Published Paper Details:

Sleep disorders can significantly impact an individual's overall health and well -being, making early detection crucial for effective intervention. This project presents a machine learning-based approach to detecting and classifying sleep disorders using health-related data. The dataset used included key features such as sleep duration, quality of sleep, physical activity levels, stress levels, body mass index (BMI), blood pressure, heart rate, and daily step count. To ensure accurate classification, multiple preprocessing steps are applied, including categorical encoding, feature scaling, and handling missing or duplicate values. The system utilizes a Random Forest classifier, trained on preprocessed data to predict potential sleep disorders. The model is evaluated using accuracy metrics and a classification report to ensure its reliability. The functionality is made accessible through a Flask-based web application, where users can input their health parameters and receive instant predictions regarding their sleep health. The system is designed to assist individuals in understanding their sleep patterns and taking necessary steps toward improved well-being. By leveraging machine learning, this project provides an efficient and user-friendly tool for sleep disorder prediction and awareness.