ARCHIVES

Abstract: Nowadays, millions of people are affected by sleep disorders, and diagnosing these conditions can be complex and time-consuming with traditional methods. Expert classification of sleep stages is often prone to human error, which can impact diagnostic accuracy. The development of accurate machine learning algorithms for sleep disorder classification requires analysing, monitoring and diagnosing sleep disorders. This proposed system explores how machine learning, specifically Artificial Neural Networks (ANNs), can be used to classify different types of sleeping disorders, such as obstructive sleep apnea, insomnia and restless legs syndrome. Utilizing a dataset containing sleep-related features from clinical studies as well as Polysomnography data, the model is trained for classifying sleep disorders. After data normalization and feature selection with the trained neural network, this proposed system is trying to achieve an improved accuracy in identifying patterns associated with various sleep disorders, surpassing traditional diagnostic methods. The findings suggest that artificial neural networks (ANNs) offer significant improvements in diagnostic precision, highlighting the potential of machine learning to enhance the diagnosis and management of sleep disorders.