This paper proposes a machine learning–based system for automatic classification of sleep disorders. Using curated datasets and models like Logistic Regression, Random Forest, Gradient Boosting, and KNN, the system improves diagnostic accuracy and scalability. A Django interface supports user interaction and visualization. The approach reduces manual effort and enhances healthcare efficiency.
The system demonstrates improved classification accuracy and robustness over manual methods. It supports scalable healthcare applications and lays the groundwork for integration with real-time monitoring systems. Future work may explore multimodal data fusion and deployment in clinical settings.
References
Includes references from COLING, ACL, SIGKDD, IEEE, and Pattern Recognition covering product classification, multimodal fusion, and hierarchical learning in sleep and e-commerce domains.
