Unsupervised Stress Detection Algorithm and Experiments with Real Life Data

  • Elena VildjiounaiteEmail author
  • Johanna Kallio
  • Jani Mäntyjärvi
  • Vesa Kyllönen
  • Mikko Lindholm
  • Georgy Gimel’farb
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10423)


Stress is the major problem in the modern society and a reason for at least half of lost working days in European enterprises, but existing stress detectors are not sufficiently convenient for everyday use. One reason is that stress perception and stress manifestation vary a lot between individuals; hence, “one-fits-all-persons” stress detectors usually achieve notably lower accuracies than person-specific methods. The majority of existing approaches to person-specific stress recognition, however, employ fully supervised training, requiring to collect fairly large sets of labelled data from each end user. These sets should contain examples of stresses and normal conditions, and such data collection effort may be tiring for end users. Therefore this work proposes an algorithm to train person-specific stress detectors using only unlabelled data, not necessarily containing examples of stresses. The proposed method, based on Hidden Markov Models with maximum posterior marginal decision rule, was tested using real life data of 28 persons and achieved average stress detection accuracy of 75%, which is similar to the accuracies of state-of-the-art supervised algorithms for real life data.


Stress detection Unsupervised learning Hidden Markov Models 


  1. 1.
    Merriam-Webster dictionary. Accessed 23 Mar 2017
  2. 2.
    Sano, A., Picard, R.W.: Stress recognition using wearable sensors and mobile phones. In: ACII 2013, pp. 671–676 (2013)Google Scholar
  3. 3.
    Alberdi, A., Aztiria, A., Basarab, A.: Towards an automatic early stress recognition system for office environments based on multimodal measurements: a review. J. Biomed. Inform. 59, 49–75 (2016)CrossRefGoogle Scholar
  4. 4.
    Hernandez, J., Morris, R.R., Picard, R.W.: Call center stress recognition with person-specific models. In: ACII 2011, pp. 125–134 (2011)CrossRefGoogle Scholar
  5. 5.
    Carneiro, D., Novais, P., Pêgo, J.M., Sousa, N., Neves, J.: Using mouse dynamics to assess stress during online exams. In: Onieva, E., Santos, I., Osaba, E., Quintián, H., Corchado, E. (eds.) HAIS 2015. LNCS, vol. 9121, pp. 345–356. Springer, Cham (2015). doi: 10.1007/978-3-319-19644-2_29CrossRefGoogle Scholar
  6. 6.
    Pimenta, A., Carneiro, D., Novais, P., Neves, J.: Detection of distraction and fatigue in groups through the analysis of interaction patterns with computers. In: Camacho, D., Braubach, L., Venticinque, S., Badica, C. (eds.) Intelligent Distributed Computing VIII. SCI, vol. 570, pp. 29–39. Springer, Cham (2015). doi: 10.1007/978-3-319-10422-5_5CrossRefGoogle Scholar
  7. 7.
    Rahman, M.M., et al.: Are we there yet?: feasibility of continuous stress assessment via wireless physiological sensors. In: ACM-BCB 2014, pp. 479–488 (2014)Google Scholar
  8. 8.
    Adams, P., Rabbi, M., Rahman, T., Matthews, M., Voida, A., Gay, G., Choudhury, T., Voida, S.: Towards personal stress informatics: comparing minimally invasive techniques for measuring daily stress in the wild. In: PervasiveHealth 2014, pp. 72–79 (2014)Google Scholar
  9. 9.
    Gjoreski, M., Gjoreski, H., Lutrek, M., Gams, M.: Continuous stress detection using a wrist device: in laboratory and real life. In: Ubicomp 2016 Adjunct, pp. 1185–1193 (2016)Google Scholar
  10. 10.
    Ferdous, R., Osmani, V., Mayora, O.: Smartphone app usage as a predictor of perceived stress levels at workplace. In: PervasiveHealth 2015, pp. 225–228 (2015)Google Scholar
  11. 11.
    Shi, Y., et al.: Personalized stress detection from physiological measurements. In: International Symposium on Quality of Life Technology (2010)Google Scholar
  12. 12.
    Garcia-Ceja, E., Osmani, V., Mayora, O.: Automatic stress detection in working environments from smartphones’ accelerometer data: a first step. IEEE J. Biomed. Health Inform. 20(4), 1053–1060 (2016)CrossRefGoogle Scholar
  13. 13.
    Maxhuni, A., Hernandez-Leal, P., Sucar, L.E., Osmani, V., Morales, E.F., Mayora, O.: Stress modelling and prediction in presence of scarce data. J. Biomed. Inform. 63, 344–356 (2016)CrossRefGoogle Scholar
  14. 14.
    Xu, Q., Nwe, T.L., Guan, C.: Cluster-based analysis for personalized stress evaluation using physiological signals. IEEE J. Biomed. Health Inform. 19(1), 275–281 (2015)CrossRefGoogle Scholar
  15. 15.
    Kusserow, M., Amft, O., Troster, G.: Modeling arousal phases in daily living using wearable sensors. IEEE Trans. Affect. Comput. 4(1), 93–105 (2013)CrossRefGoogle Scholar
  16. 16.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1986)CrossRefGoogle Scholar
  17. 17. Accessed 12 Jan 2016
  18. 18.
    Hovsepian, K., al’Absi, M., Ertin, E., Kamarck, T., Nakajima, M., Kumar, S.: cStress: towards a gold standard for continuous stress assessment in the mobile environment. In: ACM International Joint Conference on Pervasive and Ubiquitous Computing (2015)Google Scholar
  19. 19.
    Aalto, J.K., Brotheridge, C.M.: Resources, coping strategies and emotional exhaustion: a conservation of resources perspective. J. Vocat. Behav. 63(3), 490–509 (2003)CrossRefGoogle Scholar
  20. 20.
    Folkman, S., Lazarus, R.S.: An analysis of coping in a middleaged community sample. J. Health Soc. Behav. 21, 219–239 (1980)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Elena Vildjiounaite
    • 1
    Email author
  • Johanna Kallio
    • 1
  • Jani Mäntyjärvi
    • 1
  • Vesa Kyllönen
    • 1
  • Mikko Lindholm
    • 1
  • Georgy Gimel’farb
    • 2
  1. 1.VTT Technical Research Centre of FinlandEspooFinland
  2. 2.University of AucklandAucklandNew Zealand

Personalised recommendations