Stress has become a major public health concern, significantly impacting both mental and physiological well-being. Traditional stress assessment methods, such as psychological questionnaires or manual monitoring, are often subjective and unsuitable for real-time analysis. Recent advances in machine learning (ML) and wearable sensor technology have enabled objective, data-driven stress detection using Heart Rate Variability (HRV) a physiological indicator derived from the time intervals between consecutive heartbeats. Stress is a Natural response to Pressure, But when it becomes chronic, it can leads to Mental Health Issues. Stress is measured using physiological Parameter such as Heart Rate Variability (HRV).HRV is not equivalent to Heart Rate. HRV represents the variation of Time Interval Between successive Heart Beats. If a Person having Stress, it leads to increase in the Heart rate, which causes Risk to life. HRV Increases with Relaxation and decrease with stress. Indeed, HRV is usually higher when heart is beating slowly & vice versa. Our Project focuses on developing ML model capable of accurately detecting stress levels based on the Indicator given to all types of stress levels. The proposed system demonstrates the feasibility of using HRV metrics for real-time stress monitoring, offering a non-invasive and efficient alternative to conventional assessment methods. This research contributes to the development of intelligent health monitoring systems that can be integrated into wearable technologies for proactive mental health management and personalized wellness tracking.

Implementing Machine Learning-based stress detection via HRV analysis involves using advanced computer algorithms to understand how our heart’s activity changes with stress. By analyzing data from devices like ECG monitors, these algorithms can detect patterns that signal stress levels. This information can help individuals and healthcare professionals better manage stress and improve overall well-being. Machine Learning-based systems can provide real-time feedback, making it easier to track stress levels and take appropriate actions. This approach combines technology and health to create personalized solutions for stress management, potentially leading to healthier lifestyles and improved mental well-being for many people.

[1]Sadruddin, Safia, Vaishali D. Khairnar, and Deepali R. Vora. “Machine Learning based Assessment of Mental Stress using Wearable Sensors.” In 2024 11th International Conference on Computing for Sustainable Global Development (INDIACom), pp. 351-355. IEEE, 2024. [2]Mortensen, Jon Andreas, Martin Efremov Mollov, Ayan Chatterjee, Debasish Ghose, and Frank Y. Li. “Multi-class stress detection through heart rate variability: A deep neural network based study.” IEEE Access (2023). [3]Seo, Wonju, Namho Kim, Cheolsoo Park, and Sung-Min Park. “Deep learning approach for detecting work-related stress using multimodal signals.” IEEE Sensors Journal 22, no. 12 (2022): 11892-11902. [4]Ahmad, Zeeshan, Anika Tabassum, Ling Guan, and Naimul Khan. “Ecg heart-beat classification using multimodal image fusion.” In ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1330-1334. IEEE, 2021. [5]Gedam, Shruti, and Sanchita Paul. “A review on mental stress detection using wearable sensors and machine learning techniques.” IEEE Access 9 (2021): 84045-84066. [6]Di Martino, Flavio, and Franca Delmastro. “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. IEEE, 2020. [7]Benchekroun, Mouna, Pedro Elkind Velmovitsky, Dan Istrate, Vincent Zalc, Plinio Pelegrini Morita, and Dominique Lenne. “Cross dataset analysis for generalizability of HRV- based stress detection models.” Sensors 23, no. 4 (2023): 1807. [8]Panicker, Suja Sreeith, and Prakasam Gayathri. “A survey of machine learning techniques in physiology based mental stress detection systems.” Biocybernetics and Biomedical Engineering 39, no. 2 (2019): 444-469.

© 2025 International Journal of Engineering and Techniques (IJET).

Digital Object Identifier (DOI)

IJET assigns a unique DOI to every accepted article via Zenodo for persistent linking and citation. Your article’s DOI: https://doi.org/{{doi}}

Open DOI About Zenodo DOI

Close