STRESS LEVEL PREDICTION USING MACHINE LEARNING

The proposed stress level prediction system using the Random Forest algorithm provides an efficient and accurate solution for identifying stress levels based on health-related parameters. The system successfully analyzes input factors such as snoring rate, sleeping hours, heart rate, respiration rate, and body temperature to predict stress levels accurately. The Random Forest classifier improves prediction performance by using multiple decision trees and reducing overfitting. Experimental results show that the proposed system achieves high accuracy, precision, recall, and F-Measure, making it reliable for stress level analysis techniques. The system is simple, user-friendly, and capable of providing quick prediction results with better reliability and efficiency. The preprocessing and feature selection techniques help improve the overall model performance and prediction accuracy. The proposed system can assist users in monitoring their stress conditions at an early stage and support better health management. Furthermore, the system can be enhanced in the future by integrating real-time health monitoring devices, mobile applications, and integrating real-time health monitoring devices, mobile applications, and cloud-based analytics to enable continuous tracking of stress levels. This would allow users to receive instant alerts and personalized recommendations based on their physiological and behavioral data.

[1]   N. Schneiderman, G. Ironson, and S. D. Siegel, “Stress and health: Psychological, behavioral, and biological determinants,” Annu. Rev. Clin. Psychol., vol. 1,pp,607–628,2005,doi: 10.1146/annurev.clinpsy.1.102803.144141. [2]  A. N. Vgontzas, S. Pejovic, and M. Karataraki, “Sleep, Sleep Disorders, and Stress,” Encycl. Stress, pp. 506–514, 2007, doi: 10.1016/B978-012373947-6.00349-4.  [3]  G. Fink, “Stress : Concepts , Cognition , Emotion , and Behavior : Handbook of Stress Stress : Concepts , Definition , and History George Fink Florey Institute of Neuroscience and Mental Health,” no. October, 2017, [Online].Available: https://www.researchgate.net/profile/George- Fink/publication/317026245_Stress_Concepts_Cognition_ Emotion_and_Behavior_Handbook_of_Stress/links/59d17 f1b0f7e9b4fd7fa28b3/Stress-Concepts-Cognition- Emotion-and-Behavior-andbook-of-Stress.pdf [4]  Q. Bukhsh, A. Shahzad, and M. Nisa, “A study of learning stress and stress management strategies of the students of postgraduate level: A case study of Islamia university of Bahawalpur, Pakistan,” Procedia - Soc. Behav. Sci., vol. 30, pp. 182–186, 2011, doi: 10.1016/j.sbspro.2011.10.036. [5]   A. M. Shahsavarani, E. A. M. Abadi, and M. H. Kalkhoran, “Stress Assessment and Development of a Primary Care of Psychology Service,” Int. J. Med. Rev., vol. 2, no. 2, pp. 230–241, 2014.  [6]  A. Khademi, Y. El-Manzalawy, L. Master, O. M. Buxton, and V. G. Honavar, “Personalized sleep parameters estimation from actigraphy: A machine learning approach,” Nat. Sci. Sleep, vol. 11, pp. 387– 399, 2019, doi: 10.2147/NSS.S220716. [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 Trans. Consum. Electron., vol. 67, no. 1, pp. 20–29, 2021, doi: 10.1109/TCE.2020.3043683. [8]  V. C. Magana and M. Munoz-Organero, “Reducing stress on habitual journeys,” 5th IEEE Int. Conf. Consum. Electron. - Berlin, ICCEBerlin 2015, pp. 153– 157, 2016, doi: 10.1109/ICCEBerlin. 2015.7391220.  [9]  A. R. Subhani, W. Mumtaz, M. N. B. M. Saad, N. Kamel, and A. S. Malik, “Machine learning framework for the detection of mental stress at multiple levels,” IEEE Access, vol. 5, no. c, pp. 13545–13556, 2017, doi: 10.1109/ACCESS.2017.2723622. [10]    E. Garcia-Ceja, M. Riegler, T. Nordgreen, P. Jakobsen, K. J. Oedegaard, and J. Tørresen, “Mental health monitoring with multimodal sensing and machine learning: A survey,” Pervasive Mob. Comput., vol. 51, pp. 1–26, 2018, doi: 10.1016/j.pmcj.2018.09.003