Stress Level Prediction and Management Using Machine Learning Techniques

Abstract

A smart solution for users to classify stress levels and make predictions using Machine Learning techniques like voice and face recognition is presented in this paper. Excessive stress, which can have detrimental effects even if certain reactions can be controlled, is a common aspect of life, causing physical, mental, and emotional strain when personal and social resources are exceeded. Stress is experienced by over 100 million Americans, and in Sri Lanka, a South Asian nation, there is less emphasis on mental health than in Western and European nations. According to the World Health Organization, it is estimated that 5% to 10% of Sri Lanka's population needs treatment for mental health issues. User sentiments are anticipated, and suggestions are provided based on AI methods, utilizing the system's ability to recognize voices and faces. Additionally, cardiac and sleep issues are identified and addressed using physical body data from IoT devices. Performance in stress management software is improved by the system, which is designed to work with multiple languages. Availability in both English and Sinhala languages is ensured by the system.

Country : Sri Lanka

1 M.K.B. Kaushalya2 W.M.G.D. Weerapana3 B.G.N. Gimhani4 Ishara Weerathunga5 Poorna Panduwawala6 Harischandra Gambheera

  1. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  2. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  3. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  4. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  5. Department of Information Technology, Sri Lanka Institute of Information Technology, Malabe, Sri Lanka
  6. Psychiatrist, Nawaloka Hospital, Colombo, Sri Lanka

IRJIET, Volume 7, Issue 10, October 2023 pp. 355-361

doi.org/10.47001/IRJIET/2023.710047

References

  1. K. G. P. R. Chandrasiri et al., “Mellow: Stress management system for university students in Sri Lanka,” 2021 6th International Conference on Information Technology Research (ICITR), 2021. doi:10.1109/icitr54349.2021.9657419.
  2. J. Babitha, “National Conference on Smart Systems and Technologies Stress Detection Based on Emotion Recognition Using Deep Learning,” vol. 8, no. 7, pp. 109–114, 2021, [Online]. Available: www.ijirt.org
  3. https://www.researchgate.net/publication/362430198_Voice_Analysis_for_Stress_Detection_and_Application_in_Virtual_Reality_to_Improve_Public_Speaking_in_Real-time_A_Review (accessed Aug. 14, 2023).
  4. “Voice stress analysis,” The Concise Dictionary of Crime and Justice,                 2002. doi:10.4135/9781452229300.n1969
  5. P. Pierleoni, L. Pernini, A. Belli, and L. Palma, “An Android-based Heart Monitoring System for the elderly and for patients with heart disease,” International Journal of Telemedicine and Applications, vol. 2014, pp. 1–11, 2014. doi:10.1155/2014/625156.
  6. C. H. Vinkers et al., “The effect of stress on core and peripheral body temperature in humans,” Stress, vol. 16, no.  5, pp. 520–530, 2013. doi:10.3109/10253890.2013.807243
  7. L. Rachakonda, A. K. Bapatla, S. P. Mohanty, and E. Kougianos, “Sayopillow: Blockchain-integrated privacy-assured IOMT framework for stress management considering sleeping habits,” IEEE Transactions on Consumer Electronics, vol. 67, no. 1, pp. 20–29, 2021. doi:10.1109/tce.2020.3043683.
  8. L. Rachakonda, S. P. Mohanty, E. Kougianos, K. Karunakaran, and M. Ganapathiraju, “Smart-pillow: An IOT based device for stress detection considering sleeping habits,” 2018 IEEE International Symposium on Smart Electronic Systems (iSES) (Formerly iNiS), 2018. doi:10.1109/ises.2018.00043.
  9. A.Muaremi, A. Bexheti, F. Gravenhorst, B. Arnrich, and G. Troster, “Monitoring the impact of stress on the sleep patterns of pilgrims using wearable sensors,” IEEE- EMBS International Conference on Biomedical and Health Informatics (BHI), 2014. doi:10.1109/bhi.2014.6864335.
  10. Selman, B., & Hirst, G. (1985). A rule-based connectionist parsing system. In Proceedings of the Seventh Annual Conference of the Cognitive Science Society (pp. 212-219).