Real-Time Personalized Physiologically Based Stress Detection For Hazardous Operations
DOI:
https://doi.org/10.69996/fmep.2025022Keywords:
Real-time stress detection, Personalized physiological monitoring, Hazardous operations, Machine learning, Approximate Bayes classifierAbstract
This paper presents a real-time, personalized stress detection system designed to enhance safety and performance in hazardous operational environments. The system leverages physiological signals—including heart rate, blood pressure, electrodermal activity, and respiration—to classify stress levels through machine learning models. Unlike conventional generalized models, this approach focuses on individual-specific feature selection and temporal signal analysis to improve accuracy and responsiveness. A comparative evaluation using tasks of varying complexity demonstrated that personalized models, particularly when combined with the Approximate Bayes classifier, consistently outperformed traditional classifiers such as SVM, Decision Tree, and Random Forest. The proposed system features an interactive interface for system operators to upload datasets, monitor stress prediction status, and analyze stress ratios in real time. Experimental results confirmed the system's ability to detect low, medium, and high stress levels with high precision, making it suitable for deployment in high-risk domains. This study highlights the potential of personalized, real-time physiological monitoring to support timely decision-making, reduce operational risk, and promote workforce well-being.
References
[1] T. T. Finseth, M. C. Dorneich, S. Vardeman, N. Keren and W. D. Franke, “Real-time personalized physiologically based stress detection for hazardous operations,” IEEE Access, vol.11, pp.25431- 25454, 2023.
[2] M. A. Srinivas, M. Appalarajumouli, G. Karthik, C. Surendra, E. Brahmanjali and B. Sasank, “Real Time Personalized Stress Detection for Risky Operations,” International Journal of Innovative Science, Engineering & Technology, vol.11, no.3, 2024.
[3] M. Bolpagni, S. Pardini, M. Dianti and S. Gabrielli, “Personalized stress detection using biosignals from wearables: A scoping review,” Sensors, vol.24, no.10, pp.3221, 2024.
[4] N. Rane, S. Choudhary and J. Rane, “Leading-edge wearable technologies in enhancing personalized safety on construction sites: a review,” Available at SSRN 4641480, 2023.
[5] Arroju Shivani, R. Sreelakshmi, Adunoori Bhavani, Jadhav Ramdas and Akkula Jithender, “Detection and Mitigation of Web Attacks with End-To-End Deep Learning,” Journal of Computer Allied Intelligence, vol.3, no.3, pp.56-80, 2025.
[6] G. Taskasaplidis, D. A. Fotiadis and P. D. Bamidis, “Review of stress detection methods using wearable sensors,” IEEe Access, vol.12, pp.38219-38246, 2024.
[7] J. L. König, A. Hinze and J. Bowen, “Workload categorization for hazardous industries: The semantic modelling of multi-modal physiological data,” Future Generation Computer Systems, vol.141, pp.369-381, 2023.
[8] T. Finseth, M. C. Dorneich, N. Keren, W. D. Franke and S. Vardeman, “Virtual reality adaptive training for personalized stress inoculation,” Human Factors, vol.67. no.1, pp.5-20, 2025.
[9] A. Simeone, R. Grant, W. Ye and A. Caggiano, “A human-cyber-physical system for Operator 5.0 smart risk assessment,” The International Journal of Advanced Manufacturing Technology, vol.129, no.5, pp.2763-2782, 2023.
[10] I. Adamopoulos, A. Valamontes, P. Tsirkas and G. Dounias, “Predicting Workplace Hazard, Stress and Burnout among Public Health Inspectors: An AI-Driven Analysis in the Context of Climate Change,” European Journal of Investigation in Health, Psychology and Education, vol.15, no.5, pp.65, 2025.
[11] N. Mateos-García, A. B. Gil-González, A. Luis-Reboredo and B. Pérez-Lancho, “Driver stress detection from physiological signals by virtual reality simulator,” Electronics, vol.12, no.10, pp.2179, 2023.
[12] Kristy Anjala, “Understanding the Academic Stress: Factors, Impact and Strategies: A Review,” International Journal of Advance Research and Innovation, vol.12, no.1, pp.11-16, 2024.
[13] K. Magtibay and K. Umapathy, “A review of tools and methods for detection, analysis, and prediction of allostatic load due to workplace stress,” IEEE Transactions on Affective Computing, vol.15, no.1, pp.357-375, 2023.
[14] S. Ishaque, N. Khan and S. Krishnan, “Physiological signal analysis and stress classification from VR simulations using decision tree methods,” Bioengineering, vol.10, no.7, pp.766, 2023.
[15] G. Masri, F. Al-Shargie, U. Tariq, F. Almughairbi, F. Babiloni and H. Al-Nashash, “Mental stress assessment in the workplace: a review,” IEEE Transactions on Affective Computing, vol.15, no.3, pp.958-976, 2023.
[16] H. Hijry, S. M. R. Naqvi, K. Javed, O. H. Albalawi, R. Olawoyin, C. Varnier and N. Zerhouni, “Real time worker stress prediction in a smart factory assembly line,” IEEE Access, 2024.
[17] Y. Haque, R. S. Zawad, C. S. A. Rony, H. Al Banna, T. Ghosh, M. S. Kaiser and M. Mahmud, “State-of-the-art of stress prediction from heart rate variability using artificial intelligence,” Cognitive Computation, vol.16, no.2, pp.455-481, 2024.
[18] A. Apraiz, G. Lasa, F. Montagna, G. Blandino, E. Triviño-Tonato and A. Dacal-Nieto, “An experimental protocol for human stress investigation in manufacturing contexts: Its application in the no-stress project,” Systems, vol.11, no.9, pp.448, 2023.
[19] P. Hemalatha, “Secure Deep Learning Architecture Model for Data Management and Scheduling of E-Commerce Data,” Journal of Sensors, IoT & Health Sciences, vol.2, no.2, pp.16-29, 2024.
[20] M. Donati, M. Olivelli, R. Giovannini and L. Fanucci, “ECG-based stress detection and productivity factors monitoring: the real-time production factory system,” Sensors, vol.23, no.12, pp.5502, 2023.
[21] G. Rescio, A. Manni, M. Ciccarelli, A. Papetti, A. Caroppo and A. Leone, “A deep learning-based platform for workers’ stress detection using minimally intrusive multisensory devices,” Sensors, vol.24, no.3, pp.947, 2024.
[22] S. Davila-Gonzalez and S. Martin, “Human digital twin in industry 5.0: A holistic approach to worker safety and well-being through advanced AI and emotional analytics,” Sensors, vol.24, no.2, pp.655, 2024.
