Strongly Agree







And the stress measurement levels are then calculated with the following score ranges.













[1] Castaldo, R., Montesinos, L., Melillo, P., James, C., & Pecchia, L. (2019). “Ultra-short term HRV features as surrogates of short term HRV: a case study on mental stress detection in real life”. BMC medical informatics and decision making, 2019(12), pp. 1-13.

[2]  Jang, D. G., Hahn, M., Jang, J. K., Farooq, U., & Park, S. H. (2012). “A comparison of interpolation techniques for RR interval fitting in AR spectrum estimation”. Biomedical Circuits and Systems Conference, pp. 352-355.

[3] Choi, W. J., Lee, B. C., Jeong, K. S., & Lee, Y. J. (2017). “Minimum Measurement Time Affecting the Reliability of the Heart Rate Variability Analysis”. Korean Journal of Health Promotion, 2017(4), pp. 269-274.

[4] Koldijk, S., Sappelli, M., Verberne, S., Neerincx, M. A., & Kraaij, W. (2014). “The swell knowledge work dataset for stress and user modeling research”. Proceedings of the 16th international conference on multimodal interaction, pp. 291-298.

[5] NKURIKIYEYEZU, Kizito, et al. (2019). “Thermal Comfort and Stress Recognition in Office Environment”. 12th International Joint Conference,  pp. 256-263.

[6] CASTALDO, Rossana, et al. (2015). “Acute mental stress assessment via short term HRV analysis in healthy adults: A systematic review with meta-analysis”. Biomedical Signal Processing and Control, 2015(18), pp. 370-377.

[7] Hye-Geum, K. Eun-Jin C., Dai-Seg B., Young-Hwan L., & Bon-Hoon K., (2018). “Stress and heart rate variability: a meta-analysis and review of the literature”. Psychiatry Investing, 2018(15), pp. 235-245.

[8] Melillo, P., Bracale, M., & Pecchia, L. (2011). “Nonlinear Heart Rate Variability features for real-life stress detection. Case study: students under stress due to university examination”. Biomedical engineering online, 2011(10), pp. 1-13.

[9] Wijsman, J., Grundlehner, B., Liu, H., Hermens, H., & Penders, J. (2011). “Towards mental stress detection using wearable physiological sensors”. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011(11), pp. 1798-1801