Vol. 2 No. 2 (2024): Issue - 02
Articles

Enhancing Stress Detection Employing Physiological Signals from the WESAD Dataset: A Machine Learning Approach with SMOTE

DOWNLOAD PDF
  • G Ramasubba Reddy,
  • J Jagadeswara Reddy,
  • M V Subba Reddy,
  • I Sravani,
  • V Kishen Ajay Kumar
G Ramasubba Reddy
Department of Computer Science & Engineering, Sai Rajeswari Institute of Technology, Proddatur, Andhra Pradesh, India
J Jagadeswara Reddy
Department of Computer Science & Engineering, Sai Rajeswari Institute of Technology, Proddatur, Andhra Pradesh, India
M V Subba Reddy
Department of Computer Science & Engineering, Sai Rajeswari Institute of Technology, Proddatur, Andhra Pradesh, India
I Sravani
Department of Computer Science & Engineering, Sai Rajeswari Institute of Technology, Proddatur, Andhra Pradesh, India
V Kishen Ajay Kumar
Department of Electronics and Communication Engineering, Institute of Aeronautical Engineering, Hyderabad, Telangana, India.
DOI: https://doi.org/10.5281/zenodo.14566207

Published 2024-12-28

Keywords

  • Stress Detection,
  • WESAD Dataset,
  • Machine Learning,
  • Synthetic Minority Oversampling Technique (SMOTE),
  • Wearable Health Monitoring,
  • Health Monitoring Systems
    • ...More
    Less

How to Cite

G Ramasubba Reddy, J Jagadeswara Reddy, M V Subba Reddy, I Sravani, & V Kishen Ajay Kumar. (2024). Enhancing Stress Detection Employing Physiological Signals from the WESAD Dataset: A Machine Learning Approach with SMOTE. Milestone Transactions on Medical Technometrics, 2(2), 79–87. https://doi.org/10.5281/zenodo.14566207

Abstract

Numerous medical disorders, including diabetes, heart disease, and hypertension, are significantly influenced by stress. Physiological markers for real-time stress detection are becoming more popular as wearable health monitoring devices are widely used. This research uses the WESAD (Wearable Stress and Affect Detection) dataset, which contains multimodal physiological data, including ECG, EDA, EMG, respiration, and temperature, to predict stress levels. We apply four machine learning classifiers to this dataset, focusing on addressing the class imbalance using the Synthetic Minority Oversampling Technique (SMOTE). The outcomes illustrate that Decision Trees outperform other classifiers with an accuracy of 96.27%.  For future work, efforts can be directed towards incorporating additional modalities, such as EEG and eye-tracking data, to improve stress detection accuracy further. Longitudinal data collection could also help understand stress over comprehensive periods, providing insights into chronic stress patterns.
DOWNLOAD PDF

