Advertisement

An Improved Machine Learning Model for Stress Categorization

  • Rojalina PriyadarshiniEmail author
  • Mohit Ranjan Panda
  • Pradeep Kumar Mallick
  • Rabindra Kumar Barik
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1040)

Abstract

Stress and depression are now a global problem. 25% of world’s population is facing this problem. With the growing use of sensor equipped intelligent wearables, physiological parameters can be easily extracted and effectively analyzed to predict it at an early stage. Stress management is a complex problem, as to predict stress; there exist several parameters to be considered. Choosing the right parameter is a challenging task, to predict the stress more accurately. In this work, to select the most efficient parameters the unsupervised algorithm, K-Means is used; and after getting the right parameters, a radial basis function based neural network is utilized to group the captured data to be stressed or non-stressed. The model also identifies the type of the stress. The work is validated in Python based environment and gives a promising result, in terms of accuracy.

Keywords

Stress Classification Prediction Machine learning 

References

  1. 1.
    Organization, W.H.: The World Health Report 2001: Mental health: new understanding, new hope. World Health Organization (2001)Google Scholar
  2. 2.
    Mukhopadhyay, S.: Measuring stress in humans: a practical guide for the field. In: Ice, G.H., James, G.D. (eds.), pp. 271. Cambridge university press, Cambridge (2006). ISBN 0-52184479-7; Hardback. J. Biosoc. Sci. 41(1), 156–158 (2009)Google Scholar
  3. 3.
    Adams, Z.W., McClure, E.A., Gray, K.M., Danielson, C.K., Treiber, F.A., Ruggiero, K.J.: Mobile devices for the remote acquisition of physiological and behavioural biomarkers in psychiatric clinical research. J. Psychiatr. Res. 85, 1–14 (2017)CrossRefGoogle Scholar
  4. 4.
    Majumder, S., Mondal, T., Deen, M.: Wearable sensors for remote health monitoring. Sensors 17(1), 130 (2017)CrossRefGoogle Scholar
  5. 5.
    Priyadarshini, R., Barik, R., Dubey, H.: Deepfog: Fog computing-based deep neural architecture for prediction of stress types, diabetes and hypertension attacks. Computation 6(4), 62 (2018)CrossRefGoogle Scholar
  6. 6.
    Sriramprakash, S., Prasanna, V.D., Murthy, O.R.: Stress detection in working people. Procedia computer science 115, 359–366 (2017)CrossRefGoogle Scholar
  7. 7.
    Casale, S., Russo, A., Scebba, G., Serrano, S.: Speech emotion classification using machine learning algorithms. In: 2008 IEEE International Conference on Semantic Computing, pp. 158–165. IEEE (2008)Google Scholar
  8. 8.
    Sani, M., Norhazman, H., Omar, H., Zaini, N., Ghani, S.: Support vector machine for classification of stress subjects using eeg signals. In: 2014 IEEE Conference on Systems, Process and Control (ICSPC 2014), IEEE, pp. 127–131 (2014)Google Scholar
  9. 9.
    Ghaderi, A., Frounchi, J., Farnam, A.: Machine learning-based signal processing using physiological signals for stress detection. In: 2015 22nd Iranian Conference on Biomedical Engineering (ICBME), pp. 93–98 (2015).  https://doi.org/10.1109/icbme.2015.7404123
  10. 10.
    Villarejo, M.V., Zapirain, B.G., Zorrilla, A.M.: A stress sensor based on galvanic skin response (gsr) controlled by zigbee. Sensors 12(5), 6075–6101 (2012)CrossRefGoogle Scholar
  11. 11.
    Liu, D., Ulrich, M.: Listen to your heart: stress prediction using consumer heart rate sensors. [Online]. Retrieved from the Internet (2014)Google Scholar
  12. 12.
    Sun, F.T., Kuo, C., Cheng, H.T., Buthpitiya, S., Collins, P., Griss, M.: Activity-aware mental stress detection using physiological sensors. In: International conference on Mobile computing, applications, and services, pp. 282–301. Springer (2010)Google Scholar
  13. 13.
    Li, X., Chen, Z., Liang, Q., Yang, Y.: Analysis of mental stress recognition and rating based on hidden Markov model. J. Comput. Inf. Syst. 10(18), 7911–7919 (2014)Google Scholar
  14. 14.
    Gjoreski, M., Lutrek, M., Gams, M., Gjoreski, H.: Monitoring stress with a wrist device using context. J. Biomed. Inform. 73, 159–170 (2017).  https://doi.org/10.1016/j.jbi.2017.08.006, http://www.sciencedirect.com/science/article/pii/S1532046417301855CrossRefGoogle Scholar
  15. 15.
    Birjandtalab, J., Cogan, D., Pouyan, M.B., Nourani, M.: A non-eeg biosignals dataset for assessment and visualization of neurological status. In: 2016 IEEE International Workshop on Signal Processing Systems (SiPS), IEEE, pp. 110–114 (2016)Google Scholar
  16. 16.
    Song, S.H., Kim, D.K.: Development of a stress classification model using deep belief networks for stress monitoring. Heal. Inform. Res. 23, 285–292 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Rojalina Priyadarshini
    • 1
    Email author
  • Mohit Ranjan Panda
    • 2
  • Pradeep Kumar Mallick
    • 3
  • Rabindra Kumar Barik
    • 4
  1. 1.Department of Computer Science and Information TechnologyC. V. Raman College of EngineeringBhubaneswarIndia
  2. 2.Department of Computer Science and EngineeringC. V. Raman College of EngineeringBhubaneswarIndia
  3. 3.School of Computer EngineeringKalinga Institute of Industrial Technology (KIIT) Deemed to be UniversityBhubaneswarIndia
  4. 4.School of Computer AcademyKalinga Institute of Industrial Technology (KIIT) Deemed to be UniversityBhubaneswarIndia

Personalised recommendations