Sleep Monitoring

Sleep monitoring research aims to develop accurate, accessible, and cost-effective alternatives to traditional polysomnography (PSG) for diagnosing and managing sleep disorders. Current efforts focus on leveraging multimodal data from sensors like EEG, ECG, and thermal cameras, employing deep learning architectures such as masked autoencoders, bidirectional state space models, and contrastive learning methods to improve sleep stage classification and apnea detection. These advancements promise to improve the diagnosis and management of sleep disorders by enabling more convenient and widespread sleep monitoring, both in clinical and home settings.