Stress Assessment Using Machine Learning Algorithms

This article examines the analysis of physiological indicators obtained from smartwatches using machine learning methods to detect stress levels. Data such as heart rate, blood pressure, blood glucose level, oxygen level, temperature, and other parameters collected from modern smartwatches were used to assess stress. These indicators provide the necessary information for stress assessment, as they reflect changes in a person’s physiological state. The collected data were processed using machine learning algorithms, specifically KNN, Random Forest, Decision Tree, and Gradient Boosting models. The results of the study demonstrate the effectiveness of machine learning methods in stress detection, contributing to the development of modern solutions aimed at health monitoring and psychological well-being. Furthermore, these methods aid in the development of healthcare applications, disease prevention, and mental health support.