References

  1. A machine-learning approach for stress detection using wearable sensors in free-living environments. (2024). Computers in Biology and Medicine, 108918.
  2. Abd Al-Alim, M. a. (2024). A machine-learning approach for stress detection using wearable sensors in free-living environments. Computers in Biology and Medicine, 108918.
  3. Ahmed, S. M. (2024). Psychological Perspectives on Work Stress: Implications for Healthcare Professionals.
  4. Ardecani, F. B. (2024). Assessing the Impact of AR-Assisted Warnings on Roadway Workers' Stress Under Different Workload Conditions. arXiv preprint arXiv:2410.14537.
  5. Babayit, O. a. (2024). The interplay of academic procrastination, self-generated stress, and self-reported bruxism among medical and dental students: a cross-sectional study. BMC psychology, 586.
  6. Bajpai, D. a. (2020). Evaluating KNN performance on WESAD dataset. In 2020 12th International Conference on Computational Intelligence and Communication Networks (CICN) (pp. 60--62).
  7. Benita, D. S. (2024). Stress Detection Using CNN on the WESAD Dataset. In 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC) (pp. 308--313).
  8. Benita, D. S. (2024). Stress Detection Using CNN on the WESAD Dataset. In 2024 International Conference on Emerging Systems and Intelligent Computing (ESIC) (pp. 308--313).
  9. Bolpagni, M. a. (2024). Personalized Stress Detection Using Biosignals from Wearables: A Scoping Review. Sensors, 3221.
  10. Chu, B. a. (2024). Physiology, stress reaction. In StatPearls [Internet]. StatPearls Publishing.
  11. Di Martino, F. a. (2020). High-resolution physiological stress prediction models based on ensemble learning and recurrent neural networks. In 2020 IEEE symposium on computers and communications (ISCC) (pp. 1--6).
  12. Elreedy, D. a. (2024). A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Machine Learning, 4903--4923.
  13. Gedam, S. a. (2024). Advancing Mental Stress Detection in Indian Housewives: A Deep Learning Approach with Wearable Physiological Sensors and Feature Selection Methods.
  14. Geetha, R. a. (2024). Human Stress Detection in and Through Sleep Patterns Using Machine Learning Algorithms. Journal of The Institution of Engineers (India): Series B, 1--23.
  15. Ghosh, S. a. (2021). A new physiology-based objective mental stress detection technique with reduced feature set and class imbalanced dataset management. In 2021 IEEE International Conference on Technology, Research, and Innovation for Betterment of Society (TRIBES) (pp. 1--6).
  16. Gupta, R. a. (2023). Multimodal wearable sensors-based stress and affective states prediction model. In 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS) (pp. 30--35).
  17. Hsieh, C.-P. a.-T.-K.-Y. (2019). Feature selection framework for XGBoost based on electrodermal activity in stress detection. In 2019 IEEE International Workshop on Signal Processing Systems (SiPS) (pp. 330--335).
  18. Kaddoura, S. A. (2024). Deep convolutional neural networks with genetic algorithm-based synthetic minority over-sampling technique for improved imbalanced data classification. Appl. Soft Comput., 111491.
  19. Karthick, T. a. (2022). Automatic stress recognition system with deep learning using multimodal psychological data. In 2022 International Conference on Electronic Systems and Intelligent Computing (ICESIC) (pp. 122--127).
  20. Liu, R. T. (2024). A systematic review and Bayesian meta-analysis of 30 years of stress generation research: Clinical, psychological, and sociodemographic risk and protective factors for prospective negative life events. Psychological Bulletin.
  21. Mazumdar, G. a. (n.d.). ML-based stress classification and detection using multimodal affect dataset. In Advances in Networks, Intelligence and Computing (pp. 210--221). CRC Press.
  22. Pokhrel, M. K. (n.d.). Effective Strategies for Stress Management in Teaching: Enhancing Well-being and Resilience.
  23. Quadrini, M. a. (2024). Stress detection with encoding physiological signals and convolutional neural network. Machine Learning, 1--29.
  24. Rashid, N. a. (2023). Stress detection using context-aware sensor fusion from wearable devices. IEEE Internet of Things Journal, 14114--14127.
  25. Razavi, M. a. (2024). Machine learning, deep learning, and data preprocessing techniques for detecting, predicting, and monitoring stress and stress-related mental disorders: Scoping review. JMIR Mental Health, e53714.
  26. Schmid, R. F. (2024). Individual differences in parasympathetic nervous system reactivity in response to everyday stress are associated with momentary emotional exhaustion. Scientific Reports, 26662.
  27. Shedage, P. S. (2024). Stress Detection Using Multimodal Physiological Signals With Machine Learning From Wearable Devices. In 2024 IEEE Symposium on Computers and Communications (ISCC) (pp. 1--6).
  28. Vetrivel, S. a. (2024). Coping Mechanisms for Stress Among Students at Universities. In Student Well-Being in Higher Education Institutions (pp. 157--186). IGI Global.
  29. Xiao, X. a. (2024). Advances in machine learning for wearable sensors. ACS nano, 22734--22751.
  30. Zayas, V. a. (2024). Out of sight but in mind: Experimentally activating partner representations in daily life buffers against common stressors. Emotion.