Data-Driven Approaches for Personalized Sleep Disorder Diagnosis

These days, sleeping disorders are a concern for young people and people with a variety of health issues. It is important to keep in mind that sleep problems are not a recent occurrence and should not be sought after or accepted as a trend, even though it is true that issues related to sleep have garnered more attention and discussion in recent years due to growing knowledge and research. Numerous problems, such as anxiety, depression, and mental health strain, can be brought on by this illness. Machine learning (ML) can handle a wide range of tasks, including classification, prediction, and decision-making. To analyze and identify sleeping disorders using ML and can also be employed to gauge a person's level of stress. This paper presents the DL models and ML algorithms that have been deployed to sleep stage classification in the literature to date. The effectiveness of Adaboost models is investigated in this work. These models' research findings suggest the ideal parameter combination for improved performance.