Automatic sleep staging method of single-lead electroencephalogram

Abstract

The invention discloses an automatic sleep staging method of a single-lead electroencephalogram. A training model comprises a feature extraction module and a staging optimization module, the feature extraction module comprises CNNs (convolutional neural networks) (1) and an Softmax layer (2), the staging optimization module comprises bi-directional LSTM (long-short term memory) recurrent neural networks (3) and a CRF (corticotropin releasing factor) conditional random field model (4), and the CNNs (1), the Softmax layer (2), the LSTM recurrent neural networks (3) and the CRF conditional random field model (4) are sequentially connected. The method only needs the single-lead sleep electroencephalogram, portable and comfortable sleep monitoring requirements are met, temporal and spatial characteristics of the electroencephalogram are sufficiently excavated according to the convolutional neural networks and the recurrent neural networks, the method has dynamic learning capacity and can adapt to great changed environments of diseases, the staging optimization module sufficiently considers relation between the front and the back of N 30s of electroencephalogram data, and the staging accuracy and the generalization ability of the model are improved.

Description

technical field [0001] The invention relates to the technical field of sleep monitoring, in particular to a single-lead EEG sleep automatic staging method. Background technique [0002] Sleep is central to human health, and sleep loss, abnormal sleep patterns or circadian rhythm disturbances can lead to a range of emotional, cognitive or physical health problems. According to the statistics of the World Health Organization, 27% of the world's people have sleep disorders, which cause economic losses of hundreds of billions of dollars every year, but most sleep disorders can be managed once they are diagnosed. Staging the sleep state of the human body through various physiological signals is an effective method for objectively evaluating sleep quality. [0003] At present, the typical method of clinical sleep monitoring is to use polysomnography (Polysomnography, PSG) to collect physiological signals during sleep, including electroencephalogram (EEG), oculoelectricity (EOG), ...

AI Technical Summary

Problems solved by technology

The disadvantage of this scheme is that the features rely on manual experience extraction, and only separate training and verification are performed on each 30s physiological electrical signal sample, without considering the connection between the sample and the previous and subsequent samples, and the accuracy and generalization ability need to be improved

Other sleep monitoring solutions based on wristband body movement, heart rate, and RF radio frequency signals have very low accuracy and cannot meet clinical requirements

Images