International Research Journal of Education and Technology

This paper presents a predictive model for detecting human stress levels using sleep data and machine learning. Key sleep-related parameters, such as snoring rate, respiration rate, blood oxygen level, sleep duration, and heart rate, are analyzed to identify correlations between sleep patterns and stress. A hybrid model combining Random Forest, Support Vector Machine (SVM), and AdaBoost is used to improve predictive accuracy by leveraging the strengths of each algorithm. The model offers significant potential in healthcare and corporate wellness for early detection of stress-related disorders. By integrating the model into a web-based platform, it provides actionable insights for users to manage stress through better sleep hygiene. This approach addresses the growing issue of stress in modern society and promotes broader societal well-being.

Keywords: Sleep Data Analysis, Random Forest, SVM, AdaBoost