Description
Sleep is vital for both physical and mental health, making accurate diagnosis of sleep disorders essential. One common sleep disorder is Sleep Apnea (SA), characterized by obstructed breathing during sleep, which can lead to brain and heart malfunctions. In severe cases, SA may cause strokes and cardiovascular diseases, and it increases the risk of secondary issues such as daytime vehicular accidents. Due to the complexity of the condition, early diagnosis and treatment are crucial.
Polysomnography (PSG) is commonly used for diagnosing SA. However, PSG data, recorded overnight, is extensive and rapidly changing, making manual analysis by healthcare professionals challenging and time-consuming. Consequently, automated SA detection using machine learning has become a significant area of research. Given the vast volume of medical data, deep learning is essential to quickly and effectively extract meaningful features.
Initially, EEG signals are collected from standard data sources and undergo preprocessing, which decomposes them into five components: delta, theta, alpha, beta, and gamma. Manual sleep staging is complex, time-consuming, and expertise-dependent, necessitating automated solutions derived from EEG data and deep learning models. This study explores Convolutional Neural Network (CNN) architecture for sleep stage classification, leveraging its ability to effectively learn spatial features from EEG data. CNN achieves notable accuracy in classifying sleep stages, showcasing its capability in spatial feature extraction. Future work will enhance model scalability, integrate multi-modal data, and explore real-time applications in wearable devices for advanced sleep monitoring.
Reviews
There are no reviews yet.