Sleep CLIP: A Multimodal Sleep Staging Model Based on Sleep Signals and Sleep Staging Labels
Open Access
Abstract
Since the release of the contrastive language-image pre-training (CLIP) model designed by the OpenAI team, it has been applied in several fields owing to its high accuracy. Sleep staging is an important method of diagnosing sleep disorders, and the completion of sleep staging tasks with high accuracy has always remained the main goal of sleep staging algorithm designers. This study is aimed at designing a multimodal model based on the CLIP model that is more suitable for sleep staging tasks using sleep signals and labels. The pre-training efforts of the model involve five different training sets. Finally, the proposed method is tested on two training sets (EDF-39 and EDF-153), with accuracies of 87.3 and 85.4%, respectively.Keywords
This publication has 27 references indexed in Scilit:
- International Classification of Sleep Disorders2017
- Bioradiolocation-based sleep stage classification2016
- COMBINATION OF HETEROGENEOUS EEG FEATURE EXTRACTION METHODS AND STACKED SEQUENTIAL LEARNING FOR SLEEP STAGE CLASSIFICATIONInternational Journal of Neural Systems, 2013
- Overview of sleep & sleep disorders.2010
- Atlas, rules, and recording techniques for the scoring of cyclic alternating pattern (CAP) in human sleepSleep Medicine, 2001
- Random ForestsMachine Learning, 2001
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000
- Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEGIEEE Transactions on Biomedical Engineering, 2000
- Development of the polysomnographic database on CD‐ROMPsychiatry and Clinical Neurosciences, 1999
- Support vector machinesIEEE Intelligent Systems and their Applications, 1998