Abstract
Stress has become a significant concern in today’s fast-paced world, affecting
individuals’ physical and mental well-being. This project, titled Human Stress Detection Based
on Sleeping Habits Using Machine Learning Algorithms, aims to address this issue by leveraging
data-driven insights to identify stress levels. The proposed system analyzes sleeping patterns,
including sleep duration, interruptions, and quality, to classify stress levels effectively. By
utilizing advanced machine learning algorithms such as Decision Tree, Random Forest, Logistic
Regression, and Support Vector Machine, the model processes data from wearable devices or
sleep-monitoring apps to extract relevant features. Key parameters such as sleep latency,
efficiency, and disturbances are analyzed alongside other influencing factors like age, lifestyle,
and physical activity. The project employs a robust dataset for training and testing, ensuring
high accuracy and reliability in predicting stress levels. The system not only identifies stress
levels but also provides actionable insights and recommendations to improve sleep quality and
overall well-being. Evaluation metrics such as accuracy, precision, recall, and F1 score are
employed to measure the model's performance. The outcome of this project demonstrates the
potential of machine learning in enhancing healthcare applications. It provides a scalable and
efficient tool for stress detection, promoting early intervention and better management of
stress-related disorders