A Decision Support System for Stress Detection Using Bayesian Networks Implemented in GeNIe Modeler
Main Article Content
Abstract
Stress is a major factor influencing both physical and mental health, and prolonged or unmanaged stress can lead to a wide range of health disorders. Consequently, early detection of stress is essential for timely intervention, prevention, and effective health management. This study proposes a decision support system for stress detection based on Bayesian networks, implemented using the GeNIe Modeler platform. The proposed system explicitly models the causal relationships among lifestyle factors, physiological indicators, psychological symptoms, and the resulting stress level. By representing these dependencies within a probabilistic graphical framework, the model enables robust reasoning under uncertainty, which is particularly important in real-world health assessment scenarios where information may be incomplete or noisy. Expert domain knowledge is incorporated to design a meaningful and interpretable network structure that reflects established medical and psychological understanding. In addition, synthetic data generation and data-driven learning techniques are employed to estimate the conditional probability parameters of the network. The Bayesian network-based model allows the estimation of an individual’s stress level using observable evidence such as workload, sleep quality, physical activity, caffeine intake, heart rate, blood pressure, mood, fatigue, and headache. Through probabilistic inference, the model updates beliefs about stress levels even when some variables are unobserved. The implementation in GeNIe Modeler demonstrates the practical process of constructing, training, and validating Bayesian networks for medical decision support applications. Experimental results show that the proposed system provides transparent, interpretable, and reliable stress assessment, supporting both clinicians and individuals in monitoring stress conditions and making informed decisions for stress management and prevention.
Keywords
Stress detection, Bayesian networks, GeNIe Modeler.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[2] A. O. Akmandor and N. K. Jha, “Keep the Stress Away with SoDA: Stress Detection and Alleviation System,” in IEEE Transactions on Multi-Scale Computing Systems, vol. 3, no. 4, pp. 269-282, 1 Oct.-Dec. 2017, doi: 10.1109/TMSCS.2017.2703613.
[3] S. Gedam and S. Paul, “A Review on Mental Stress Detection Using Wearable Sensors and Machine Learning Techniques,” in IEEE Access, vol. 9, pp. 84045-84066, 2021, doi: 10.1109/ACCESS.2021.3085502.
[4] L. Zhu et al., “Stress Detection Through Wrist-Based Electrodermal Activity Monitoring and Machine Learning,” in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 5, pp. 2155-2165, May 2023, doi: 10.1109/JBHI.2023.3239305.
[5] A. de Santos Sierra, C. Sanchez Avila, J. Guerra Casanova and G. Bailador del Pozo, “A Stress-Detection System Based on Physiological Signals and Fuzzy Logic,” in IEEE Transactions on Industrial Electronics, vol. 58, no. 10, pp. 4857-4865, Oct. 2011, doi: 10.1109/TIE.2010.2103538.
[6] J. A. Healey and R. W. Picard, “Detecting stress during real-world driving tasks using physiological sensors,” in IEEE Transactions on Intelligent Transportation Systems, vol. 6, no. 2, pp. 156-166, June 2005, doi: 10.1109/TITS.2005.848368.
[7] Jing Zhai, A. B. Barreto, C. Chin and Chao Li, “Realization of stress detection using psychophysiological signals for improvement of human-computer interactions,” Proceedings. IEEE SoutheastCon, 2005., Ft. Lauderdale, FL, USA, 2005, pp. 415-420, doi: 10.1109/SECON.2005.1423280.
[8] G. Rigas, Y. Goletsis and D. I. Fotiadis, “Real-Time Driver’s Stress Event Detection,” in IEEE Transactions on Intelligent Transportation Systems, vol. 13, no. 1, pp. 221-234, March 2012, doi: 10.1109/TITS.2011.2168215.
[9] J. D. García-Franco, F. J. Díez, and M. Á. Carrasco, “Probabilistic graphical model for the evaluation of the emotional and dramatic personality disorders,” Frontiers in Psychology, vol. 13, Art. no. 996609, 2022, doi: 10.3389/fpsyg.2022.996609.
[10] GeNIe Modeler: https://www.bayesfusion.com/genie/