Applying Machine Learning Algorithms For The Classification Of Sleep Disorders

Sleep disorders significantly impact physical and mental health, necessitating accurate and accessible diagnostic methods. Traditional diagnostic techniques like Polysomnography (PSG) are often inconvenient, expensive, and limited in availability. This project aims to leverage machine learning algorithms to classify sleep disorders using health and lifestyle data from the Kaggle Sleep Health and Lifestyle Dataset. The existing system employs algorithms such as K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree, Random Forest, and Artificial Neural Network (ANN), which have several limitations including computational expense and sensitivity to hyperparameters. To address these issues, the proposed system implements ensemble learning techniques, specifically Stacking Classifier and Voting Classifier, to enhance accuracy, robustness, and interpretability. By combining the strengths of multiple models, the project seeks to provide a more efficient, cost-effective, and accessible solution for diagnosing sleep disorders, ultimately improving patient outcomes and quality of life.

Keywords: Sleep Disorders, Machine Learning, Stacking Classifier, Voting Classifier, Sleep Apnea, Insomnia.