Sleep Disorder Detection using Machine Learning Method

Evidence is mounting quickly that multifactorial nocturnal surveillance, when combined with wearable technology and deep learning, may be problematic for the early detection and evaluation of sleep problems. Data of Numerous sleep disorders, such as insomnia, are growing increasingly widespread and severe, according to the World Health Organization (WHO) and hospitals that conduct medical research. This dynamic is associated with high levels of daily worry, stress, and depressive diseases. The use of ruing is used to forecast various sleep disorders. It contrasts the numerous strategies employed by various researcher did work in signal processing methodologies, as well as their benefits and shortcomings. The crucial element is sleep. It is essential for the normal maintenance of one’s bodily and mental health, just as crucial as breathing, eating, and drinking. Numerous obstacles prevent AI from being widely used and generalizable in therapeutic contexts. Nevertheless, AI has the potential to be a strong tool in the healthcare industry since it can improve patient diagnostic capacities, the management of sleep disorders. However, before incorporating existing algorithms for deep learning and machine learning into sleep clinics, it is essential to regulate and standardize them. In this research our model got highest accuracy of 93% which was highest as compare to other models.